mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-03 09:53:45 +00:00
Merge branch 'main' into add-mongodb-vector_io
This commit is contained in:
Young Han
GitHub
commit
5e9d28f0b4
1791 changed files with 125464 additions and 386541 deletions
|
|
@ -5,7 +5,7 @@ omit =
|
|||
*/llama_stack/templates/*
|
||||
.venv/*
|
||||
*/llama_stack/cli/scripts/*
|
||||
*/llama_stack/ui/*
|
||||
*/llama_stack_ui/*
|
||||
*/llama_stack/distribution/ui/*
|
||||
*/llama_stack/strong_typing/*
|
||||
*/llama_stack/env.py
|
||||
|
|
|
|||
|
|
@ -72,7 +72,8 @@ runs:
|
|||
echo "New recordings detected, committing and pushing"
|
||||
git add tests/integration/
|
||||
|
||||
git commit -m "Recordings update from CI (suite: ${{ inputs.suite }})"
|
||||
git commit -m "Recordings update from CI (setup: ${{ inputs.setup }}, suite: ${{ inputs.suite }})"
|
||||
|
||||
git fetch origin ${{ github.ref_name }}
|
||||
git rebase origin/${{ github.ref_name }}
|
||||
echo "Rebased successfully"
|
||||
|
|
@ -88,6 +89,8 @@ runs:
|
|||
run: |
|
||||
# Ollama logs (if ollama container exists)
|
||||
sudo docker logs ollama > ollama-${{ inputs.inference-mode }}.log 2>&1 || true
|
||||
# vllm logs (if vllm container exists)
|
||||
sudo docker logs vllm > vllm-${{ inputs.inference-mode }}.log 2>&1 || true
|
||||
# Note: distro container logs are now dumped in integration-tests.sh before container is removed
|
||||
|
||||
- name: Upload logs
|
||||
|
|
|
|||
9
.github/actions/setup-vllm/action.yml
vendored
9
.github/actions/setup-vllm/action.yml
vendored
|
|
@ -11,13 +11,14 @@ runs:
|
|||
--name vllm \
|
||||
-p 8000:8000 \
|
||||
--privileged=true \
|
||||
quay.io/higginsd/vllm-cpu:65393ee064 \
|
||||
quay.io/higginsd/vllm-cpu:65393ee064-qwen3 \
|
||||
--host 0.0.0.0 \
|
||||
--port 8000 \
|
||||
--enable-auto-tool-choice \
|
||||
--tool-call-parser llama3_json \
|
||||
--model /root/.cache/Llama-3.2-1B-Instruct \
|
||||
--served-model-name meta-llama/Llama-3.2-1B-Instruct
|
||||
--tool-call-parser hermes \
|
||||
--model /root/.cache/Qwen3-0.6B \
|
||||
--served-model-name Qwen/Qwen3-0.6B \
|
||||
--max-model-len 8192
|
||||
|
||||
# Wait for vllm to be ready
|
||||
echo "Waiting for vllm to be ready..."
|
||||
|
|
|
|||
2
.github/dependabot.yml
vendored
2
.github/dependabot.yml
vendored
|
|
@ -22,7 +22,7 @@ updates:
|
|||
prefix: chore(python-deps)
|
||||
|
||||
- package-ecosystem: npm
|
||||
directory: "/llama_stack/ui"
|
||||
directory: "/llama_stack_ui"
|
||||
schedule:
|
||||
interval: "weekly"
|
||||
day: "saturday"
|
||||
|
|
|
|||
1
.github/workflows/README.md
vendored
1
.github/workflows/README.md
vendored
|
|
@ -18,6 +18,7 @@ Llama Stack uses GitHub Actions for Continuous Integration (CI). Below is a tabl
|
|||
| Python Package Build Test | [python-build-test.yml](python-build-test.yml) | Test building the llama-stack PyPI project |
|
||||
| Integration Tests (Record) | [record-integration-tests.yml](record-integration-tests.yml) | Run the integration test suite from tests/integration |
|
||||
| Check semantic PR titles | [semantic-pr.yml](semantic-pr.yml) | Ensure that PR titles follow the conventional commit spec |
|
||||
| Stainless SDK Builds | [stainless-builds.yml](stainless-builds.yml) | Build Stainless SDK from OpenAPI spec changes |
|
||||
| Close stale issues and PRs | [stale_bot.yml](stale_bot.yml) | Run the Stale Bot action |
|
||||
| Test External Providers Installed via Module | [test-external-provider-module.yml](test-external-provider-module.yml) | Test External Provider installation via Python module |
|
||||
| Test External API and Providers | [test-external.yml](test-external.yml) | Test the External API and Provider mechanisms |
|
||||
|
|
|
|||
2
.github/workflows/integration-auth-tests.yml
vendored
2
.github/workflows/integration-auth-tests.yml
vendored
|
|
@ -14,7 +14,7 @@ on:
|
|||
paths:
|
||||
- 'distributions/**'
|
||||
- 'src/llama_stack/**'
|
||||
- '!src/llama_stack/ui/**'
|
||||
- '!src/llama_stack_ui/**'
|
||||
- 'tests/integration/**'
|
||||
- 'uv.lock'
|
||||
- 'pyproject.toml'
|
||||
|
|
|
|||
38
.github/workflows/integration-tests.yml
vendored
38
.github/workflows/integration-tests.yml
vendored
|
|
@ -14,7 +14,7 @@ on:
|
|||
types: [opened, synchronize, reopened]
|
||||
paths:
|
||||
- 'src/llama_stack/**'
|
||||
- '!src/llama_stack/ui/**'
|
||||
- '!src/llama_stack_ui/**'
|
||||
- 'tests/**'
|
||||
- 'uv.lock'
|
||||
- 'pyproject.toml'
|
||||
|
|
@ -23,10 +23,10 @@ on:
|
|||
- '.github/actions/setup-test-environment/action.yml'
|
||||
- '.github/actions/run-and-record-tests/action.yml'
|
||||
- 'scripts/integration-tests.sh'
|
||||
- 'scripts/generate_ci_matrix.py'
|
||||
schedule:
|
||||
# If changing the cron schedule, update the provider in the test-matrix job
|
||||
- cron: '0 0 * * *' # (test latest client) Daily at 12 AM UTC
|
||||
- cron: '1 0 * * 0' # (test vllm) Weekly on Sunday at 1 AM UTC
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
test-all-client-versions:
|
||||
|
|
@ -44,8 +44,27 @@ concurrency:
|
|||
cancel-in-progress: true
|
||||
|
||||
jobs:
|
||||
generate-matrix:
|
||||
runs-on: ubuntu-latest
|
||||
outputs:
|
||||
matrix: ${{ steps.set-matrix.outputs.matrix }}
|
||||
steps:
|
||||
- name: Checkout repository
|
||||
uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
|
||||
|
||||
- name: Generate test matrix
|
||||
id: set-matrix
|
||||
run: |
|
||||
# Generate matrix from CI_MATRIX in tests/integration/suites.py
|
||||
# Supports schedule-based and manual input overrides
|
||||
MATRIX=$(PYTHONPATH=. python3 scripts/generate_ci_matrix.py \
|
||||
--schedule "${{ github.event.schedule }}" \
|
||||
--test-setup "${{ github.event.inputs.test-setup }}")
|
||||
echo "matrix=$MATRIX" >> $GITHUB_OUTPUT
|
||||
echo "Generated matrix: $MATRIX"
|
||||
|
||||
run-replay-mode-tests:
|
||||
needs: generate-matrix
|
||||
runs-on: ubuntu-latest
|
||||
name: ${{ format('Integration Tests ({0}, {1}, {2}, client={3}, {4})', matrix.client-type, matrix.config.setup, matrix.python-version, matrix.client-version, matrix.config.suite) }}
|
||||
|
||||
|
|
@ -56,18 +75,9 @@ jobs:
|
|||
# Use Python 3.13 only on nightly schedule (daily latest client test), otherwise use 3.12
|
||||
python-version: ${{ github.event.schedule == '0 0 * * *' && fromJSON('["3.12", "3.13"]') || fromJSON('["3.12"]') }}
|
||||
client-version: ${{ (github.event.schedule == '0 0 * * *' || github.event.inputs.test-all-client-versions == 'true') && fromJSON('["published", "latest"]') || fromJSON('["latest"]') }}
|
||||
# Define (setup, suite) pairs - they are always matched and cannot be independent
|
||||
# Weekly schedule (Sun 1 AM): vllm+base
|
||||
# Input test-setup=ollama-vision: ollama-vision+vision
|
||||
# Default (including test-setup=ollama): ollama+base, ollama-vision+vision, gpt+responses
|
||||
config: >-
|
||||
${{
|
||||
github.event.schedule == '1 0 * * 0'
|
||||
&& fromJSON('[{"setup": "vllm", "suite": "base"}]')
|
||||
|| github.event.inputs.test-setup == 'ollama-vision'
|
||||
&& fromJSON('[{"setup": "ollama-vision", "suite": "vision"}]')
|
||||
|| fromJSON('[{"setup": "ollama", "suite": "base"}, {"setup": "ollama-vision", "suite": "vision"}, {"setup": "gpt", "suite": "responses"}]')
|
||||
}}
|
||||
# Test configurations: Generated from CI_MATRIX in tests/integration/suites.py
|
||||
# See scripts/generate_ci_matrix.py for generation logic
|
||||
config: ${{ fromJSON(needs.generate-matrix.outputs.matrix).include }}
|
||||
|
||||
steps:
|
||||
- name: Checkout repository
|
||||
|
|
|
|||
|
|
@ -13,7 +13,7 @@ on:
|
|||
- 'release-[0-9]+.[0-9]+.x'
|
||||
paths:
|
||||
- 'src/llama_stack/**'
|
||||
- '!src/llama_stack/ui/**'
|
||||
- '!src/llama_stack_ui/**'
|
||||
- 'tests/integration/vector_io/**'
|
||||
- 'uv.lock'
|
||||
- 'pyproject.toml'
|
||||
|
|
|
|||
15
.github/workflows/pre-commit.yml
vendored
15
.github/workflows/pre-commit.yml
vendored
|
|
@ -43,14 +43,14 @@ jobs:
|
|||
with:
|
||||
node-version: '20'
|
||||
cache: 'npm'
|
||||
cache-dependency-path: 'src/llama_stack/ui/'
|
||||
cache-dependency-path: 'src/llama_stack_ui/'
|
||||
|
||||
- name: Set up uv
|
||||
uses: astral-sh/setup-uv@85856786d1ce8acfbcc2f13a5f3fbd6b938f9f41 # v7.1.2
|
||||
|
||||
- name: Install npm dependencies
|
||||
run: npm ci
|
||||
working-directory: src/llama_stack/ui
|
||||
working-directory: src/llama_stack_ui
|
||||
|
||||
- name: Install pre-commit
|
||||
run: python -m pip install pre-commit
|
||||
|
|
@ -165,3 +165,14 @@ jobs:
|
|||
echo "::error::Full mypy failed. Reproduce locally with 'uv run pre-commit run mypy-full --hook-stage manual --all-files'."
|
||||
fi
|
||||
exit $status
|
||||
|
||||
- name: Check if any unused recordings
|
||||
run: |
|
||||
set -e
|
||||
PYTHONPATH=$PWD uv run ./scripts/cleanup_recordings.py --delete
|
||||
changes=$(git status --short tests/integration | grep 'recordings' || true)
|
||||
if [ -n "$changes" ]; then
|
||||
echo "::error::Unused integration recordings detected. Run 'PYTHONPATH=$(pwd) uv run ./scripts/cleanup_recordings.py --delete' locally and commit the deletions."
|
||||
echo "$changes"
|
||||
exit 1
|
||||
fi
|
||||
|
|
|
|||
2
.github/workflows/python-build-test.yml
vendored
2
.github/workflows/python-build-test.yml
vendored
|
|
@ -10,7 +10,7 @@ on:
|
|||
branches:
|
||||
- main
|
||||
paths-ignore:
|
||||
- 'src/llama_stack/ui/**'
|
||||
- 'src/llama_stack_ui/**'
|
||||
|
||||
jobs:
|
||||
build:
|
||||
|
|
|
|||
110
.github/workflows/stainless-builds.yml
vendored
Normal file
110
.github/workflows/stainless-builds.yml
vendored
Normal file
|
|
@ -0,0 +1,110 @@
|
|||
name: Stainless SDK Builds
|
||||
run-name: Build Stainless SDK from OpenAPI spec changes
|
||||
|
||||
# This workflow uses pull_request_target, which allows it to run on pull requests
|
||||
# from forks with access to secrets. This is safe because the workflow definition
|
||||
# comes from the base branch (trusted), and the action only reads OpenAPI spec
|
||||
# files without executing any code from the PR.
|
||||
|
||||
on:
|
||||
pull_request_target:
|
||||
types:
|
||||
- opened
|
||||
- synchronize
|
||||
- reopened
|
||||
- closed
|
||||
paths:
|
||||
- "client-sdks/stainless/**"
|
||||
|
||||
concurrency:
|
||||
group: ${{ github.workflow }}-${{ github.event.pull_request.number }}
|
||||
cancel-in-progress: true
|
||||
|
||||
env:
|
||||
# Stainless organization name.
|
||||
STAINLESS_ORG: llamastack
|
||||
|
||||
# Stainless project name.
|
||||
STAINLESS_PROJECT: llama-stack-client
|
||||
|
||||
# Path to your OpenAPI spec.
|
||||
OAS_PATH: ./client-sdks/stainless/openapi.yml
|
||||
|
||||
# Path to your Stainless config. Optional; only provide this if you prefer
|
||||
# to maintain the ground truth Stainless config in your own repo.
|
||||
CONFIG_PATH: ./client-sdks/stainless/config.yml
|
||||
|
||||
# When to fail the job based on build conclusion.
|
||||
# Options: "never" | "note" | "warning" | "error" | "fatal".
|
||||
FAIL_ON: error
|
||||
|
||||
# In your repo secrets, configure:
|
||||
# - STAINLESS_API_KEY: a Stainless API key, which you can generate on the
|
||||
# Stainless organization dashboard
|
||||
|
||||
jobs:
|
||||
preview:
|
||||
if: github.event.action != 'closed'
|
||||
runs-on: ubuntu-latest
|
||||
permissions:
|
||||
contents: read
|
||||
pull-requests: write
|
||||
steps:
|
||||
# Checkout the PR's code to access the OpenAPI spec and config files.
|
||||
# This is necessary to read the spec/config from the PR (including from forks).
|
||||
- name: Checkout repository
|
||||
uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
|
||||
with:
|
||||
repository: ${{ github.event.pull_request.head.repo.full_name }}
|
||||
ref: ${{ github.event.pull_request.head.sha }}
|
||||
fetch-depth: 2
|
||||
|
||||
# This action builds preview SDKs from the OpenAPI spec changes and
|
||||
# posts/updates a comment on the PR with build results and links to the preview.
|
||||
- name: Run preview builds
|
||||
uses: stainless-api/upload-openapi-spec-action/preview@32823b096b4319c53ee948d702d9052873af485f # 1.6.0
|
||||
with:
|
||||
stainless_api_key: ${{ secrets.STAINLESS_API_KEY }}
|
||||
org: ${{ env.STAINLESS_ORG }}
|
||||
project: ${{ env.STAINLESS_PROJECT }}
|
||||
oas_path: ${{ env.OAS_PATH }}
|
||||
config_path: ${{ env.CONFIG_PATH }}
|
||||
fail_on: ${{ env.FAIL_ON }}
|
||||
base_sha: ${{ github.event.pull_request.base.sha }}
|
||||
base_ref: ${{ github.event.pull_request.base.ref }}
|
||||
head_sha: ${{ github.event.pull_request.head.sha }}
|
||||
|
||||
merge:
|
||||
if: github.event.action == 'closed' && github.event.pull_request.merged == true
|
||||
runs-on: ubuntu-latest
|
||||
permissions:
|
||||
contents: read
|
||||
pull-requests: write
|
||||
steps:
|
||||
# Checkout the PR's code to access the OpenAPI spec and config files.
|
||||
# This is necessary to read the spec/config from the PR (including from forks).
|
||||
- name: Checkout repository
|
||||
uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
|
||||
with:
|
||||
repository: ${{ github.event.pull_request.head.repo.full_name }}
|
||||
ref: ${{ github.event.pull_request.head.sha }}
|
||||
fetch-depth: 2
|
||||
|
||||
# Note that this only merges in changes that happened on the last build on
|
||||
# preview/${{ github.head_ref }}. It's possible that there are OAS/config
|
||||
# changes that haven't been built, if the preview-sdk job didn't finish
|
||||
# before this step starts. In theory we want to wait for all builds
|
||||
# against preview/${{ github.head_ref }} to complete, but assuming that
|
||||
# the preview-sdk job happens before the PR merge, it should be fine.
|
||||
- name: Run merge build
|
||||
uses: stainless-api/upload-openapi-spec-action/merge@32823b096b4319c53ee948d702d9052873af485f # 1.6.0
|
||||
with:
|
||||
stainless_api_key: ${{ secrets.STAINLESS_API_KEY }}
|
||||
org: ${{ env.STAINLESS_ORG }}
|
||||
project: ${{ env.STAINLESS_PROJECT }}
|
||||
oas_path: ${{ env.OAS_PATH }}
|
||||
config_path: ${{ env.CONFIG_PATH }}
|
||||
fail_on: ${{ env.FAIL_ON }}
|
||||
base_sha: ${{ github.event.pull_request.base.sha }}
|
||||
base_ref: ${{ github.event.pull_request.base.ref }}
|
||||
head_sha: ${{ github.event.pull_request.head.sha }}
|
||||
2
.github/workflows/test-external.yml
vendored
2
.github/workflows/test-external.yml
vendored
|
|
@ -9,7 +9,7 @@ on:
|
|||
branches: [ main ]
|
||||
paths:
|
||||
- 'src/llama_stack/**'
|
||||
- '!src/llama_stack/ui/**'
|
||||
- '!src/llama_stack_ui/**'
|
||||
- 'tests/integration/**'
|
||||
- 'uv.lock'
|
||||
- 'pyproject.toml'
|
||||
|
|
|
|||
12
.github/workflows/ui-unit-tests.yml
vendored
12
.github/workflows/ui-unit-tests.yml
vendored
|
|
@ -8,7 +8,7 @@ on:
|
|||
pull_request:
|
||||
branches: [ main ]
|
||||
paths:
|
||||
- 'src/llama_stack/ui/**'
|
||||
- 'src/llama_stack_ui/**'
|
||||
- '.github/workflows/ui-unit-tests.yml' # This workflow
|
||||
workflow_dispatch:
|
||||
|
||||
|
|
@ -33,22 +33,22 @@ jobs:
|
|||
with:
|
||||
node-version: ${{ matrix.node-version }}
|
||||
cache: 'npm'
|
||||
cache-dependency-path: 'src/llama_stack/ui/package-lock.json'
|
||||
cache-dependency-path: 'src/llama_stack_ui/package-lock.json'
|
||||
|
||||
- name: Install dependencies
|
||||
working-directory: src/llama_stack/ui
|
||||
working-directory: src/llama_stack_ui
|
||||
run: npm ci
|
||||
|
||||
- name: Run linting
|
||||
working-directory: src/llama_stack/ui
|
||||
working-directory: src/llama_stack_ui
|
||||
run: npm run lint
|
||||
|
||||
- name: Run format check
|
||||
working-directory: src/llama_stack/ui
|
||||
working-directory: src/llama_stack_ui
|
||||
run: npm run format:check
|
||||
|
||||
- name: Run unit tests
|
||||
working-directory: src/llama_stack/ui
|
||||
working-directory: src/llama_stack_ui
|
||||
env:
|
||||
CI: true
|
||||
|
||||
|
|
|
|||
2
.github/workflows/unit-tests.yml
vendored
2
.github/workflows/unit-tests.yml
vendored
|
|
@ -13,7 +13,7 @@ on:
|
|||
- 'release-[0-9]+.[0-9]+.x'
|
||||
paths:
|
||||
- 'src/llama_stack/**'
|
||||
- '!src/llama_stack/ui/**'
|
||||
- '!src/llama_stack_ui/**'
|
||||
- 'tests/unit/**'
|
||||
- 'uv.lock'
|
||||
- 'pyproject.toml'
|
||||
|
|
|
|||
|
|
@ -161,7 +161,7 @@ repos:
|
|||
name: Format & Lint UI
|
||||
entry: bash ./scripts/run-ui-linter.sh
|
||||
language: system
|
||||
files: ^src/llama_stack/ui/.*\.(ts|tsx)$
|
||||
files: ^src/llama_stack_ui/.*\.(ts|tsx)$
|
||||
pass_filenames: false
|
||||
require_serial: true
|
||||
|
||||
|
|
|
|||
|
|
@ -1,7 +1,7 @@
|
|||
These are the source-of-truth configuration files used to generate the Stainless client SDKs via Stainless.
|
||||
|
||||
- `openapi.yml`: this is the OpenAPI specification for the Llama Stack API.
|
||||
- `openapi.stainless.yml`: this is the Stainless _configuration_ which instructs Stainless how to generate the client SDKs.
|
||||
- `config.yml`: this is the Stainless _configuration_ which instructs Stainless how to generate the client SDKs.
|
||||
|
||||
A small side note: notice the `.yml` suffixes since Stainless uses that suffix typically for its configuration files.
|
||||
|
||||
|
|
|
|||
521
client-sdks/stainless/config.yml
Normal file
521
client-sdks/stainless/config.yml
Normal file
|
|
@ -0,0 +1,521 @@
|
|||
# yaml-language-server: $schema=https://app.stainlessapi.com/config-internal.schema.json
|
||||
|
||||
organization:
|
||||
# Name of your organization or company, used to determine the name of the client
|
||||
# and headings.
|
||||
name: llama-stack-client
|
||||
docs: https://llama-stack.readthedocs.io/en/latest/
|
||||
contact: llamastack@meta.com
|
||||
security:
|
||||
- {}
|
||||
- BearerAuth: []
|
||||
security_schemes:
|
||||
BearerAuth:
|
||||
type: http
|
||||
scheme: bearer
|
||||
# `targets` define the output targets and their customization options, such as
|
||||
# whether to emit the Node SDK and what it's package name should be.
|
||||
targets:
|
||||
node:
|
||||
package_name: llama-stack-client
|
||||
production_repo: llamastack/llama-stack-client-typescript
|
||||
publish:
|
||||
npm: false
|
||||
python:
|
||||
package_name: llama_stack_client
|
||||
production_repo: llamastack/llama-stack-client-python
|
||||
options:
|
||||
use_uv: true
|
||||
publish:
|
||||
pypi: true
|
||||
project_name: llama_stack_client
|
||||
kotlin:
|
||||
reverse_domain: com.llama_stack_client.api
|
||||
production_repo: null
|
||||
publish:
|
||||
maven: false
|
||||
go:
|
||||
package_name: llama-stack-client
|
||||
production_repo: llamastack/llama-stack-client-go
|
||||
options:
|
||||
enable_v2: true
|
||||
back_compat_use_shared_package: false
|
||||
|
||||
# `client_settings` define settings for the API client, such as extra constructor
|
||||
# arguments (used for authentication), retry behavior, idempotency, etc.
|
||||
client_settings:
|
||||
default_env_prefix: LLAMA_STACK_CLIENT
|
||||
opts:
|
||||
api_key:
|
||||
type: string
|
||||
read_env: LLAMA_STACK_CLIENT_API_KEY
|
||||
auth: { security_scheme: BearerAuth }
|
||||
nullable: true
|
||||
|
||||
# `environments` are a map of the name of the environment (e.g. "sandbox",
|
||||
# "production") to the corresponding url to use.
|
||||
environments:
|
||||
production: http://any-hosted-llama-stack.com
|
||||
|
||||
# `pagination` defines [pagination schemes] which provides a template to match
|
||||
# endpoints and generate next-page and auto-pagination helpers in the SDKs.
|
||||
pagination:
|
||||
- name: datasets_iterrows
|
||||
type: offset
|
||||
request:
|
||||
dataset_id:
|
||||
type: string
|
||||
start_index:
|
||||
type: integer
|
||||
x-stainless-pagination-property:
|
||||
purpose: offset_count_param
|
||||
limit:
|
||||
type: integer
|
||||
response:
|
||||
data:
|
||||
type: array
|
||||
items:
|
||||
type: object
|
||||
next_index:
|
||||
type: integer
|
||||
x-stainless-pagination-property:
|
||||
purpose: offset_count_start_field
|
||||
- name: openai_cursor_page
|
||||
type: cursor
|
||||
request:
|
||||
limit:
|
||||
type: integer
|
||||
after:
|
||||
type: string
|
||||
x-stainless-pagination-property:
|
||||
purpose: next_cursor_param
|
||||
response:
|
||||
data:
|
||||
type: array
|
||||
items: {}
|
||||
has_more:
|
||||
type: boolean
|
||||
last_id:
|
||||
type: string
|
||||
x-stainless-pagination-property:
|
||||
purpose: next_cursor_field
|
||||
# `resources` define the structure and organziation for your API, such as how
|
||||
# methods and models are grouped together and accessed. See the [configuration
|
||||
# guide] for more information.
|
||||
#
|
||||
# [configuration guide]:
|
||||
# https://app.stainlessapi.com/docs/guides/configure#resources
|
||||
resources:
|
||||
$shared:
|
||||
models:
|
||||
interleaved_content_item: InterleavedContentItem
|
||||
interleaved_content: InterleavedContent
|
||||
param_type: ParamType
|
||||
safety_violation: SafetyViolation
|
||||
sampling_params: SamplingParams
|
||||
scoring_result: ScoringResult
|
||||
system_message: SystemMessage
|
||||
query_result: RAGQueryResult
|
||||
document: RAGDocument
|
||||
query_config: RAGQueryConfig
|
||||
toolgroups:
|
||||
models:
|
||||
tool_group: ToolGroup
|
||||
list_tool_groups_response: ListToolGroupsResponse
|
||||
methods:
|
||||
register: post /v1/toolgroups
|
||||
get: get /v1/toolgroups/{toolgroup_id}
|
||||
list: get /v1/toolgroups
|
||||
unregister: delete /v1/toolgroups/{toolgroup_id}
|
||||
tools:
|
||||
methods:
|
||||
get: get /v1/tools/{tool_name}
|
||||
list:
|
||||
endpoint: get /v1/tools
|
||||
paginated: false
|
||||
|
||||
tool_runtime:
|
||||
models:
|
||||
tool_def: ToolDef
|
||||
tool_invocation_result: ToolInvocationResult
|
||||
methods:
|
||||
list_tools:
|
||||
endpoint: get /v1/tool-runtime/list-tools
|
||||
paginated: false
|
||||
invoke_tool: post /v1/tool-runtime/invoke
|
||||
subresources:
|
||||
rag_tool:
|
||||
methods:
|
||||
insert: post /v1/tool-runtime/rag-tool/insert
|
||||
query: post /v1/tool-runtime/rag-tool/query
|
||||
|
||||
responses:
|
||||
models:
|
||||
response_object_stream: OpenAIResponseObjectStream
|
||||
response_object: OpenAIResponseObject
|
||||
methods:
|
||||
create:
|
||||
type: http
|
||||
endpoint: post /v1/responses
|
||||
streaming:
|
||||
stream_event_model: responses.response_object_stream
|
||||
param_discriminator: stream
|
||||
retrieve: get /v1/responses/{response_id}
|
||||
list:
|
||||
type: http
|
||||
endpoint: get /v1/responses
|
||||
delete:
|
||||
type: http
|
||||
endpoint: delete /v1/responses/{response_id}
|
||||
subresources:
|
||||
input_items:
|
||||
methods:
|
||||
list:
|
||||
type: http
|
||||
endpoint: get /v1/responses/{response_id}/input_items
|
||||
|
||||
prompts:
|
||||
models:
|
||||
prompt: Prompt
|
||||
list_prompts_response: ListPromptsResponse
|
||||
methods:
|
||||
create: post /v1/prompts
|
||||
list:
|
||||
endpoint: get /v1/prompts
|
||||
paginated: false
|
||||
retrieve: get /v1/prompts/{prompt_id}
|
||||
update: post /v1/prompts/{prompt_id}
|
||||
delete: delete /v1/prompts/{prompt_id}
|
||||
set_default_version: post /v1/prompts/{prompt_id}/set-default-version
|
||||
subresources:
|
||||
versions:
|
||||
methods:
|
||||
list:
|
||||
endpoint: get /v1/prompts/{prompt_id}/versions
|
||||
paginated: false
|
||||
|
||||
conversations:
|
||||
models:
|
||||
conversation_object: Conversation
|
||||
methods:
|
||||
create:
|
||||
type: http
|
||||
endpoint: post /v1/conversations
|
||||
retrieve: get /v1/conversations/{conversation_id}
|
||||
update:
|
||||
type: http
|
||||
endpoint: post /v1/conversations/{conversation_id}
|
||||
delete:
|
||||
type: http
|
||||
endpoint: delete /v1/conversations/{conversation_id}
|
||||
subresources:
|
||||
items:
|
||||
methods:
|
||||
get:
|
||||
type: http
|
||||
endpoint: get /v1/conversations/{conversation_id}/items/{item_id}
|
||||
list:
|
||||
type: http
|
||||
endpoint: get /v1/conversations/{conversation_id}/items
|
||||
create:
|
||||
type: http
|
||||
endpoint: post /v1/conversations/{conversation_id}/items
|
||||
|
||||
inspect:
|
||||
models:
|
||||
healthInfo: HealthInfo
|
||||
providerInfo: ProviderInfo
|
||||
routeInfo: RouteInfo
|
||||
versionInfo: VersionInfo
|
||||
methods:
|
||||
health: get /v1/health
|
||||
version: get /v1/version
|
||||
|
||||
embeddings:
|
||||
models:
|
||||
create_embeddings_response: OpenAIEmbeddingsResponse
|
||||
methods:
|
||||
create: post /v1/embeddings
|
||||
|
||||
chat:
|
||||
models:
|
||||
chat_completion_chunk: OpenAIChatCompletionChunk
|
||||
subresources:
|
||||
completions:
|
||||
methods:
|
||||
create:
|
||||
type: http
|
||||
endpoint: post /v1/chat/completions
|
||||
streaming:
|
||||
stream_event_model: chat.chat_completion_chunk
|
||||
param_discriminator: stream
|
||||
list:
|
||||
type: http
|
||||
endpoint: get /v1/chat/completions
|
||||
retrieve:
|
||||
type: http
|
||||
endpoint: get /v1/chat/completions/{completion_id}
|
||||
completions:
|
||||
methods:
|
||||
create:
|
||||
type: http
|
||||
endpoint: post /v1/completions
|
||||
streaming:
|
||||
param_discriminator: stream
|
||||
|
||||
vector_io:
|
||||
models:
|
||||
queryChunksResponse: QueryChunksResponse
|
||||
methods:
|
||||
insert: post /v1/vector-io/insert
|
||||
query: post /v1/vector-io/query
|
||||
|
||||
vector_stores:
|
||||
models:
|
||||
vector_store: VectorStoreObject
|
||||
list_vector_stores_response: VectorStoreListResponse
|
||||
vector_store_delete_response: VectorStoreDeleteResponse
|
||||
vector_store_search_response: VectorStoreSearchResponsePage
|
||||
methods:
|
||||
create: post /v1/vector_stores
|
||||
list:
|
||||
endpoint: get /v1/vector_stores
|
||||
retrieve: get /v1/vector_stores/{vector_store_id}
|
||||
update: post /v1/vector_stores/{vector_store_id}
|
||||
delete: delete /v1/vector_stores/{vector_store_id}
|
||||
search: post /v1/vector_stores/{vector_store_id}/search
|
||||
subresources:
|
||||
files:
|
||||
models:
|
||||
vector_store_file: VectorStoreFileObject
|
||||
methods:
|
||||
list: get /v1/vector_stores/{vector_store_id}/files
|
||||
retrieve: get /v1/vector_stores/{vector_store_id}/files/{file_id}
|
||||
update: post /v1/vector_stores/{vector_store_id}/files/{file_id}
|
||||
delete: delete /v1/vector_stores/{vector_store_id}/files/{file_id}
|
||||
create: post /v1/vector_stores/{vector_store_id}/files
|
||||
content: get /v1/vector_stores/{vector_store_id}/files/{file_id}/content
|
||||
file_batches:
|
||||
models:
|
||||
vector_store_file_batches: VectorStoreFileBatchObject
|
||||
list_vector_store_files_in_batch_response: VectorStoreFilesListInBatchResponse
|
||||
methods:
|
||||
create: post /v1/vector_stores/{vector_store_id}/file_batches
|
||||
retrieve: get /v1/vector_stores/{vector_store_id}/file_batches/{batch_id}
|
||||
list_files: get /v1/vector_stores/{vector_store_id}/file_batches/{batch_id}/files
|
||||
cancel: post /v1/vector_stores/{vector_store_id}/file_batches/{batch_id}/cancel
|
||||
|
||||
models:
|
||||
models:
|
||||
model: OpenAIModel
|
||||
list_models_response: OpenAIListModelsResponse
|
||||
methods:
|
||||
list:
|
||||
endpoint: get /v1/models
|
||||
paginated: false
|
||||
retrieve: get /v1/models/{model_id}
|
||||
register: post /v1/models
|
||||
unregister: delete /v1/models/{model_id}
|
||||
subresources:
|
||||
openai:
|
||||
methods:
|
||||
list:
|
||||
endpoint: get /v1/models
|
||||
paginated: false
|
||||
|
||||
providers:
|
||||
models:
|
||||
list_providers_response: ListProvidersResponse
|
||||
methods:
|
||||
list:
|
||||
endpoint: get /v1/providers
|
||||
paginated: false
|
||||
retrieve: get /v1/providers/{provider_id}
|
||||
|
||||
routes:
|
||||
models:
|
||||
list_routes_response: ListRoutesResponse
|
||||
methods:
|
||||
list:
|
||||
endpoint: get /v1/inspect/routes
|
||||
paginated: false
|
||||
|
||||
moderations:
|
||||
models:
|
||||
create_response: ModerationObject
|
||||
methods:
|
||||
create: post /v1/moderations
|
||||
|
||||
safety:
|
||||
models:
|
||||
run_shield_response: RunShieldResponse
|
||||
methods:
|
||||
run_shield: post /v1/safety/run-shield
|
||||
|
||||
shields:
|
||||
models:
|
||||
shield: Shield
|
||||
list_shields_response: ListShieldsResponse
|
||||
methods:
|
||||
retrieve: get /v1/shields/{identifier}
|
||||
list:
|
||||
endpoint: get /v1/shields
|
||||
paginated: false
|
||||
register: post /v1/shields
|
||||
delete: delete /v1/shields/{identifier}
|
||||
|
||||
scoring:
|
||||
methods:
|
||||
score: post /v1/scoring/score
|
||||
score_batch: post /v1/scoring/score-batch
|
||||
scoring_functions:
|
||||
methods:
|
||||
retrieve: get /v1/scoring-functions/{scoring_fn_id}
|
||||
list:
|
||||
endpoint: get /v1/scoring-functions
|
||||
paginated: false
|
||||
register: post /v1/scoring-functions
|
||||
models:
|
||||
scoring_fn: ScoringFn
|
||||
scoring_fn_params: ScoringFnParams
|
||||
list_scoring_functions_response: ListScoringFunctionsResponse
|
||||
|
||||
files:
|
||||
methods:
|
||||
create: post /v1/files
|
||||
list: get /v1/files
|
||||
retrieve: get /v1/files/{file_id}
|
||||
delete: delete /v1/files/{file_id}
|
||||
content: get /v1/files/{file_id}/content
|
||||
models:
|
||||
file: OpenAIFileObject
|
||||
list_files_response: ListOpenAIFileResponse
|
||||
delete_file_response: OpenAIFileDeleteResponse
|
||||
|
||||
alpha:
|
||||
subresources:
|
||||
inference:
|
||||
methods:
|
||||
rerank: post /v1alpha/inference/rerank
|
||||
|
||||
post_training:
|
||||
models:
|
||||
algorithm_config: AlgorithmConfig
|
||||
post_training_job: PostTrainingJob
|
||||
list_post_training_jobs_response: ListPostTrainingJobsResponse
|
||||
methods:
|
||||
preference_optimize: post /v1alpha/post-training/preference-optimize
|
||||
supervised_fine_tune: post /v1alpha/post-training/supervised-fine-tune
|
||||
subresources:
|
||||
job:
|
||||
methods:
|
||||
artifacts: get /v1alpha/post-training/job/artifacts
|
||||
cancel: post /v1alpha/post-training/job/cancel
|
||||
status: get /v1alpha/post-training/job/status
|
||||
list:
|
||||
endpoint: get /v1alpha/post-training/jobs
|
||||
paginated: false
|
||||
|
||||
benchmarks:
|
||||
methods:
|
||||
retrieve: get /v1alpha/eval/benchmarks/{benchmark_id}
|
||||
list:
|
||||
endpoint: get /v1alpha/eval/benchmarks
|
||||
paginated: false
|
||||
register: post /v1alpha/eval/benchmarks
|
||||
models:
|
||||
benchmark: Benchmark
|
||||
list_benchmarks_response: ListBenchmarksResponse
|
||||
|
||||
eval:
|
||||
methods:
|
||||
evaluate_rows: post /v1alpha/eval/benchmarks/{benchmark_id}/evaluations
|
||||
run_eval: post /v1alpha/eval/benchmarks/{benchmark_id}/jobs
|
||||
evaluate_rows_alpha: post /v1alpha/eval/benchmarks/{benchmark_id}/evaluations
|
||||
run_eval_alpha: post /v1alpha/eval/benchmarks/{benchmark_id}/jobs
|
||||
|
||||
subresources:
|
||||
jobs:
|
||||
methods:
|
||||
cancel: delete /v1alpha/eval/benchmarks/{benchmark_id}/jobs/{job_id}
|
||||
status: get /v1alpha/eval/benchmarks/{benchmark_id}/jobs/{job_id}
|
||||
retrieve: get /v1alpha/eval/benchmarks/{benchmark_id}/jobs/{job_id}/result
|
||||
models:
|
||||
evaluate_response: EvaluateResponse
|
||||
benchmark_config: BenchmarkConfig
|
||||
job: Job
|
||||
|
||||
beta:
|
||||
subresources:
|
||||
datasets:
|
||||
models:
|
||||
list_datasets_response: ListDatasetsResponse
|
||||
methods:
|
||||
register: post /v1beta/datasets
|
||||
retrieve: get /v1beta/datasets/{dataset_id}
|
||||
list:
|
||||
endpoint: get /v1beta/datasets
|
||||
paginated: false
|
||||
unregister: delete /v1beta/datasets/{dataset_id}
|
||||
iterrows: get /v1beta/datasetio/iterrows/{dataset_id}
|
||||
appendrows: post /v1beta/datasetio/append-rows/{dataset_id}
|
||||
|
||||
settings:
|
||||
license: MIT
|
||||
unwrap_response_fields: [data]
|
||||
|
||||
openapi:
|
||||
transformations:
|
||||
- command: mergeObject
|
||||
reason: Better return_type using enum
|
||||
args:
|
||||
target:
|
||||
- "$.components.schemas"
|
||||
object:
|
||||
ReturnType:
|
||||
additionalProperties: false
|
||||
properties:
|
||||
type:
|
||||
enum:
|
||||
- string
|
||||
- number
|
||||
- boolean
|
||||
- array
|
||||
- object
|
||||
- json
|
||||
- union
|
||||
- chat_completion_input
|
||||
- completion_input
|
||||
- agent_turn_input
|
||||
required:
|
||||
- type
|
||||
type: object
|
||||
- command: replaceProperties
|
||||
reason: Replace return type properties with better model (see above)
|
||||
args:
|
||||
filter:
|
||||
only:
|
||||
- "$.components.schemas.ScoringFn.properties.return_type"
|
||||
- "$.components.schemas.RegisterScoringFunctionRequest.properties.return_type"
|
||||
value:
|
||||
$ref: "#/components/schemas/ReturnType"
|
||||
- command: oneOfToAnyOf
|
||||
reason: Prism (mock server) doesn't like one of our requests as it technically matches multiple variants
|
||||
|
||||
# `readme` is used to configure the code snippets that will be rendered in the
|
||||
# README.md of various SDKs. In particular, you can change the `headline`
|
||||
# snippet's endpoint and the arguments to call it with.
|
||||
readme:
|
||||
example_requests:
|
||||
default:
|
||||
type: request
|
||||
endpoint: post /v1/chat/completions
|
||||
params: &ref_0 {}
|
||||
headline:
|
||||
type: request
|
||||
endpoint: post /v1/models
|
||||
params: *ref_0
|
||||
pagination:
|
||||
type: request
|
||||
endpoint: post /v1/chat/completions
|
||||
params: {}
|
||||
File diff suppressed because it is too large
Load diff
|
|
@ -47,7 +47,7 @@ RUN set -eux; \
|
|||
exit 1; \
|
||||
fi
|
||||
|
||||
RUN pip install --no-cache-dir uv
|
||||
RUN pip install --no-cache uv
|
||||
ENV UV_SYSTEM_PYTHON=1
|
||||
|
||||
ENV INSTALL_MODE=${INSTALL_MODE}
|
||||
|
|
@ -72,7 +72,7 @@ RUN set -eux; \
|
|||
echo "LLAMA_STACK_CLIENT_DIR is set but $LLAMA_STACK_CLIENT_DIR does not exist" >&2; \
|
||||
exit 1; \
|
||||
fi; \
|
||||
uv pip install --no-cache-dir -e "$LLAMA_STACK_CLIENT_DIR"; \
|
||||
uv pip install --no-cache -e "$LLAMA_STACK_CLIENT_DIR"; \
|
||||
fi;
|
||||
|
||||
# Install llama-stack
|
||||
|
|
@ -88,22 +88,22 @@ RUN set -eux; \
|
|||
fi; \
|
||||
if [ -n "$SAVED_UV_EXTRA_INDEX_URL" ] && [ -n "$SAVED_UV_INDEX_STRATEGY" ]; then \
|
||||
UV_EXTRA_INDEX_URL="$SAVED_UV_EXTRA_INDEX_URL" UV_INDEX_STRATEGY="$SAVED_UV_INDEX_STRATEGY" \
|
||||
uv pip install --no-cache-dir -e "$LLAMA_STACK_DIR"; \
|
||||
uv pip install --no-cache -e "$LLAMA_STACK_DIR"; \
|
||||
else \
|
||||
uv pip install --no-cache-dir -e "$LLAMA_STACK_DIR"; \
|
||||
uv pip install --no-cache -e "$LLAMA_STACK_DIR"; \
|
||||
fi; \
|
||||
elif [ "$INSTALL_MODE" = "test-pypi" ]; then \
|
||||
uv pip install --no-cache-dir fastapi libcst; \
|
||||
uv pip install --no-cache fastapi libcst; \
|
||||
if [ -n "$TEST_PYPI_VERSION" ]; then \
|
||||
uv pip install --no-cache-dir --extra-index-url https://test.pypi.org/simple/ --index-strategy unsafe-best-match "llama-stack==$TEST_PYPI_VERSION"; \
|
||||
uv pip install --no-cache --extra-index-url https://test.pypi.org/simple/ --index-strategy unsafe-best-match "llama-stack==$TEST_PYPI_VERSION"; \
|
||||
else \
|
||||
uv pip install --no-cache-dir --extra-index-url https://test.pypi.org/simple/ --index-strategy unsafe-best-match llama-stack; \
|
||||
uv pip install --no-cache --extra-index-url https://test.pypi.org/simple/ --index-strategy unsafe-best-match llama-stack; \
|
||||
fi; \
|
||||
else \
|
||||
if [ -n "$PYPI_VERSION" ]; then \
|
||||
uv pip install --no-cache-dir "llama-stack==$PYPI_VERSION"; \
|
||||
uv pip install --no-cache "llama-stack==$PYPI_VERSION"; \
|
||||
else \
|
||||
uv pip install --no-cache-dir llama-stack; \
|
||||
uv pip install --no-cache llama-stack; \
|
||||
fi; \
|
||||
fi;
|
||||
|
||||
|
|
@ -117,7 +117,7 @@ RUN set -eux; \
|
|||
fi; \
|
||||
deps="$(llama stack list-deps "$DISTRO_NAME")"; \
|
||||
if [ -n "$deps" ]; then \
|
||||
printf '%s\n' "$deps" | xargs -L1 uv pip install --no-cache-dir; \
|
||||
printf '%s\n' "$deps" | xargs -L1 uv pip install --no-cache; \
|
||||
fi
|
||||
|
||||
# Cleanup
|
||||
|
|
|
|||
|
|
@ -35,9 +35,6 @@ Here are the key topics that will help you build effective AI applications:
|
|||
- **[Telemetry](./telemetry.mdx)** - Monitor and analyze your agents' performance and behavior
|
||||
- **[Safety](./safety.mdx)** - Implement guardrails and safety measures to ensure responsible AI behavior
|
||||
|
||||
### 🎮 **Interactive Development**
|
||||
- **[Playground](./playground.mdx)** - Interactive environment for testing and developing applications
|
||||
|
||||
## Application Patterns
|
||||
|
||||
### 🤖 **Conversational Agents**
|
||||
|
|
|
|||
|
|
@ -1,298 +0,0 @@
|
|||
---
|
||||
title: Llama Stack Playground
|
||||
description: Interactive interface to explore and experiment with Llama Stack capabilities
|
||||
sidebar_label: Playground
|
||||
sidebar_position: 10
|
||||
---
|
||||
|
||||
import Tabs from '@theme/Tabs';
|
||||
import TabItem from '@theme/TabItem';
|
||||
|
||||
# Llama Stack Playground
|
||||
|
||||
:::note[Experimental Feature]
|
||||
The Llama Stack Playground is currently experimental and subject to change. We welcome feedback and contributions to help improve it.
|
||||
:::
|
||||
|
||||
The Llama Stack Playground is a simple interface that aims to:
|
||||
- **Showcase capabilities and concepts** of Llama Stack in an interactive environment
|
||||
- **Demo end-to-end application code** to help users get started building their own applications
|
||||
- **Provide a UI** to help users inspect and understand Llama Stack API providers and resources
|
||||
|
||||
## Key Features
|
||||
|
||||
### Interactive Playground Pages
|
||||
|
||||
The playground provides interactive pages for users to explore Llama Stack API capabilities:
|
||||
|
||||
#### Chatbot Interface
|
||||
|
||||
<video
|
||||
controls
|
||||
autoPlay
|
||||
playsInline
|
||||
muted
|
||||
loop
|
||||
style={{width: '100%'}}
|
||||
>
|
||||
<source src="https://github.com/user-attachments/assets/8d2ef802-5812-4a28-96e1-316038c84cbf" type="video/mp4" />
|
||||
Your browser does not support the video tag.
|
||||
</video>
|
||||
|
||||
<Tabs>
|
||||
<TabItem value="chat" label="Chat">
|
||||
|
||||
**Simple Chat Interface**
|
||||
- Chat directly with Llama models through an intuitive interface
|
||||
- Uses the `/chat/completions` streaming API under the hood
|
||||
- Real-time message streaming for responsive interactions
|
||||
- Perfect for testing model capabilities and prompt engineering
|
||||
|
||||
</TabItem>
|
||||
<TabItem value="rag" label="RAG Chat">
|
||||
|
||||
**Document-Aware Conversations**
|
||||
- Upload documents to create memory banks
|
||||
- Chat with a RAG-enabled agent that can query your documents
|
||||
- Uses Llama Stack's `/agents` API to create and manage RAG sessions
|
||||
- Ideal for exploring knowledge-enhanced AI applications
|
||||
|
||||
</TabItem>
|
||||
</Tabs>
|
||||
|
||||
#### Evaluation Interface
|
||||
|
||||
<video
|
||||
controls
|
||||
autoPlay
|
||||
playsInline
|
||||
muted
|
||||
loop
|
||||
style={{width: '100%'}}
|
||||
>
|
||||
<source src="https://github.com/user-attachments/assets/6cc1659f-eba4-49ca-a0a5-7c243557b4f5" type="video/mp4" />
|
||||
Your browser does not support the video tag.
|
||||
</video>
|
||||
|
||||
<Tabs>
|
||||
<TabItem value="scoring" label="Scoring Evaluations">
|
||||
|
||||
**Custom Dataset Evaluation**
|
||||
- Upload your own evaluation datasets
|
||||
- Run evaluations using available scoring functions
|
||||
- Uses Llama Stack's `/scoring` API for flexible evaluation workflows
|
||||
- Great for testing application performance on custom metrics
|
||||
|
||||
</TabItem>
|
||||
<TabItem value="benchmarks" label="Benchmark Evaluations">
|
||||
|
||||
<video
|
||||
controls
|
||||
autoPlay
|
||||
playsInline
|
||||
muted
|
||||
loop
|
||||
style={{width: '100%', marginBottom: '1rem'}}
|
||||
>
|
||||
<source src="https://github.com/user-attachments/assets/345845c7-2a2b-4095-960a-9ae40f6a93cf" type="video/mp4" />
|
||||
Your browser does not support the video tag.
|
||||
</video>
|
||||
|
||||
**Pre-registered Evaluation Tasks**
|
||||
- Evaluate models or agents on pre-defined tasks
|
||||
- Uses Llama Stack's `/eval` API for comprehensive evaluation
|
||||
- Combines datasets and scoring functions for standardized testing
|
||||
|
||||
**Setup Requirements:**
|
||||
Register evaluation datasets and benchmarks first:
|
||||
|
||||
```bash
|
||||
# Register evaluation dataset
|
||||
llama-stack-client datasets register \
|
||||
--dataset-id "mmlu" \
|
||||
--provider-id "huggingface" \
|
||||
--url "https://huggingface.co/datasets/llamastack/evals" \
|
||||
--metadata '{"path": "llamastack/evals", "name": "evals__mmlu__details", "split": "train"}' \
|
||||
--schema '{"input_query": {"type": "string"}, "expected_answer": {"type": "string"}, "chat_completion_input": {"type": "string"}}'
|
||||
|
||||
# Register benchmark task
|
||||
llama-stack-client benchmarks register \
|
||||
--eval-task-id meta-reference-mmlu \
|
||||
--provider-id meta-reference \
|
||||
--dataset-id mmlu \
|
||||
--scoring-functions basic::regex_parser_multiple_choice_answer
|
||||
```
|
||||
|
||||
</TabItem>
|
||||
</Tabs>
|
||||
|
||||
#### Inspection Interface
|
||||
|
||||
<video
|
||||
controls
|
||||
autoPlay
|
||||
playsInline
|
||||
muted
|
||||
loop
|
||||
style={{width: '100%'}}
|
||||
>
|
||||
<source src="https://github.com/user-attachments/assets/01d52b2d-92af-4e3a-b623-a9b8ba22ba99" type="video/mp4" />
|
||||
Your browser does not support the video tag.
|
||||
</video>
|
||||
|
||||
<Tabs>
|
||||
<TabItem value="providers" label="API Providers">
|
||||
|
||||
**Provider Management**
|
||||
- Inspect available Llama Stack API providers
|
||||
- View provider configurations and capabilities
|
||||
- Uses the `/providers` API for real-time provider information
|
||||
- Essential for understanding your deployment's capabilities
|
||||
|
||||
</TabItem>
|
||||
<TabItem value="resources" label="API Resources">
|
||||
|
||||
**Resource Exploration**
|
||||
- Inspect Llama Stack API resources including:
|
||||
- **Models**: Available language models
|
||||
- **Datasets**: Registered evaluation datasets
|
||||
- **Memory Banks**: Vector databases and knowledge stores
|
||||
- **Benchmarks**: Evaluation tasks and scoring functions
|
||||
- **Shields**: Safety and content moderation tools
|
||||
- Uses `/<resources>/list` APIs for comprehensive resource visibility
|
||||
- For detailed information about resources, see [Core Concepts](/docs/concepts)
|
||||
|
||||
</TabItem>
|
||||
</Tabs>
|
||||
|
||||
## Getting Started
|
||||
|
||||
### Quick Start Guide
|
||||
|
||||
<Tabs>
|
||||
<TabItem value="setup" label="Setup">
|
||||
|
||||
**1. Start the Llama Stack API Server**
|
||||
|
||||
```bash
|
||||
llama stack list-deps together | xargs -L1 uv pip install
|
||||
llama stack run together
|
||||
```
|
||||
|
||||
**2. Start the Streamlit UI**
|
||||
|
||||
```bash
|
||||
# Launch the playground interface
|
||||
uv run --with ".[ui]" streamlit run llama_stack.core/ui/app.py
|
||||
```
|
||||
|
||||
</TabItem>
|
||||
<TabItem value="usage" label="Usage Tips">
|
||||
|
||||
**Making the Most of the Playground:**
|
||||
|
||||
- **Start with Chat**: Test basic model interactions and prompt engineering
|
||||
- **Explore RAG**: Upload sample documents to see knowledge-enhanced responses
|
||||
- **Try Evaluations**: Use the scoring interface to understand evaluation metrics
|
||||
- **Inspect Resources**: Check what providers and resources are available
|
||||
- **Experiment with Settings**: Adjust parameters to see how they affect results
|
||||
|
||||
</TabItem>
|
||||
</Tabs>
|
||||
|
||||
### Available Distributions
|
||||
|
||||
The playground works with any Llama Stack distribution. Popular options include:
|
||||
|
||||
<Tabs>
|
||||
<TabItem value="together" label="Together AI">
|
||||
|
||||
```bash
|
||||
llama stack list-deps together | xargs -L1 uv pip install
|
||||
llama stack run together
|
||||
```
|
||||
|
||||
**Features:**
|
||||
- Cloud-hosted models
|
||||
- Fast inference
|
||||
- Multiple model options
|
||||
|
||||
</TabItem>
|
||||
<TabItem value="ollama" label="Ollama (Local)">
|
||||
|
||||
```bash
|
||||
llama stack list-deps ollama | xargs -L1 uv pip install
|
||||
llama stack run ollama
|
||||
```
|
||||
|
||||
**Features:**
|
||||
- Local model execution
|
||||
- Privacy-focused
|
||||
- No internet required
|
||||
|
||||
</TabItem>
|
||||
<TabItem value="meta-reference" label="Meta Reference">
|
||||
|
||||
```bash
|
||||
llama stack list-deps meta-reference | xargs -L1 uv pip install
|
||||
llama stack run meta-reference
|
||||
```
|
||||
|
||||
**Features:**
|
||||
- Reference implementation
|
||||
- All API features available
|
||||
- Best for development
|
||||
|
||||
</TabItem>
|
||||
</Tabs>
|
||||
|
||||
## Use Cases & Examples
|
||||
|
||||
### Educational Use Cases
|
||||
- **Learning Llama Stack**: Hands-on exploration of API capabilities
|
||||
- **Prompt Engineering**: Interactive testing of different prompting strategies
|
||||
- **RAG Experimentation**: Understanding how document retrieval affects responses
|
||||
- **Evaluation Understanding**: See how different metrics evaluate model performance
|
||||
|
||||
### Development Use Cases
|
||||
- **Prototype Testing**: Quick validation of application concepts
|
||||
- **API Exploration**: Understanding available endpoints and parameters
|
||||
- **Integration Planning**: Seeing how different components work together
|
||||
- **Demo Creation**: Showcasing Llama Stack capabilities to stakeholders
|
||||
|
||||
### Research Use Cases
|
||||
- **Model Comparison**: Side-by-side testing of different models
|
||||
- **Evaluation Design**: Understanding how scoring functions work
|
||||
- **Safety Testing**: Exploring shield effectiveness with different inputs
|
||||
- **Performance Analysis**: Measuring model behavior across different scenarios
|
||||
|
||||
## Best Practices
|
||||
|
||||
### 🚀 **Getting Started**
|
||||
- Begin with simple chat interactions to understand basic functionality
|
||||
- Gradually explore more advanced features like RAG and evaluations
|
||||
- Use the inspection tools to understand your deployment's capabilities
|
||||
|
||||
### 🔧 **Development Workflow**
|
||||
- Use the playground to prototype before writing application code
|
||||
- Test different parameter settings interactively
|
||||
- Validate evaluation approaches before implementing them programmatically
|
||||
|
||||
### 📊 **Evaluation & Testing**
|
||||
- Start with simple scoring functions before trying complex evaluations
|
||||
- Use the playground to understand evaluation results before automation
|
||||
- Test safety features with various input types
|
||||
|
||||
### 🎯 **Production Preparation**
|
||||
- Use playground insights to inform your production API usage
|
||||
- Test edge cases and error conditions interactively
|
||||
- Validate resource configurations before deployment
|
||||
|
||||
## Related Resources
|
||||
|
||||
- **[Getting Started Guide](../getting_started/quickstart)** - Complete setup and introduction
|
||||
- **[Core Concepts](/docs/concepts)** - Understanding Llama Stack fundamentals
|
||||
- **[Agents](./agent)** - Building intelligent agents
|
||||
- **[RAG (Retrieval Augmented Generation)](./rag)** - Knowledge-enhanced applications
|
||||
- **[Evaluations](./evals)** - Comprehensive evaluation framework
|
||||
- **[API Reference](/docs/api/llama-stack-specification)** - Complete API documentation
|
||||
|
|
@ -10,7 +10,7 @@ import TabItem from '@theme/TabItem';
|
|||
|
||||
# Kubernetes Deployment Guide
|
||||
|
||||
Deploy Llama Stack and vLLM servers in a Kubernetes cluster instead of running them locally. This guide covers both local development with Kind and production deployment on AWS EKS.
|
||||
Deploy Llama Stack and vLLM servers in a Kubernetes cluster instead of running them locally. This guide covers deployment using the Kubernetes operator to manage the Llama Stack server with Kind. The vLLM inference server is deployed manually.
|
||||
|
||||
## Prerequisites
|
||||
|
||||
|
|
@ -110,115 +110,176 @@ spec:
|
|||
EOF
|
||||
```
|
||||
|
||||
### Step 3: Configure Llama Stack
|
||||
### Step 3: Install Kubernetes Operator
|
||||
|
||||
Update your run configuration:
|
||||
|
||||
```yaml
|
||||
providers:
|
||||
inference:
|
||||
- provider_id: vllm
|
||||
provider_type: remote::vllm
|
||||
config:
|
||||
url: http://vllm-server.default.svc.cluster.local:8000/v1
|
||||
max_tokens: 4096
|
||||
api_token: fake
|
||||
```
|
||||
|
||||
Build container image:
|
||||
Install the Llama Stack Kubernetes operator to manage Llama Stack deployments:
|
||||
|
||||
```bash
|
||||
tmp_dir=$(mktemp -d) && cat >$tmp_dir/Containerfile.llama-stack-run-k8s <<EOF
|
||||
FROM distribution-myenv:dev
|
||||
RUN apt-get update && apt-get install -y git
|
||||
RUN git clone https://github.com/meta-llama/llama-stack.git /app/llama-stack-source
|
||||
ADD ./vllm-llama-stack-run-k8s.yaml /app/config.yaml
|
||||
EOF
|
||||
podman build -f $tmp_dir/Containerfile.llama-stack-run-k8s -t llama-stack-run-k8s $tmp_dir
|
||||
# Install from the latest main branch
|
||||
kubectl apply -f https://raw.githubusercontent.com/llamastack/llama-stack-k8s-operator/main/release/operator.yaml
|
||||
|
||||
# Or install a specific version (e.g., v0.4.0)
|
||||
# kubectl apply -f https://raw.githubusercontent.com/llamastack/llama-stack-k8s-operator/v0.4.0/release/operator.yaml
|
||||
```
|
||||
|
||||
### Step 4: Deploy Llama Stack Server
|
||||
Verify the operator is running:
|
||||
|
||||
```bash
|
||||
kubectl get pods -n llama-stack-operator-system
|
||||
```
|
||||
|
||||
For more information about the operator, see the [llama-stack-k8s-operator repository](https://github.com/llamastack/llama-stack-k8s-operator).
|
||||
|
||||
### Step 4: Deploy Llama Stack Server using Operator
|
||||
|
||||
Create a `LlamaStackDistribution` custom resource to deploy the Llama Stack server. The operator will automatically create the necessary Deployment, Service, and other resources.
|
||||
You can optionally override the default `run.yaml` using `spec.server.userConfig` with a ConfigMap (see [userConfig spec](https://github.com/llamastack/llama-stack-k8s-operator/blob/main/docs/api-overview.md#userconfigspec)).
|
||||
|
||||
```yaml
|
||||
cat <<EOF | kubectl apply -f -
|
||||
apiVersion: v1
|
||||
kind: PersistentVolumeClaim
|
||||
apiVersion: llamastack.io/v1alpha1
|
||||
kind: LlamaStackDistribution
|
||||
metadata:
|
||||
name: llama-pvc
|
||||
spec:
|
||||
accessModes:
|
||||
- ReadWriteOnce
|
||||
resources:
|
||||
requests:
|
||||
storage: 1Gi
|
||||
---
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
name: llama-stack-server
|
||||
name: llamastack-vllm
|
||||
spec:
|
||||
replicas: 1
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: llama-stack
|
||||
template:
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/name: llama-stack
|
||||
spec:
|
||||
containers:
|
||||
- name: llama-stack
|
||||
image: localhost/llama-stack-run-k8s:latest
|
||||
imagePullPolicy: IfNotPresent
|
||||
command: ["llama", "stack", "run", "/app/config.yaml"]
|
||||
ports:
|
||||
- containerPort: 5000
|
||||
volumeMounts:
|
||||
- name: llama-storage
|
||||
mountPath: /root/.llama
|
||||
volumes:
|
||||
- name: llama-storage
|
||||
persistentVolumeClaim:
|
||||
claimName: llama-pvc
|
||||
---
|
||||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
name: llama-stack-service
|
||||
spec:
|
||||
selector:
|
||||
app.kubernetes.io/name: llama-stack
|
||||
ports:
|
||||
- protocol: TCP
|
||||
port: 5000
|
||||
targetPort: 5000
|
||||
type: ClusterIP
|
||||
server:
|
||||
distribution:
|
||||
name: starter
|
||||
containerSpec:
|
||||
port: 8321
|
||||
env:
|
||||
- name: VLLM_URL
|
||||
value: "http://vllm-server.default.svc.cluster.local:8000/v1"
|
||||
- name: VLLM_MAX_TOKENS
|
||||
value: "4096"
|
||||
- name: VLLM_API_TOKEN
|
||||
value: "fake"
|
||||
# Optional: override run.yaml from a ConfigMap using userConfig
|
||||
userConfig:
|
||||
configMap:
|
||||
name: llama-stack-config
|
||||
storage:
|
||||
size: "20Gi"
|
||||
mountPath: "/home/lls/.lls"
|
||||
EOF
|
||||
```
|
||||
|
||||
**Configuration Options:**
|
||||
|
||||
- `replicas`: Number of Llama Stack server instances to run
|
||||
- `server.distribution.name`: The distribution to use (e.g., `starter` for the starter distribution). See the [list of supported distributions](https://github.com/llamastack/llama-stack-k8s-operator/blob/main/distributions.json) in the operator repository.
|
||||
- `server.distribution.image`: (Optional) Custom container image for non-supported distributions. Use this field when deploying a distribution that is not in the supported list. If specified, this takes precedence over `name`.
|
||||
- `server.containerSpec.port`: Port on which the Llama Stack server listens (default: 8321)
|
||||
- `server.containerSpec.env`: Environment variables to configure providers:
|
||||
- `server.userConfig`: (Optional) Override the default `run.yaml` using a ConfigMap. See [userConfig spec](https://github.com/llamastack/llama-stack-k8s-operator/blob/main/docs/api-overview.md#userconfigspec).
|
||||
- `server.storage.size`: Size of the persistent volume for model and data storage
|
||||
- `server.storage.mountPath`: Where to mount the storage in the container
|
||||
|
||||
**Note:** For a complete list of supported distributions, see [distributions.json](https://github.com/llamastack/llama-stack-k8s-operator/blob/main/distributions.json) in the operator repository. To use a custom or non-supported distribution, set the `server.distribution.image` field with your container image instead of `server.distribution.name`.
|
||||
|
||||
The operator automatically creates:
|
||||
- A Deployment for the Llama Stack server
|
||||
- A Service to access the server
|
||||
- A PersistentVolumeClaim for storage
|
||||
- All necessary RBAC resources
|
||||
|
||||
|
||||
Check the status of your deployment:
|
||||
|
||||
```bash
|
||||
kubectl get llamastackdistribution
|
||||
kubectl describe llamastackdistribution llamastack-vllm
|
||||
```
|
||||
|
||||
### Step 5: Test Deployment
|
||||
|
||||
Wait for the Llama Stack server pod to be ready:
|
||||
|
||||
```bash
|
||||
# Port forward and test
|
||||
kubectl port-forward service/llama-stack-service 5000:5000
|
||||
llama-stack-client --endpoint http://localhost:5000 inference chat-completion --message "hello, what model are you?"
|
||||
# Check the status of the LlamaStackDistribution
|
||||
kubectl get llamastackdistribution llamastack-vllm
|
||||
|
||||
# Check the pods created by the operator
|
||||
kubectl get pods -l app.kubernetes.io/name=llama-stack
|
||||
|
||||
# Wait for the pod to be ready
|
||||
kubectl wait --for=condition=ready pod -l app.kubernetes.io/name=llama-stack --timeout=300s
|
||||
```
|
||||
|
||||
Get the service name created by the operator (it typically follows the pattern `<llamastackdistribution-name>-service`):
|
||||
|
||||
```bash
|
||||
# List services to find the service name
|
||||
kubectl get services | grep llamastack
|
||||
|
||||
# Port forward and test (replace SERVICE_NAME with the actual service name)
|
||||
kubectl port-forward service/llamastack-vllm-service 8321:8321
|
||||
```
|
||||
|
||||
In another terminal, test the deployment:
|
||||
|
||||
```bash
|
||||
llama-stack-client --endpoint http://localhost:8321 inference chat-completion --message "hello, what model are you?"
|
||||
```
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
**Check pod status:**
|
||||
### vLLM Server Issues
|
||||
|
||||
**Check vLLM pod status:**
|
||||
```bash
|
||||
kubectl get pods -l app.kubernetes.io/name=vllm
|
||||
kubectl logs -l app.kubernetes.io/name=vllm
|
||||
```
|
||||
|
||||
**Test service connectivity:**
|
||||
**Test vLLM service connectivity:**
|
||||
```bash
|
||||
kubectl run -it --rm debug --image=curlimages/curl --restart=Never -- curl http://vllm-server:8000/v1/models
|
||||
```
|
||||
|
||||
### Llama Stack Server Issues
|
||||
|
||||
**Check LlamaStackDistribution status:**
|
||||
```bash
|
||||
# Get detailed status
|
||||
kubectl describe llamastackdistribution llamastack-vllm
|
||||
|
||||
# Check for events
|
||||
kubectl get events --sort-by='.lastTimestamp' | grep llamastack-vllm
|
||||
```
|
||||
|
||||
**Check operator-managed pods:**
|
||||
```bash
|
||||
# List all pods managed by the operator
|
||||
kubectl get pods -l app.kubernetes.io/name=llama-stack
|
||||
|
||||
# Check pod logs (replace POD_NAME with actual pod name)
|
||||
kubectl logs -l app.kubernetes.io/name=llama-stack
|
||||
```
|
||||
|
||||
**Check operator status:**
|
||||
```bash
|
||||
# Verify the operator is running
|
||||
kubectl get pods -n llama-stack-operator-system
|
||||
|
||||
# Check operator logs if issues persist
|
||||
kubectl logs -n llama-stack-operator-system -l control-plane=controller-manager
|
||||
```
|
||||
|
||||
**Verify service connectivity:**
|
||||
```bash
|
||||
# Get the service endpoint
|
||||
kubectl get svc llamastack-vllm-service
|
||||
|
||||
# Test connectivity from within the cluster
|
||||
kubectl run -it --rm debug --image=curlimages/curl --restart=Never -- curl http://llamastack-vllm-service:8321/health
|
||||
```
|
||||
|
||||
## Related Resources
|
||||
|
||||
- **[Deployment Overview](/docs/deploying/)** - Overview of deployment options
|
||||
- **[Distributions](/docs/distributions)** - Understanding Llama Stack distributions
|
||||
- **[Configuration](/docs/distributions/configuration)** - Detailed configuration options
|
||||
- **[LlamaStack Operator](https://github.com/llamastack/llama-stack-k8s-operator)** - Overview of llama-stack kubernetes operator
|
||||
- **[LlamaStackDistribution](https://github.com/llamastack/llama-stack-k8s-operator/blob/main/docs/api-overview.md)** - API Spec of the llama-stack operator Custom Resource.
|
||||
|
|
|
|||
|
|
@ -11,7 +11,7 @@ If you are planning to use an external service for Inference (even Ollama or TGI
|
|||
This avoids the overhead of setting up a server.
|
||||
```bash
|
||||
# setup
|
||||
uv pip install llama-stack
|
||||
uv pip install llama-stack llama-stack-client
|
||||
llama stack list-deps starter | xargs -L1 uv pip install
|
||||
```
|
||||
|
||||
|
|
|
|||
|
|
@ -19,3 +19,4 @@ This section provides an overview of the distributions available in Llama Stack.
|
|||
- **[Starting Llama Stack Server](./starting_llama_stack_server.mdx)** - How to run distributions
|
||||
- **[Importing as Library](./importing_as_library.mdx)** - Use distributions in your code
|
||||
- **[Configuration Reference](./configuration.mdx)** - Configuration file format details
|
||||
- **[Llama Stack UI](./llama_stack_ui.mdx)** - Web-based user interface for interacting with Llama Stack servers
|
||||
|
|
|
|||
|
|
@ -44,7 +44,7 @@ spec:
|
|||
|
||||
# Navigate to the UI directory
|
||||
echo "Navigating to UI directory..."
|
||||
cd /app/llama_stack/ui
|
||||
cd /app/llama_stack_ui
|
||||
|
||||
# Check if package.json exists
|
||||
if [ ! -f "package.json" ]; then
|
||||
|
|
|
|||
109
docs/docs/distributions/llama_stack_ui.mdx
Normal file
109
docs/docs/distributions/llama_stack_ui.mdx
Normal file
|
|
@ -0,0 +1,109 @@
|
|||
---
|
||||
title: Llama Stack UI
|
||||
description: Web-based user interface for interacting with Llama Stack servers
|
||||
sidebar_label: Llama Stack UI
|
||||
sidebar_position: 8
|
||||
---
|
||||
|
||||
# Llama Stack UI
|
||||
|
||||
The Llama Stack UI is a web-based interface for interacting with Llama Stack servers. Built with Next.js and React, it provides a visual way to work with agents, manage resources, and view logs.
|
||||
|
||||
## Features
|
||||
|
||||
- **Logs & Monitoring**: View chat completions, agent responses, and vector store activity
|
||||
- **Vector Stores**: Create and manage vector databases for RAG (Retrieval-Augmented Generation) workflows
|
||||
- **Prompt Management**: Create and manage reusable prompts
|
||||
|
||||
## Prerequisites
|
||||
|
||||
You need a running Llama Stack server. The UI is a client that connects to the Llama Stack backend.
|
||||
|
||||
If you don't have a Llama Stack server running yet, see the [Starting Llama Stack Server](../getting_started/starting_llama_stack_server.mdx) guide.
|
||||
|
||||
## Running the UI
|
||||
|
||||
### Option 1: Using npx (Recommended for Quick Start)
|
||||
|
||||
The fastest way to get started is using `npx`:
|
||||
|
||||
```bash
|
||||
npx llama-stack-ui
|
||||
```
|
||||
|
||||
This will start the UI server on `http://localhost:8322` (default port).
|
||||
|
||||
### Option 2: Using Docker
|
||||
|
||||
Run the UI in a container:
|
||||
|
||||
```bash
|
||||
docker run -p 8322:8322 llamastack/ui
|
||||
```
|
||||
|
||||
Access the UI at `http://localhost:8322`.
|
||||
|
||||
## Environment Variables
|
||||
|
||||
The UI can be configured using the following environment variables:
|
||||
|
||||
| Variable | Description | Default |
|
||||
|----------|-------------|---------|
|
||||
| `LLAMA_STACK_BACKEND_URL` | URL of your Llama Stack server | `http://localhost:8321` |
|
||||
| `LLAMA_STACK_UI_PORT` | Port for the UI server | `8322` |
|
||||
|
||||
If the Llama Stack server is running with authentication enabled, you can configure the UI to use it by setting the following environment variables:
|
||||
|
||||
| Variable | Description | Default |
|
||||
|----------|-------------|---------|
|
||||
| `NEXTAUTH_URL` | NextAuth URL for authentication | `http://localhost:8322` |
|
||||
| `GITHUB_CLIENT_ID` | GitHub OAuth client ID (optional, for authentication) | - |
|
||||
| `GITHUB_CLIENT_SECRET` | GitHub OAuth client secret (optional, for authentication) | - |
|
||||
|
||||
### Setting Environment Variables
|
||||
|
||||
#### For npx:
|
||||
|
||||
```bash
|
||||
LLAMA_STACK_BACKEND_URL=http://localhost:8321 \
|
||||
LLAMA_STACK_UI_PORT=8080 \
|
||||
npx llama-stack-ui
|
||||
```
|
||||
|
||||
#### For Docker:
|
||||
|
||||
```bash
|
||||
docker run -p 8080:8080 \
|
||||
-e LLAMA_STACK_BACKEND_URL=http://localhost:8321 \
|
||||
-e LLAMA_STACK_UI_PORT=8080 \
|
||||
llamastack/ui
|
||||
```
|
||||
|
||||
## Using the UI
|
||||
|
||||
### Managing Resources
|
||||
|
||||
- **Vector Stores**: Create vector databases for RAG workflows, view stored documents and embeddings
|
||||
- **Prompts**: Create and manage reusable prompt templates
|
||||
- **Chat Completions**: View history of chat interactions
|
||||
- **Responses**: Browse detailed agent responses and tool calls
|
||||
|
||||
## Development
|
||||
|
||||
If you want to run the UI from source for development:
|
||||
|
||||
```bash
|
||||
# From the project root
|
||||
cd src/llama_stack_ui
|
||||
|
||||
# Install dependencies
|
||||
npm install
|
||||
|
||||
# Set environment variables
|
||||
export LLAMA_STACK_BACKEND_URL=http://localhost:8321
|
||||
|
||||
# Start the development server
|
||||
npm run dev
|
||||
```
|
||||
|
||||
The development server will start on `http://localhost:8322` with hot reloading enabled.
|
||||
143
docs/docs/distributions/remote_hosted_distro/oci.md
Normal file
143
docs/docs/distributions/remote_hosted_distro/oci.md
Normal file
|
|
@ -0,0 +1,143 @@
|
|||
---
|
||||
orphan: true
|
||||
---
|
||||
<!-- This file was auto-generated by distro_codegen.py, please edit source -->
|
||||
# OCI Distribution
|
||||
|
||||
The `llamastack/distribution-oci` distribution consists of the following provider configurations.
|
||||
|
||||
| API | Provider(s) |
|
||||
|-----|-------------|
|
||||
| agents | `inline::meta-reference` |
|
||||
| datasetio | `remote::huggingface`, `inline::localfs` |
|
||||
| eval | `inline::meta-reference` |
|
||||
| files | `inline::localfs` |
|
||||
| inference | `remote::oci` |
|
||||
| safety | `inline::llama-guard` |
|
||||
| scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` |
|
||||
| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::rag-runtime`, `remote::model-context-protocol` |
|
||||
| vector_io | `inline::faiss`, `remote::chromadb`, `remote::pgvector` |
|
||||
|
||||
|
||||
### Environment Variables
|
||||
|
||||
The following environment variables can be configured:
|
||||
|
||||
- `OCI_AUTH_TYPE`: OCI authentication type (instance_principal or config_file) (default: `instance_principal`)
|
||||
- `OCI_REGION`: OCI region (e.g., us-ashburn-1, us-chicago-1, us-phoenix-1, eu-frankfurt-1) (default: ``)
|
||||
- `OCI_COMPARTMENT_OCID`: OCI compartment ID for the Generative AI service (default: ``)
|
||||
- `OCI_CONFIG_FILE_PATH`: OCI config file path (required if OCI_AUTH_TYPE is config_file) (default: `~/.oci/config`)
|
||||
- `OCI_CLI_PROFILE`: OCI CLI profile name to use from config file (default: `DEFAULT`)
|
||||
|
||||
|
||||
## Prerequisites
|
||||
### Oracle Cloud Infrastructure Setup
|
||||
|
||||
Before using the OCI Generative AI distribution, ensure you have:
|
||||
|
||||
1. **Oracle Cloud Infrastructure Account**: Sign up at [Oracle Cloud Infrastructure](https://cloud.oracle.com/)
|
||||
2. **Generative AI Service Access**: Enable the Generative AI service in your OCI tenancy
|
||||
3. **Compartment**: Create or identify a compartment where you'll deploy Generative AI models
|
||||
4. **Authentication**: Configure authentication using either:
|
||||
- **Instance Principal** (recommended for cloud-hosted deployments)
|
||||
- **API Key** (for on-premises or development environments)
|
||||
|
||||
### Authentication Methods
|
||||
|
||||
#### Instance Principal Authentication (Recommended)
|
||||
Instance Principal authentication allows OCI resources to authenticate using the identity of the compute instance they're running on. This is the most secure method for production deployments.
|
||||
|
||||
Requirements:
|
||||
- Instance must be running in an Oracle Cloud Infrastructure compartment
|
||||
- Instance must have appropriate IAM policies to access Generative AI services
|
||||
|
||||
#### API Key Authentication
|
||||
For development or on-premises deployments, follow [this doc](https://docs.oracle.com/en-us/iaas/Content/API/Concepts/apisigningkey.htm) to learn how to create your API signing key for your config file.
|
||||
|
||||
### Required IAM Policies
|
||||
|
||||
Ensure your OCI user or instance has the following policy statements:
|
||||
|
||||
```
|
||||
Allow group <group_name> to use generative-ai-inference-endpoints in compartment <compartment_name>
|
||||
Allow group <group_name> to manage generative-ai-inference-endpoints in compartment <compartment_name>
|
||||
```
|
||||
|
||||
## Supported Services
|
||||
|
||||
### Inference: OCI Generative AI
|
||||
Oracle Cloud Infrastructure Generative AI provides access to high-performance AI models through OCI's Platform-as-a-Service offering. The service supports:
|
||||
|
||||
- **Chat Completions**: Conversational AI with context awareness
|
||||
- **Text Generation**: Complete prompts and generate text content
|
||||
|
||||
#### Available Models
|
||||
Common OCI Generative AI models include access to Meta, Cohere, OpenAI, Grok, and more models.
|
||||
|
||||
### Safety: Llama Guard
|
||||
For content safety and moderation, this distribution uses Meta's LlamaGuard model through the OCI Generative AI service to provide:
|
||||
- Content filtering and moderation
|
||||
- Policy compliance checking
|
||||
- Harmful content detection
|
||||
|
||||
### Vector Storage: Multiple Options
|
||||
The distribution supports several vector storage providers:
|
||||
- **FAISS**: Local in-memory vector search
|
||||
- **ChromaDB**: Distributed vector database
|
||||
- **PGVector**: PostgreSQL with vector extensions
|
||||
|
||||
### Additional Services
|
||||
- **Dataset I/O**: Local filesystem and Hugging Face integration
|
||||
- **Tool Runtime**: Web search (Brave, Tavily) and RAG capabilities
|
||||
- **Evaluation**: Meta reference evaluation framework
|
||||
|
||||
## Running Llama Stack with OCI
|
||||
|
||||
You can run the OCI distribution via Docker or local virtual environment.
|
||||
|
||||
### Via venv
|
||||
|
||||
If you've set up your local development environment, you can also build the image using your local virtual environment.
|
||||
|
||||
```bash
|
||||
OCI_AUTH=$OCI_AUTH_TYPE OCI_REGION=$OCI_REGION OCI_COMPARTMENT_OCID=$OCI_COMPARTMENT_OCID llama stack run --port 8321 oci
|
||||
```
|
||||
|
||||
### Configuration Examples
|
||||
|
||||
#### Using Instance Principal (Recommended for Production)
|
||||
```bash
|
||||
export OCI_AUTH_TYPE=instance_principal
|
||||
export OCI_REGION=us-chicago-1
|
||||
export OCI_COMPARTMENT_OCID=ocid1.compartment.oc1..<your-compartment-id>
|
||||
```
|
||||
|
||||
#### Using API Key Authentication (Development)
|
||||
```bash
|
||||
export OCI_AUTH_TYPE=config_file
|
||||
export OCI_CONFIG_FILE_PATH=~/.oci/config
|
||||
export OCI_CLI_PROFILE=DEFAULT
|
||||
export OCI_REGION=us-chicago-1
|
||||
export OCI_COMPARTMENT_OCID=ocid1.compartment.oc1..your-compartment-id
|
||||
```
|
||||
|
||||
## Regional Endpoints
|
||||
|
||||
OCI Generative AI is available in multiple regions. The service automatically routes to the appropriate regional endpoint based on your configuration. For a full list of regional model availability, visit:
|
||||
|
||||
https://docs.oracle.com/en-us/iaas/Content/generative-ai/overview.htm#regions
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
### Common Issues
|
||||
|
||||
1. **Authentication Errors**: Verify your OCI credentials and IAM policies
|
||||
2. **Model Not Found**: Ensure the model OCID is correct and the model is available in your region
|
||||
3. **Permission Denied**: Check compartment permissions and Generative AI service access
|
||||
4. **Region Unavailable**: Verify the specified region supports Generative AI services
|
||||
|
||||
### Getting Help
|
||||
|
||||
For additional support:
|
||||
- [OCI Generative AI Documentation](https://docs.oracle.com/en-us/iaas/Content/generative-ai/home.htm)
|
||||
- [Llama Stack Issues](https://github.com/meta-llama/llama-stack/issues)
|
||||
|
|
@ -163,7 +163,41 @@ docker run \
|
|||
--port $LLAMA_STACK_PORT
|
||||
```
|
||||
|
||||
### Via venv
|
||||
The container will run the distribution with a SQLite store by default. This store is used for the following components:
|
||||
|
||||
- Metadata store: store metadata about the models, providers, etc.
|
||||
- Inference store: collect of responses from the inference provider
|
||||
- Agents store: store agent configurations (sessions, turns, etc.)
|
||||
- Agents Responses store: store responses from the agents
|
||||
|
||||
However, you can use PostgreSQL instead by running the `starter::run-with-postgres-store.yaml` configuration:
|
||||
|
||||
```bash
|
||||
docker run \
|
||||
-it \
|
||||
--pull always \
|
||||
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
|
||||
-e OPENAI_API_KEY=your_openai_key \
|
||||
-e FIREWORKS_API_KEY=your_fireworks_key \
|
||||
-e TOGETHER_API_KEY=your_together_key \
|
||||
-e POSTGRES_HOST=your_postgres_host \
|
||||
-e POSTGRES_PORT=your_postgres_port \
|
||||
-e POSTGRES_DB=your_postgres_db \
|
||||
-e POSTGRES_USER=your_postgres_user \
|
||||
-e POSTGRES_PASSWORD=your_postgres_password \
|
||||
llamastack/distribution-starter \
|
||||
starter::run-with-postgres-store.yaml
|
||||
```
|
||||
|
||||
Postgres environment variables:
|
||||
|
||||
- `POSTGRES_HOST`: Postgres host (default: `localhost`)
|
||||
- `POSTGRES_PORT`: Postgres port (default: `5432`)
|
||||
- `POSTGRES_DB`: Postgres database name (default: `llamastack`)
|
||||
- `POSTGRES_USER`: Postgres username (default: `llamastack`)
|
||||
- `POSTGRES_PASSWORD`: Postgres password (default: `llamastack`)
|
||||
|
||||
### Via Conda or venv
|
||||
|
||||
Ensure you have configured the starter distribution using the environment variables explained above.
|
||||
|
||||
|
|
@ -171,8 +205,11 @@ Ensure you have configured the starter distribution using the environment variab
|
|||
# Install dependencies for the starter distribution
|
||||
uv run --with llama-stack llama stack list-deps starter | xargs -L1 uv pip install
|
||||
|
||||
# Run the server
|
||||
# Run the server (with SQLite - default)
|
||||
uv run --with llama-stack llama stack run starter
|
||||
|
||||
# Or run with PostgreSQL
|
||||
uv run --with llama-stack llama stack run starter::run-with-postgres-store.yaml
|
||||
```
|
||||
|
||||
## Example Usage
|
||||
|
|
|
|||
|
|
@ -144,7 +144,7 @@ source .venv/bin/activate
|
|||
```bash
|
||||
uv venv client --python 3.12
|
||||
source client/bin/activate
|
||||
pip install llama-stack-client
|
||||
uv pip install llama-stack-client
|
||||
```
|
||||
</TabItem>
|
||||
</Tabs>
|
||||
|
|
|
|||
|
|
@ -1,5 +1,5 @@
|
|||
---
|
||||
description: "AWS Bedrock inference provider for accessing various AI models through AWS's managed service."
|
||||
description: "AWS Bedrock inference provider using OpenAI compatible endpoint."
|
||||
sidebar_label: Remote - Bedrock
|
||||
title: remote::bedrock
|
||||
---
|
||||
|
|
@ -8,7 +8,7 @@ title: remote::bedrock
|
|||
|
||||
## Description
|
||||
|
||||
AWS Bedrock inference provider for accessing various AI models through AWS's managed service.
|
||||
AWS Bedrock inference provider using OpenAI compatible endpoint.
|
||||
|
||||
## Configuration
|
||||
|
||||
|
|
@ -16,19 +16,12 @@ AWS Bedrock inference provider for accessing various AI models through AWS's man
|
|||
|-------|------|----------|---------|-------------|
|
||||
| `allowed_models` | `list[str \| None` | No | | List of models that should be registered with the model registry. If None, all models are allowed. |
|
||||
| `refresh_models` | `<class 'bool'>` | No | False | Whether to refresh models periodically from the provider |
|
||||
| `aws_access_key_id` | `str \| None` | No | | The AWS access key to use. Default use environment variable: AWS_ACCESS_KEY_ID |
|
||||
| `aws_secret_access_key` | `str \| None` | No | | The AWS secret access key to use. Default use environment variable: AWS_SECRET_ACCESS_KEY |
|
||||
| `aws_session_token` | `str \| None` | No | | The AWS session token to use. Default use environment variable: AWS_SESSION_TOKEN |
|
||||
| `region_name` | `str \| None` | No | | The default AWS Region to use, for example, us-west-1 or us-west-2.Default use environment variable: AWS_DEFAULT_REGION |
|
||||
| `profile_name` | `str \| None` | No | | The profile name that contains credentials to use.Default use environment variable: AWS_PROFILE |
|
||||
| `total_max_attempts` | `int \| None` | No | | An integer representing the maximum number of attempts that will be made for a single request, including the initial attempt. Default use environment variable: AWS_MAX_ATTEMPTS |
|
||||
| `retry_mode` | `str \| None` | No | | A string representing the type of retries Boto3 will perform.Default use environment variable: AWS_RETRY_MODE |
|
||||
| `connect_timeout` | `float \| None` | No | 60.0 | The time in seconds till a timeout exception is thrown when attempting to make a connection. The default is 60 seconds. |
|
||||
| `read_timeout` | `float \| None` | No | 60.0 | The time in seconds till a timeout exception is thrown when attempting to read from a connection.The default is 60 seconds. |
|
||||
| `session_ttl` | `int \| None` | No | 3600 | The time in seconds till a session expires. The default is 3600 seconds (1 hour). |
|
||||
| `api_key` | `pydantic.types.SecretStr \| None` | No | | Authentication credential for the provider |
|
||||
| `region_name` | `<class 'str'>` | No | us-east-2 | AWS Region for the Bedrock Runtime endpoint |
|
||||
|
||||
## Sample Configuration
|
||||
|
||||
```yaml
|
||||
{}
|
||||
api_key: ${env.AWS_BEDROCK_API_KEY:=}
|
||||
region_name: ${env.AWS_DEFAULT_REGION:=us-east-2}
|
||||
```
|
||||
|
|
|
|||
41
docs/docs/providers/inference/remote_oci.mdx
Normal file
41
docs/docs/providers/inference/remote_oci.mdx
Normal file
|
|
@ -0,0 +1,41 @@
|
|||
---
|
||||
description: |
|
||||
Oracle Cloud Infrastructure (OCI) Generative AI inference provider for accessing OCI's Generative AI Platform-as-a-Service models.
|
||||
Provider documentation
|
||||
https://docs.oracle.com/en-us/iaas/Content/generative-ai/home.htm
|
||||
sidebar_label: Remote - Oci
|
||||
title: remote::oci
|
||||
---
|
||||
|
||||
# remote::oci
|
||||
|
||||
## Description
|
||||
|
||||
|
||||
Oracle Cloud Infrastructure (OCI) Generative AI inference provider for accessing OCI's Generative AI Platform-as-a-Service models.
|
||||
Provider documentation
|
||||
https://docs.oracle.com/en-us/iaas/Content/generative-ai/home.htm
|
||||
|
||||
|
||||
## Configuration
|
||||
|
||||
| Field | Type | Required | Default | Description |
|
||||
|-------|------|----------|---------|-------------|
|
||||
| `allowed_models` | `list[str \| None` | No | | List of models that should be registered with the model registry. If None, all models are allowed. |
|
||||
| `refresh_models` | `<class 'bool'>` | No | False | Whether to refresh models periodically from the provider |
|
||||
| `api_key` | `pydantic.types.SecretStr \| None` | No | | Authentication credential for the provider |
|
||||
| `oci_auth_type` | `<class 'str'>` | No | instance_principal | OCI authentication type (must be one of: instance_principal, config_file) |
|
||||
| `oci_region` | `<class 'str'>` | No | us-ashburn-1 | OCI region (e.g., us-ashburn-1) |
|
||||
| `oci_compartment_id` | `<class 'str'>` | No | | OCI compartment ID for the Generative AI service |
|
||||
| `oci_config_file_path` | `<class 'str'>` | No | ~/.oci/config | OCI config file path (required if oci_auth_type is config_file) |
|
||||
| `oci_config_profile` | `<class 'str'>` | No | DEFAULT | OCI config profile (required if oci_auth_type is config_file) |
|
||||
|
||||
## Sample Configuration
|
||||
|
||||
```yaml
|
||||
oci_auth_type: ${env.OCI_AUTH_TYPE:=instance_principal}
|
||||
oci_config_file_path: ${env.OCI_CONFIG_FILE_PATH:=~/.oci/config}
|
||||
oci_config_profile: ${env.OCI_CLI_PROFILE:=DEFAULT}
|
||||
oci_region: ${env.OCI_REGION:=us-ashburn-1}
|
||||
oci_compartment_id: ${env.OCI_COMPARTMENT_OCID:=}
|
||||
```
|
||||
|
|
@ -16,7 +16,7 @@ Passthrough inference provider for connecting to any external inference service
|
|||
|-------|------|----------|---------|-------------|
|
||||
| `allowed_models` | `list[str \| None` | No | | List of models that should be registered with the model registry. If None, all models are allowed. |
|
||||
| `refresh_models` | `<class 'bool'>` | No | False | Whether to refresh models periodically from the provider |
|
||||
| `api_key` | `pydantic.types.SecretStr \| None` | No | | API Key for the passthrouth endpoint |
|
||||
| `api_key` | `pydantic.types.SecretStr \| None` | No | | Authentication credential for the provider |
|
||||
| `url` | `<class 'str'>` | No | | The URL for the passthrough endpoint |
|
||||
|
||||
## Sample Configuration
|
||||
|
|
|
|||
|
|
@ -48,11 +48,9 @@ Both OpenAI and Llama Stack support a web-search built-in tool. The [OpenAI doc
|
|||
|
||||
> The type of the web search tool. One of `web_search` or `web_search_2025_08_26`.
|
||||
|
||||
In contrast, the [Llama Stack documentation](https://llamastack.github.io/docs/api/create-a-new-open-ai-response) says that the allowed values for `type` for web search are `MOD1`, `MOD2` and `MOD3`.
|
||||
Is that correct? If so, what are the meanings of each of them? It might make sense for the allowed values for OpenAI map to some values for Llama Stack so that code written to the OpenAI specification
|
||||
also work with Llama Stack.
|
||||
Llama Stack now supports both `web_search` and `web_search_2025_08_26` types, matching OpenAI's API. For backward compatibility, Llama Stack also supports `web_search_preview` and `web_search_preview_2025_03_11` types.
|
||||
|
||||
The OpenAI web search tool also has fields for `filters` and `user_location` which are not documented as options for Llama Stack. If feasible, it would be good to support these too.
|
||||
The OpenAI web search tool also has fields for `filters` and `user_location` which are not yet implemented in Llama Stack. If feasible, it would be good to support these too.
|
||||
|
||||
---
|
||||
|
||||
|
|
|
|||
|
|
@ -37,7 +37,7 @@
|
|||
"outputs": [],
|
||||
"source": [
|
||||
"# NBVAL_SKIP\n",
|
||||
"!pip install -U llama-stack\n",
|
||||
"!pip install -U llama-stack llama-stack-client\n",
|
||||
"llama stack list-deps fireworks | xargs -L1 uv pip install\n"
|
||||
]
|
||||
},
|
||||
|
|
|
|||
|
|
@ -44,7 +44,7 @@
|
|||
"outputs": [],
|
||||
"source": [
|
||||
"# NBVAL_SKIP\n",
|
||||
"!pip install -U llama-stack"
|
||||
"!pip install -U llama-stack llama-stack-client\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
|
|||
|
|
@ -74,6 +74,7 @@
|
|||
"source": [
|
||||
"```bash\n",
|
||||
"uv sync --extra dev\n",
|
||||
"uv pip install -U llama-stack-client\n",
|
||||
"uv pip install -e .\n",
|
||||
"source .venv/bin/activate\n",
|
||||
"```"
|
||||
|
|
|
|||
|
|
@ -196,16 +196,10 @@ def _get_endpoint_functions(
|
|||
def _get_defining_class(member_fn: str, derived_cls: type) -> type:
|
||||
"Find the class in which a member function is first defined in a class inheritance hierarchy."
|
||||
|
||||
# This import must be dynamic here
|
||||
from llama_stack.apis.tools import RAGToolRuntime, ToolRuntime
|
||||
|
||||
# iterate in reverse member resolution order to find most specific class first
|
||||
for cls in reversed(inspect.getmro(derived_cls)):
|
||||
for name, _ in inspect.getmembers(cls, inspect.isfunction):
|
||||
if name == member_fn:
|
||||
# HACK ALERT
|
||||
if cls == RAGToolRuntime:
|
||||
return ToolRuntime
|
||||
return cls
|
||||
|
||||
raise ValidationError(
|
||||
|
|
|
|||
|
|
@ -57,6 +57,7 @@ const sidebars: SidebarsConfig = {
|
|||
'distributions/importing_as_library',
|
||||
'distributions/configuration',
|
||||
'distributions/starting_llama_stack_server',
|
||||
'distributions/llama_stack_ui',
|
||||
{
|
||||
type: 'category',
|
||||
label: 'Self-Hosted Distributions',
|
||||
|
|
|
|||
1094
docs/static/deprecated-llama-stack-spec.yaml
vendored
1094
docs/static/deprecated-llama-stack-spec.yaml
vendored
File diff suppressed because it is too large
Load diff
214
docs/static/experimental-llama-stack-spec.yaml
vendored
214
docs/static/experimental-llama-stack-spec.yaml
vendored
|
|
@ -162,7 +162,7 @@ paths:
|
|||
schema:
|
||||
$ref: '#/components/schemas/RegisterDatasetRequest'
|
||||
required: true
|
||||
deprecated: false
|
||||
deprecated: true
|
||||
/v1beta/datasets/{dataset_id}:
|
||||
get:
|
||||
responses:
|
||||
|
|
@ -219,7 +219,7 @@ paths:
|
|||
required: true
|
||||
schema:
|
||||
type: string
|
||||
deprecated: false
|
||||
deprecated: true
|
||||
/v1alpha/eval/benchmarks:
|
||||
get:
|
||||
responses:
|
||||
|
|
@ -270,7 +270,7 @@ paths:
|
|||
schema:
|
||||
$ref: '#/components/schemas/RegisterBenchmarkRequest'
|
||||
required: true
|
||||
deprecated: false
|
||||
deprecated: true
|
||||
/v1alpha/eval/benchmarks/{benchmark_id}:
|
||||
get:
|
||||
responses:
|
||||
|
|
@ -327,7 +327,7 @@ paths:
|
|||
required: true
|
||||
schema:
|
||||
type: string
|
||||
deprecated: false
|
||||
deprecated: true
|
||||
/v1alpha/eval/benchmarks/{benchmark_id}/evaluations:
|
||||
post:
|
||||
responses:
|
||||
|
|
@ -936,68 +936,6 @@ components:
|
|||
- data
|
||||
title: ListDatasetsResponse
|
||||
description: Response from listing datasets.
|
||||
DataSource:
|
||||
oneOf:
|
||||
- $ref: '#/components/schemas/URIDataSource'
|
||||
- $ref: '#/components/schemas/RowsDataSource'
|
||||
discriminator:
|
||||
propertyName: type
|
||||
mapping:
|
||||
uri: '#/components/schemas/URIDataSource'
|
||||
rows: '#/components/schemas/RowsDataSource'
|
||||
RegisterDatasetRequest:
|
||||
type: object
|
||||
properties:
|
||||
purpose:
|
||||
type: string
|
||||
enum:
|
||||
- post-training/messages
|
||||
- eval/question-answer
|
||||
- eval/messages-answer
|
||||
description: >-
|
||||
The purpose of the dataset. One of: - "post-training/messages": The dataset
|
||||
contains a messages column with list of messages for post-training. {
|
||||
"messages": [ {"role": "user", "content": "Hello, world!"}, {"role": "assistant",
|
||||
"content": "Hello, world!"}, ] } - "eval/question-answer": The dataset
|
||||
contains a question column and an answer column for evaluation. { "question":
|
||||
"What is the capital of France?", "answer": "Paris" } - "eval/messages-answer":
|
||||
The dataset contains a messages column with list of messages and an answer
|
||||
column for evaluation. { "messages": [ {"role": "user", "content": "Hello,
|
||||
my name is John Doe."}, {"role": "assistant", "content": "Hello, John
|
||||
Doe. How can I help you today?"}, {"role": "user", "content": "What's
|
||||
my name?"}, ], "answer": "John Doe" }
|
||||
source:
|
||||
$ref: '#/components/schemas/DataSource'
|
||||
description: >-
|
||||
The data source of the dataset. Ensure that the data source schema is
|
||||
compatible with the purpose of the dataset. Examples: - { "type": "uri",
|
||||
"uri": "https://mywebsite.com/mydata.jsonl" } - { "type": "uri", "uri":
|
||||
"lsfs://mydata.jsonl" } - { "type": "uri", "uri": "data:csv;base64,{base64_content}"
|
||||
} - { "type": "uri", "uri": "huggingface://llamastack/simpleqa?split=train"
|
||||
} - { "type": "rows", "rows": [ { "messages": [ {"role": "user", "content":
|
||||
"Hello, world!"}, {"role": "assistant", "content": "Hello, world!"}, ]
|
||||
} ] }
|
||||
metadata:
|
||||
type: object
|
||||
additionalProperties:
|
||||
oneOf:
|
||||
- type: 'null'
|
||||
- type: boolean
|
||||
- type: number
|
||||
- type: string
|
||||
- type: array
|
||||
- type: object
|
||||
description: >-
|
||||
The metadata for the dataset. - E.g. {"description": "My dataset"}.
|
||||
dataset_id:
|
||||
type: string
|
||||
description: >-
|
||||
The ID of the dataset. If not provided, an ID will be generated.
|
||||
additionalProperties: false
|
||||
required:
|
||||
- purpose
|
||||
- source
|
||||
title: RegisterDatasetRequest
|
||||
Benchmark:
|
||||
type: object
|
||||
properties:
|
||||
|
|
@ -1065,47 +1003,6 @@ components:
|
|||
required:
|
||||
- data
|
||||
title: ListBenchmarksResponse
|
||||
RegisterBenchmarkRequest:
|
||||
type: object
|
||||
properties:
|
||||
benchmark_id:
|
||||
type: string
|
||||
description: The ID of the benchmark to register.
|
||||
dataset_id:
|
||||
type: string
|
||||
description: >-
|
||||
The ID of the dataset to use for the benchmark.
|
||||
scoring_functions:
|
||||
type: array
|
||||
items:
|
||||
type: string
|
||||
description: >-
|
||||
The scoring functions to use for the benchmark.
|
||||
provider_benchmark_id:
|
||||
type: string
|
||||
description: >-
|
||||
The ID of the provider benchmark to use for the benchmark.
|
||||
provider_id:
|
||||
type: string
|
||||
description: >-
|
||||
The ID of the provider to use for the benchmark.
|
||||
metadata:
|
||||
type: object
|
||||
additionalProperties:
|
||||
oneOf:
|
||||
- type: 'null'
|
||||
- type: boolean
|
||||
- type: number
|
||||
- type: string
|
||||
- type: array
|
||||
- type: object
|
||||
description: The metadata to use for the benchmark.
|
||||
additionalProperties: false
|
||||
required:
|
||||
- benchmark_id
|
||||
- dataset_id
|
||||
- scoring_functions
|
||||
title: RegisterBenchmarkRequest
|
||||
AggregationFunctionType:
|
||||
type: string
|
||||
enum:
|
||||
|
|
@ -2254,6 +2151,109 @@ components:
|
|||
- hyperparam_search_config
|
||||
- logger_config
|
||||
title: SupervisedFineTuneRequest
|
||||
DataSource:
|
||||
oneOf:
|
||||
- $ref: '#/components/schemas/URIDataSource'
|
||||
- $ref: '#/components/schemas/RowsDataSource'
|
||||
discriminator:
|
||||
propertyName: type
|
||||
mapping:
|
||||
uri: '#/components/schemas/URIDataSource'
|
||||
rows: '#/components/schemas/RowsDataSource'
|
||||
RegisterDatasetRequest:
|
||||
type: object
|
||||
properties:
|
||||
purpose:
|
||||
type: string
|
||||
enum:
|
||||
- post-training/messages
|
||||
- eval/question-answer
|
||||
- eval/messages-answer
|
||||
description: >-
|
||||
The purpose of the dataset. One of: - "post-training/messages": The dataset
|
||||
contains a messages column with list of messages for post-training. {
|
||||
"messages": [ {"role": "user", "content": "Hello, world!"}, {"role": "assistant",
|
||||
"content": "Hello, world!"}, ] } - "eval/question-answer": The dataset
|
||||
contains a question column and an answer column for evaluation. { "question":
|
||||
"What is the capital of France?", "answer": "Paris" } - "eval/messages-answer":
|
||||
The dataset contains a messages column with list of messages and an answer
|
||||
column for evaluation. { "messages": [ {"role": "user", "content": "Hello,
|
||||
my name is John Doe."}, {"role": "assistant", "content": "Hello, John
|
||||
Doe. How can I help you today?"}, {"role": "user", "content": "What's
|
||||
my name?"}, ], "answer": "John Doe" }
|
||||
source:
|
||||
$ref: '#/components/schemas/DataSource'
|
||||
description: >-
|
||||
The data source of the dataset. Ensure that the data source schema is
|
||||
compatible with the purpose of the dataset. Examples: - { "type": "uri",
|
||||
"uri": "https://mywebsite.com/mydata.jsonl" } - { "type": "uri", "uri":
|
||||
"lsfs://mydata.jsonl" } - { "type": "uri", "uri": "data:csv;base64,{base64_content}"
|
||||
} - { "type": "uri", "uri": "huggingface://llamastack/simpleqa?split=train"
|
||||
} - { "type": "rows", "rows": [ { "messages": [ {"role": "user", "content":
|
||||
"Hello, world!"}, {"role": "assistant", "content": "Hello, world!"}, ]
|
||||
} ] }
|
||||
metadata:
|
||||
type: object
|
||||
additionalProperties:
|
||||
oneOf:
|
||||
- type: 'null'
|
||||
- type: boolean
|
||||
- type: number
|
||||
- type: string
|
||||
- type: array
|
||||
- type: object
|
||||
description: >-
|
||||
The metadata for the dataset. - E.g. {"description": "My dataset"}.
|
||||
dataset_id:
|
||||
type: string
|
||||
description: >-
|
||||
The ID of the dataset. If not provided, an ID will be generated.
|
||||
additionalProperties: false
|
||||
required:
|
||||
- purpose
|
||||
- source
|
||||
title: RegisterDatasetRequest
|
||||
RegisterBenchmarkRequest:
|
||||
type: object
|
||||
properties:
|
||||
benchmark_id:
|
||||
type: string
|
||||
description: The ID of the benchmark to register.
|
||||
dataset_id:
|
||||
type: string
|
||||
description: >-
|
||||
The ID of the dataset to use for the benchmark.
|
||||
scoring_functions:
|
||||
type: array
|
||||
items:
|
||||
type: string
|
||||
description: >-
|
||||
The scoring functions to use for the benchmark.
|
||||
provider_benchmark_id:
|
||||
type: string
|
||||
description: >-
|
||||
The ID of the provider benchmark to use for the benchmark.
|
||||
provider_id:
|
||||
type: string
|
||||
description: >-
|
||||
The ID of the provider to use for the benchmark.
|
||||
metadata:
|
||||
type: object
|
||||
additionalProperties:
|
||||
oneOf:
|
||||
- type: 'null'
|
||||
- type: boolean
|
||||
- type: number
|
||||
- type: string
|
||||
- type: array
|
||||
- type: object
|
||||
description: The metadata to use for the benchmark.
|
||||
additionalProperties: false
|
||||
required:
|
||||
- benchmark_id
|
||||
- dataset_id
|
||||
- scoring_functions
|
||||
title: RegisterBenchmarkRequest
|
||||
responses:
|
||||
BadRequest400:
|
||||
description: The request was invalid or malformed
|
||||
|
|
|
|||
13724
docs/static/llama-stack-spec.html
vendored
13724
docs/static/llama-stack-spec.html
vendored
File diff suppressed because it is too large
Load diff
927
docs/static/llama-stack-spec.yaml
vendored
927
docs/static/llama-stack-spec.yaml
vendored
File diff suppressed because it is too large
Load diff
1141
docs/static/stainless-llama-stack-spec.yaml
vendored
1141
docs/static/stainless-llama-stack-spec.yaml
vendored
File diff suppressed because it is too large
Load diff
|
|
@ -24,13 +24,13 @@ classifiers = [
|
|||
"Topic :: Scientific/Engineering :: Information Analysis",
|
||||
]
|
||||
dependencies = [
|
||||
"PyYAML>=6.0",
|
||||
"aiohttp",
|
||||
"fastapi>=0.115.0,<1.0", # server
|
||||
"fire", # for MCP in LLS client
|
||||
"httpx",
|
||||
"jinja2>=3.1.6",
|
||||
"jsonschema",
|
||||
"llama-stack-client>=0.3.0",
|
||||
"openai>=2.5.0",
|
||||
"prompt-toolkit",
|
||||
"python-dotenv",
|
||||
|
|
@ -52,11 +52,8 @@ dependencies = [
|
|||
]
|
||||
|
||||
[project.optional-dependencies]
|
||||
ui = [
|
||||
"streamlit",
|
||||
"pandas",
|
||||
"llama-stack-client>=0.3.0",
|
||||
"streamlit-option-menu",
|
||||
client = [
|
||||
"llama-stack-client>=0.3.0", # Optional for library-only usage
|
||||
]
|
||||
|
||||
[dependency-groups]
|
||||
|
|
@ -104,6 +101,7 @@ type_checking = [
|
|||
"lm-format-enforcer",
|
||||
"mcp",
|
||||
"ollama",
|
||||
"llama-stack-client>=0.3.0",
|
||||
]
|
||||
# These are the dependencies required for running unit tests.
|
||||
unit = [
|
||||
|
|
@ -300,6 +298,7 @@ exclude = [
|
|||
"^src/llama_stack/providers/remote/agents/sample/",
|
||||
"^src/llama_stack/providers/remote/datasetio/huggingface/",
|
||||
"^src/llama_stack/providers/remote/datasetio/nvidia/",
|
||||
"^src/llama_stack/providers/remote/inference/oci/",
|
||||
"^src/llama_stack/providers/remote/inference/bedrock/",
|
||||
"^src/llama_stack/providers/remote/inference/nvidia/",
|
||||
"^src/llama_stack/providers/remote/inference/passthrough/",
|
||||
|
|
|
|||
272
scripts/cleanup_recordings.py
Executable file
272
scripts/cleanup_recordings.py
Executable file
|
|
@ -0,0 +1,272 @@
|
|||
#!/usr/bin/env python3
|
||||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
"""
|
||||
Clean up unused test recordings based on CI test collection.
|
||||
|
||||
This script:
|
||||
1. Reads CI matrix definitions from tests/integration/ci_matrix.json (default + scheduled overrides)
|
||||
2. Uses pytest --collect-only with --json-report to gather all test IDs that run in CI
|
||||
3. Compares against existing recordings to identify unused ones
|
||||
4. Optionally deletes unused recordings
|
||||
|
||||
Usage:
|
||||
# Dry run - see what would be deleted
|
||||
./scripts/cleanup_recordings.py
|
||||
|
||||
# Save manifest of CI test IDs for inspection
|
||||
./scripts/cleanup_recordings.py --manifest ci_tests.txt
|
||||
|
||||
# Actually delete unused recordings
|
||||
./scripts/cleanup_recordings.py --delete
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import os
|
||||
import subprocess
|
||||
import tempfile
|
||||
from collections import defaultdict
|
||||
from pathlib import Path
|
||||
|
||||
REPO_ROOT = Path(__file__).parent.parent
|
||||
|
||||
# Load CI matrix from JSON file
|
||||
CI_MATRIX_FILE = REPO_ROOT / "tests/integration/ci_matrix.json"
|
||||
with open(CI_MATRIX_FILE) as f:
|
||||
_matrix_config = json.load(f)
|
||||
|
||||
DEFAULT_CI_MATRIX: list[dict[str, str]] = _matrix_config["default"]
|
||||
SCHEDULED_MATRICES: dict[str, list[dict[str, str]]] = _matrix_config.get("schedules", {})
|
||||
|
||||
|
||||
def _unique_configs(entries):
|
||||
seen: set[tuple[str, str]] = set()
|
||||
for entry in entries:
|
||||
suite = entry["suite"]
|
||||
setup = entry["setup"]
|
||||
key = (suite, setup)
|
||||
if key in seen:
|
||||
continue
|
||||
seen.add(key)
|
||||
yield {"suite": suite, "setup": setup}
|
||||
|
||||
|
||||
def iter_all_ci_configs() -> list[dict[str, str]]:
|
||||
"""Return unique CI configs across default and scheduled matrices."""
|
||||
combined = list(DEFAULT_CI_MATRIX)
|
||||
for configs in SCHEDULED_MATRICES.values():
|
||||
combined.extend(configs)
|
||||
return list(_unique_configs(combined))
|
||||
|
||||
|
||||
def collect_ci_tests():
|
||||
"""Collect all test IDs that would run in CI using --collect-only with JSON output."""
|
||||
|
||||
all_test_ids = set()
|
||||
configs = iter_all_ci_configs()
|
||||
|
||||
for config in configs:
|
||||
print(f"Collecting tests for suite={config['suite']}, setup={config['setup']}...")
|
||||
|
||||
# Create a temporary file for JSON report
|
||||
with tempfile.NamedTemporaryFile(mode="w", suffix=".json", delete=False) as f:
|
||||
json_report_file = f.name
|
||||
|
||||
try:
|
||||
# Configure environment for collection run
|
||||
env = os.environ.copy()
|
||||
env["PYTEST_ADDOPTS"] = f"--json-report --json-report-file={json_report_file}"
|
||||
repo_path = str(REPO_ROOT)
|
||||
existing_path = env.get("PYTHONPATH", "")
|
||||
env["PYTHONPATH"] = f"{repo_path}{os.pathsep}{existing_path}" if existing_path else repo_path
|
||||
|
||||
result = subprocess.run(
|
||||
[
|
||||
"./scripts/integration-tests.sh",
|
||||
"--collect-only",
|
||||
"--suite",
|
||||
config["suite"],
|
||||
"--setup",
|
||||
config["setup"],
|
||||
],
|
||||
capture_output=True,
|
||||
text=True,
|
||||
cwd=REPO_ROOT,
|
||||
env=env,
|
||||
)
|
||||
|
||||
if result.returncode != 0:
|
||||
raise RuntimeError(
|
||||
"Test collection failed.\n"
|
||||
f"Command: {' '.join(result.args)}\n"
|
||||
f"stdout:\n{result.stdout}\n"
|
||||
f"stderr:\n{result.stderr}"
|
||||
)
|
||||
|
||||
# Parse JSON report to extract test IDs
|
||||
try:
|
||||
with open(json_report_file) as f:
|
||||
report = json.load(f)
|
||||
|
||||
# The "collectors" field contains collected test items
|
||||
# Each collector has a "result" array with test node IDs
|
||||
for collector in report.get("collectors", []):
|
||||
for item in collector.get("result", []):
|
||||
# The "nodeid" field is the test ID
|
||||
if "nodeid" in item:
|
||||
all_test_ids.add(item["nodeid"])
|
||||
|
||||
print(f" Collected {len(all_test_ids)} test IDs so far")
|
||||
|
||||
except (json.JSONDecodeError, FileNotFoundError) as e:
|
||||
print(f" Warning: Failed to parse JSON report: {e}")
|
||||
continue
|
||||
|
||||
finally:
|
||||
# Clean up temp file
|
||||
if os.path.exists(json_report_file):
|
||||
os.unlink(json_report_file)
|
||||
|
||||
print(f"\nTotal unique test IDs collected: {len(all_test_ids)}")
|
||||
return all_test_ids, configs
|
||||
|
||||
|
||||
def get_base_test_id(test_id: str) -> str:
|
||||
"""Extract base test ID without parameterization.
|
||||
|
||||
Example:
|
||||
'tests/integration/inference/test_foo.py::test_bar[param1-param2]'
|
||||
-> 'tests/integration/inference/test_foo.py::test_bar'
|
||||
"""
|
||||
return test_id.split("[")[0] if "[" in test_id else test_id
|
||||
|
||||
|
||||
def find_all_recordings():
|
||||
"""Find all recording JSON files."""
|
||||
return list((REPO_ROOT / "tests/integration").rglob("recordings/*.json"))
|
||||
|
||||
|
||||
def analyze_recordings(ci_test_ids, dry_run=True):
|
||||
"""Analyze recordings and identify unused ones."""
|
||||
|
||||
# Use full test IDs with parameterization for exact matching
|
||||
all_recordings = find_all_recordings()
|
||||
print(f"\nTotal recording files: {len(all_recordings)}")
|
||||
|
||||
# Categorize recordings
|
||||
used_recordings = []
|
||||
unused_recordings = []
|
||||
shared_recordings = [] # model-list endpoints without test_id
|
||||
parse_errors = []
|
||||
|
||||
for json_file in all_recordings:
|
||||
try:
|
||||
with open(json_file) as f:
|
||||
data = json.load(f)
|
||||
|
||||
test_id = data.get("test_id", "")
|
||||
|
||||
if not test_id:
|
||||
# Shared/infrastructure recordings (model lists, etc)
|
||||
shared_recordings.append(json_file)
|
||||
continue
|
||||
|
||||
# Match exact test_id (with full parameterization)
|
||||
if test_id in ci_test_ids:
|
||||
used_recordings.append(json_file)
|
||||
else:
|
||||
unused_recordings.append((json_file, test_id))
|
||||
|
||||
except Exception as e:
|
||||
parse_errors.append((json_file, str(e)))
|
||||
|
||||
# Print summary
|
||||
print("\nRecording Analysis:")
|
||||
print(f" Used in CI: {len(used_recordings)}")
|
||||
print(f" Shared (no ID): {len(shared_recordings)}")
|
||||
print(f" UNUSED: {len(unused_recordings)}")
|
||||
print(f" Parse errors: {len(parse_errors)}")
|
||||
|
||||
if unused_recordings:
|
||||
print("\nUnused recordings by test:")
|
||||
|
||||
# Group by base test ID
|
||||
by_test = defaultdict(list)
|
||||
for file, test_id in unused_recordings:
|
||||
base = get_base_test_id(test_id)
|
||||
by_test[base].append(file)
|
||||
|
||||
for base_test, files in sorted(by_test.items()):
|
||||
print(f"\n {base_test}")
|
||||
print(f" ({len(files)} recording(s))")
|
||||
for f in files[:3]:
|
||||
print(f" - {f.relative_to(REPO_ROOT / 'tests/integration')}")
|
||||
if len(files) > 3:
|
||||
print(f" ... and {len(files) - 3} more")
|
||||
|
||||
if parse_errors:
|
||||
print("\nParse errors:")
|
||||
for file, error in parse_errors[:5]:
|
||||
print(f" {file.relative_to(REPO_ROOT)}: {error}")
|
||||
if len(parse_errors) > 5:
|
||||
print(f" ... and {len(parse_errors) - 5} more")
|
||||
|
||||
# Perform cleanup
|
||||
if not dry_run:
|
||||
print(f"\nDeleting {len(unused_recordings)} unused recordings...")
|
||||
for file, _ in unused_recordings:
|
||||
file.unlink()
|
||||
print(f" Deleted: {file.relative_to(REPO_ROOT / 'tests/integration')}")
|
||||
print("✅ Cleanup complete")
|
||||
else:
|
||||
print("\n(Dry run - no files deleted)")
|
||||
print("\nTo delete these files, run with --delete")
|
||||
|
||||
return len(unused_recordings)
|
||||
|
||||
|
||||
def main():
|
||||
parser = argparse.ArgumentParser(
|
||||
description="Clean up unused test recordings based on CI test collection",
|
||||
formatter_class=argparse.RawDescriptionHelpFormatter,
|
||||
epilog=__doc__,
|
||||
)
|
||||
parser.add_argument("--delete", action="store_true", help="Actually delete unused recordings (default is dry-run)")
|
||||
parser.add_argument("--manifest", help="Save collected test IDs to file (optional)")
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
print("=" * 60)
|
||||
print("Recording Cleanup Utility")
|
||||
print("=" * 60)
|
||||
|
||||
ci_configs = iter_all_ci_configs()
|
||||
|
||||
print(f"\nDetected CI configurations: {len(ci_configs)}")
|
||||
for config in ci_configs:
|
||||
print(f" - suite={config['suite']}, setup={config['setup']}")
|
||||
|
||||
# Collect test IDs from CI configurations
|
||||
ci_test_ids, _ = collect_ci_tests()
|
||||
|
||||
if args.manifest:
|
||||
with open(args.manifest, "w") as f:
|
||||
for test_id in sorted(ci_test_ids):
|
||||
f.write(f"{test_id}\n")
|
||||
print(f"\nSaved test IDs to: {args.manifest}")
|
||||
|
||||
# Analyze and cleanup
|
||||
unused_count = analyze_recordings(ci_test_ids, dry_run=not args.delete)
|
||||
|
||||
print("\n" + "=" * 60)
|
||||
if unused_count > 0 and not args.delete:
|
||||
print("Run with --delete to remove unused recordings")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
61
scripts/generate_ci_matrix.py
Executable file
61
scripts/generate_ci_matrix.py
Executable file
|
|
@ -0,0 +1,61 @@
|
|||
#!/usr/bin/env python3
|
||||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
"""
|
||||
Generate CI test matrix from ci_matrix.json with schedule/input overrides.
|
||||
|
||||
This script is used by .github/workflows/integration-tests.yml to generate
|
||||
the test matrix dynamically based on the CI_MATRIX definition.
|
||||
"""
|
||||
|
||||
import json
|
||||
from pathlib import Path
|
||||
|
||||
CI_MATRIX_FILE = Path(__file__).parent.parent / "tests/integration/ci_matrix.json"
|
||||
|
||||
with open(CI_MATRIX_FILE) as f:
|
||||
matrix_config = json.load(f)
|
||||
|
||||
DEFAULT_MATRIX = matrix_config["default"]
|
||||
SCHEDULE_MATRICES: dict[str, list[dict[str, str]]] = matrix_config.get("schedules", {})
|
||||
|
||||
|
||||
def generate_matrix(schedule="", test_setup=""):
|
||||
"""
|
||||
Generate test matrix based on schedule or manual input.
|
||||
|
||||
Args:
|
||||
schedule: GitHub cron schedule string (e.g., "1 0 * * 0" for weekly)
|
||||
test_setup: Manual test setup input (e.g., "ollama-vision")
|
||||
|
||||
Returns:
|
||||
Matrix configuration as JSON string
|
||||
"""
|
||||
# Weekly scheduled test matrices
|
||||
if schedule and schedule in SCHEDULE_MATRICES:
|
||||
matrix = SCHEDULE_MATRICES[schedule]
|
||||
# Manual input for specific setup
|
||||
elif test_setup == "ollama-vision":
|
||||
matrix = [{"suite": "vision", "setup": "ollama-vision"}]
|
||||
# Default: use JSON-defined matrix
|
||||
else:
|
||||
matrix = DEFAULT_MATRIX
|
||||
|
||||
# GitHub Actions expects {"include": [...]} format
|
||||
return json.dumps({"include": matrix})
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
import argparse
|
||||
|
||||
parser = argparse.ArgumentParser(description="Generate CI test matrix")
|
||||
parser.add_argument("--schedule", default="", help="GitHub schedule cron string")
|
||||
parser.add_argument("--test-setup", default="", help="Manual test setup input")
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
print(generate_matrix(args.schedule, args.test_setup))
|
||||
|
|
@ -231,10 +231,12 @@ if [[ "$STACK_CONFIG" == *"server:"* && "$COLLECT_ONLY" == false ]]; then
|
|||
# Use a fixed port for the OTEL collector so the server can connect to it
|
||||
COLLECTOR_PORT=4317
|
||||
export LLAMA_STACK_TEST_COLLECTOR_PORT="${COLLECTOR_PORT}"
|
||||
export OTEL_EXPORTER_OTLP_ENDPOINT="http://127.0.0.1:${COLLECTOR_PORT}"
|
||||
# Disabled: https://github.com/llamastack/llama-stack/issues/4089
|
||||
#export OTEL_EXPORTER_OTLP_ENDPOINT="http://127.0.0.1:${COLLECTOR_PORT}"
|
||||
export OTEL_EXPORTER_OTLP_PROTOCOL="http/protobuf"
|
||||
export OTEL_BSP_SCHEDULE_DELAY="200"
|
||||
export OTEL_BSP_EXPORT_TIMEOUT="2000"
|
||||
export OTEL_METRIC_EXPORT_INTERVAL="200"
|
||||
|
||||
# remove "server:" from STACK_CONFIG
|
||||
stack_config=$(echo "$STACK_CONFIG" | sed 's/^server://')
|
||||
|
|
@ -336,7 +338,11 @@ if [[ "$STACK_CONFIG" == *"docker:"* && "$COLLECT_ONLY" == false ]]; then
|
|||
DOCKER_ENV_VARS=""
|
||||
DOCKER_ENV_VARS="$DOCKER_ENV_VARS -e LLAMA_STACK_TEST_INFERENCE_MODE=$INFERENCE_MODE"
|
||||
DOCKER_ENV_VARS="$DOCKER_ENV_VARS -e LLAMA_STACK_TEST_STACK_CONFIG_TYPE=server"
|
||||
DOCKER_ENV_VARS="$DOCKER_ENV_VARS -e OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:${COLLECTOR_PORT}"
|
||||
# Disabled: https://github.com/llamastack/llama-stack/issues/4089
|
||||
#DOCKER_ENV_VARS="$DOCKER_ENV_VARS -e OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:${COLLECTOR_PORT}"
|
||||
DOCKER_ENV_VARS="$DOCKER_ENV_VARS -e OTEL_METRIC_EXPORT_INTERVAL=200"
|
||||
DOCKER_ENV_VARS="$DOCKER_ENV_VARS -e OTEL_BSP_SCHEDULE_DELAY=200"
|
||||
DOCKER_ENV_VARS="$DOCKER_ENV_VARS -e OTEL_BSP_EXPORT_TIMEOUT=2000"
|
||||
|
||||
# Pass through API keys if they exist
|
||||
[ -n "${TOGETHER_API_KEY:-}" ] && DOCKER_ENV_VARS="$DOCKER_ENV_VARS -e TOGETHER_API_KEY=$TOGETHER_API_KEY"
|
||||
|
|
@ -349,6 +355,10 @@ if [[ "$STACK_CONFIG" == *"docker:"* && "$COLLECT_ONLY" == false ]]; then
|
|||
[ -n "${OLLAMA_URL:-}" ] && DOCKER_ENV_VARS="$DOCKER_ENV_VARS -e OLLAMA_URL=$OLLAMA_URL"
|
||||
[ -n "${SAFETY_MODEL:-}" ] && DOCKER_ENV_VARS="$DOCKER_ENV_VARS -e SAFETY_MODEL=$SAFETY_MODEL"
|
||||
|
||||
if [[ "$TEST_SETUP" == "vllm" ]]; then
|
||||
DOCKER_ENV_VARS="$DOCKER_ENV_VARS -e VLLM_URL=http://localhost:8000/v1"
|
||||
fi
|
||||
|
||||
# Determine the actual image name (may have localhost/ prefix)
|
||||
IMAGE_NAME=$(docker images --format "{{.Repository}}:{{.Tag}}" | grep "distribution-$DISTRO:dev$" | head -1)
|
||||
if [[ -z "$IMAGE_NAME" ]]; then
|
||||
|
|
@ -401,11 +411,6 @@ fi
|
|||
echo "=== Running Integration Tests ==="
|
||||
EXCLUDE_TESTS="builtin_tool or safety_with_image or code_interpreter or test_rag"
|
||||
|
||||
# Additional exclusions for vllm setup
|
||||
if [[ "$TEST_SETUP" == "vllm" ]]; then
|
||||
EXCLUDE_TESTS="${EXCLUDE_TESTS} or test_inference_store_tool_calls"
|
||||
fi
|
||||
|
||||
PYTEST_PATTERN="not( $EXCLUDE_TESTS )"
|
||||
if [[ -n "$TEST_PATTERN" ]]; then
|
||||
PYTEST_PATTERN="${PYTEST_PATTERN} and $TEST_PATTERN"
|
||||
|
|
|
|||
|
|
@ -6,7 +6,7 @@
|
|||
# the root directory of this source tree.
|
||||
|
||||
set -e
|
||||
cd src/llama_stack/ui
|
||||
cd src/llama_stack_ui
|
||||
|
||||
if [ ! -d node_modules ] || [ ! -x node_modules/.bin/prettier ] || [ ! -x node_modules/.bin/eslint ]; then
|
||||
echo "UI dependencies not installed, skipping prettier/linter check"
|
||||
|
|
|
|||
|
|
@ -3,8 +3,3 @@
|
|||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
from llama_stack.core.library_client import ( # noqa: F401
|
||||
AsyncLlamaStackAsLibraryClient,
|
||||
LlamaStackAsLibraryClient,
|
||||
)
|
||||
|
|
|
|||
|
|
@ -87,6 +87,7 @@ class Agents(Protocol):
|
|||
"List of guardrails to apply during response generation. Guardrails provide safety and content moderation."
|
||||
),
|
||||
] = None,
|
||||
max_tool_calls: int | None = None,
|
||||
) -> OpenAIResponseObject | AsyncIterator[OpenAIResponseObjectStream]:
|
||||
"""Create a model response.
|
||||
|
||||
|
|
@ -97,6 +98,7 @@ class Agents(Protocol):
|
|||
:param conversation: (Optional) The ID of a conversation to add the response to. Must begin with 'conv_'. Input and output messages will be automatically added to the conversation.
|
||||
:param include: (Optional) Additional fields to include in the response.
|
||||
:param guardrails: (Optional) List of guardrails to apply during response generation. Can be guardrail IDs (strings) or guardrail specifications.
|
||||
:param max_tool_calls: (Optional) Max number of total calls to built-in tools that can be processed in a response.
|
||||
:returns: An OpenAIResponseObject.
|
||||
"""
|
||||
...
|
||||
|
|
|
|||
|
|
@ -403,7 +403,7 @@ class OpenAIResponseText(BaseModel):
|
|||
|
||||
|
||||
# Must match type Literals of OpenAIResponseInputToolWebSearch below
|
||||
WebSearchToolTypes = ["web_search", "web_search_preview", "web_search_preview_2025_03_11"]
|
||||
WebSearchToolTypes = ["web_search", "web_search_preview", "web_search_preview_2025_03_11", "web_search_2025_08_26"]
|
||||
|
||||
|
||||
@json_schema_type
|
||||
|
|
@ -415,9 +415,12 @@ class OpenAIResponseInputToolWebSearch(BaseModel):
|
|||
"""
|
||||
|
||||
# Must match values of WebSearchToolTypes above
|
||||
type: Literal["web_search"] | Literal["web_search_preview"] | Literal["web_search_preview_2025_03_11"] = (
|
||||
"web_search"
|
||||
)
|
||||
type: (
|
||||
Literal["web_search"]
|
||||
| Literal["web_search_preview"]
|
||||
| Literal["web_search_preview_2025_03_11"]
|
||||
| Literal["web_search_2025_08_26"]
|
||||
) = "web_search"
|
||||
# TODO: actually use search_context_size somewhere...
|
||||
search_context_size: str | None = Field(default="medium", pattern="^low|medium|high$")
|
||||
# TODO: add user_location
|
||||
|
|
@ -591,6 +594,7 @@ class OpenAIResponseObject(BaseModel):
|
|||
:param truncation: (Optional) Truncation strategy applied to the response
|
||||
:param usage: (Optional) Token usage information for the response
|
||||
:param instructions: (Optional) System message inserted into the model's context
|
||||
:param max_tool_calls: (Optional) Max number of total calls to built-in tools that can be processed in a response
|
||||
"""
|
||||
|
||||
created_at: int
|
||||
|
|
@ -612,6 +616,7 @@ class OpenAIResponseObject(BaseModel):
|
|||
truncation: str | None = None
|
||||
usage: OpenAIResponseUsage | None = None
|
||||
instructions: str | None = None
|
||||
max_tool_calls: int | None = None
|
||||
|
||||
|
||||
@json_schema_type
|
||||
|
|
|
|||
|
|
@ -74,7 +74,7 @@ class Benchmarks(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/eval/benchmarks", method="POST", level=LLAMA_STACK_API_V1ALPHA)
|
||||
@webmethod(route="/eval/benchmarks", method="POST", level=LLAMA_STACK_API_V1ALPHA, deprecated=True)
|
||||
async def register_benchmark(
|
||||
self,
|
||||
benchmark_id: str,
|
||||
|
|
@ -95,7 +95,7 @@ class Benchmarks(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/eval/benchmarks/{benchmark_id}", method="DELETE", level=LLAMA_STACK_API_V1ALPHA)
|
||||
@webmethod(route="/eval/benchmarks/{benchmark_id}", method="DELETE", level=LLAMA_STACK_API_V1ALPHA, deprecated=True)
|
||||
async def unregister_benchmark(self, benchmark_id: str) -> None:
|
||||
"""Unregister a benchmark.
|
||||
|
||||
|
|
|
|||
|
|
@ -34,3 +34,44 @@ class PaginatedResponse(BaseModel):
|
|||
data: list[dict[str, Any]]
|
||||
has_more: bool
|
||||
url: str | None = None
|
||||
|
||||
|
||||
# This is a short term solution to allow inference API to return metrics
|
||||
# The ideal way to do this is to have a way for all response types to include metrics
|
||||
# and all metric events logged to the telemetry API to be included with the response
|
||||
# To do this, we will need to augment all response types with a metrics field.
|
||||
# We have hit a blocker from stainless SDK that prevents us from doing this.
|
||||
# The blocker is that if we were to augment the response types that have a data field
|
||||
# in them like so
|
||||
# class ListModelsResponse(BaseModel):
|
||||
# metrics: Optional[List[MetricEvent]] = None
|
||||
# data: List[Models]
|
||||
# ...
|
||||
# The client SDK will need to access the data by using a .data field, which is not
|
||||
# ergonomic. Stainless SDK does support unwrapping the response type, but it
|
||||
# requires that the response type to only have a single field.
|
||||
|
||||
# We will need a way in the client SDK to signal that the metrics are needed
|
||||
# and if they are needed, the client SDK has to return the full response type
|
||||
# without unwrapping it.
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class MetricInResponse(BaseModel):
|
||||
"""A metric value included in API responses.
|
||||
:param metric: The name of the metric
|
||||
:param value: The numeric value of the metric
|
||||
:param unit: (Optional) The unit of measurement for the metric value
|
||||
"""
|
||||
|
||||
metric: str
|
||||
value: int | float
|
||||
unit: str | None = None
|
||||
|
||||
|
||||
class MetricResponseMixin(BaseModel):
|
||||
"""Mixin class for API responses that can include metrics.
|
||||
:param metrics: (Optional) List of metrics associated with the API response
|
||||
"""
|
||||
|
||||
metrics: list[MetricInResponse] | None = None
|
||||
|
|
|
|||
22
src/llama_stack/apis/common/tracing.py
Normal file
22
src/llama_stack/apis/common/tracing.py
Normal file
|
|
@ -0,0 +1,22 @@
|
|||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
|
||||
def telemetry_traceable(cls):
|
||||
"""
|
||||
Mark a protocol for automatic tracing when telemetry is enabled.
|
||||
|
||||
This is a metadata-only decorator with no dependencies on core.
|
||||
Actual tracing is applied by core routers at runtime if telemetry is enabled.
|
||||
|
||||
Usage:
|
||||
@runtime_checkable
|
||||
@telemetry_traceable
|
||||
class MyProtocol(Protocol):
|
||||
...
|
||||
"""
|
||||
cls.__marked_for_tracing__ = True
|
||||
return cls
|
||||
|
|
@ -6,26 +6,22 @@
|
|||
|
||||
from .conversations import (
|
||||
Conversation,
|
||||
ConversationCreateRequest,
|
||||
ConversationDeletedResource,
|
||||
ConversationItem,
|
||||
ConversationItemCreateRequest,
|
||||
ConversationItemDeletedResource,
|
||||
ConversationItemList,
|
||||
Conversations,
|
||||
ConversationUpdateRequest,
|
||||
Metadata,
|
||||
)
|
||||
|
||||
__all__ = [
|
||||
"Conversation",
|
||||
"ConversationCreateRequest",
|
||||
"ConversationDeletedResource",
|
||||
"ConversationItem",
|
||||
"ConversationItemCreateRequest",
|
||||
"ConversationItemDeletedResource",
|
||||
"ConversationItemList",
|
||||
"Conversations",
|
||||
"ConversationUpdateRequest",
|
||||
"Metadata",
|
||||
]
|
||||
|
|
|
|||
|
|
@ -20,8 +20,8 @@ from llama_stack.apis.agents.openai_responses import (
|
|||
OpenAIResponseOutputMessageMCPListTools,
|
||||
OpenAIResponseOutputMessageWebSearchToolCall,
|
||||
)
|
||||
from llama_stack.apis.common.tracing import telemetry_traceable
|
||||
from llama_stack.apis.version import LLAMA_STACK_API_V1
|
||||
from llama_stack.core.telemetry.trace_protocol import trace_protocol
|
||||
from llama_stack.schema_utils import json_schema_type, register_schema, webmethod
|
||||
|
||||
Metadata = dict[str, str]
|
||||
|
|
@ -102,32 +102,6 @@ register_schema(ConversationItem, name="ConversationItem")
|
|||
# ]
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class ConversationCreateRequest(BaseModel):
|
||||
"""Request body for creating a conversation."""
|
||||
|
||||
items: list[ConversationItem] | None = Field(
|
||||
default=[],
|
||||
description="Initial items to include in the conversation context. You may add up to 20 items at a time.",
|
||||
max_length=20,
|
||||
)
|
||||
metadata: Metadata | None = Field(
|
||||
default={},
|
||||
description="Set of 16 key-value pairs that can be attached to an object. Useful for storing additional information",
|
||||
max_length=16,
|
||||
)
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class ConversationUpdateRequest(BaseModel):
|
||||
"""Request body for updating a conversation."""
|
||||
|
||||
metadata: Metadata = Field(
|
||||
...,
|
||||
description="Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.",
|
||||
)
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class ConversationDeletedResource(BaseModel):
|
||||
"""Response for deleted conversation."""
|
||||
|
|
@ -183,7 +157,7 @@ class ConversationItemDeletedResource(BaseModel):
|
|||
|
||||
|
||||
@runtime_checkable
|
||||
@trace_protocol
|
||||
@telemetry_traceable
|
||||
class Conversations(Protocol):
|
||||
"""Conversations
|
||||
|
||||
|
|
|
|||
|
|
@ -146,7 +146,7 @@ class ListDatasetsResponse(BaseModel):
|
|||
|
||||
|
||||
class Datasets(Protocol):
|
||||
@webmethod(route="/datasets", method="POST", level=LLAMA_STACK_API_V1BETA)
|
||||
@webmethod(route="/datasets", method="POST", level=LLAMA_STACK_API_V1BETA, deprecated=True)
|
||||
async def register_dataset(
|
||||
self,
|
||||
purpose: DatasetPurpose,
|
||||
|
|
@ -235,7 +235,7 @@ class Datasets(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/datasets/{dataset_id:path}", method="DELETE", level=LLAMA_STACK_API_V1BETA)
|
||||
@webmethod(route="/datasets/{dataset_id:path}", method="DELETE", level=LLAMA_STACK_API_V1BETA, deprecated=True)
|
||||
async def unregister_dataset(
|
||||
self,
|
||||
dataset_id: str,
|
||||
|
|
|
|||
|
|
@ -11,8 +11,8 @@ from fastapi import File, Form, Response, UploadFile
|
|||
from pydantic import BaseModel, Field
|
||||
|
||||
from llama_stack.apis.common.responses import Order
|
||||
from llama_stack.apis.common.tracing import telemetry_traceable
|
||||
from llama_stack.apis.version import LLAMA_STACK_API_V1
|
||||
from llama_stack.core.telemetry.trace_protocol import trace_protocol
|
||||
from llama_stack.schema_utils import json_schema_type, webmethod
|
||||
|
||||
|
||||
|
|
@ -102,7 +102,7 @@ class OpenAIFileDeleteResponse(BaseModel):
|
|||
|
||||
|
||||
@runtime_checkable
|
||||
@trace_protocol
|
||||
@telemetry_traceable
|
||||
class Files(Protocol):
|
||||
"""Files
|
||||
|
||||
|
|
|
|||
|
|
@ -1,43 +0,0 @@
|
|||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
from termcolor import cprint
|
||||
|
||||
from llama_stack.apis.inference import (
|
||||
ChatCompletionResponseEventType,
|
||||
ChatCompletionResponseStreamChunk,
|
||||
)
|
||||
|
||||
|
||||
class LogEvent:
|
||||
def __init__(
|
||||
self,
|
||||
content: str = "",
|
||||
end: str = "\n",
|
||||
color="white",
|
||||
):
|
||||
self.content = content
|
||||
self.color = color
|
||||
self.end = "\n" if end is None else end
|
||||
|
||||
def print(self, flush=True):
|
||||
cprint(f"{self.content}", color=self.color, end=self.end, flush=flush)
|
||||
|
||||
|
||||
class EventLogger:
|
||||
async def log(self, event_generator):
|
||||
async for chunk in event_generator:
|
||||
if isinstance(chunk, ChatCompletionResponseStreamChunk):
|
||||
event = chunk.event
|
||||
if event.event_type == ChatCompletionResponseEventType.start:
|
||||
yield LogEvent("Assistant> ", color="cyan", end="")
|
||||
elif event.event_type == ChatCompletionResponseEventType.progress:
|
||||
yield LogEvent(event.delta, color="yellow", end="")
|
||||
elif event.event_type == ChatCompletionResponseEventType.complete:
|
||||
yield LogEvent("")
|
||||
else:
|
||||
yield LogEvent("Assistant> ", color="cyan", end="")
|
||||
yield LogEvent(chunk.completion_message.content, color="yellow")
|
||||
|
|
@ -5,7 +5,7 @@
|
|||
# the root directory of this source tree.
|
||||
|
||||
from collections.abc import AsyncIterator
|
||||
from enum import Enum
|
||||
from enum import Enum, StrEnum
|
||||
from typing import (
|
||||
Annotated,
|
||||
Any,
|
||||
|
|
@ -15,29 +15,18 @@ from typing import (
|
|||
)
|
||||
|
||||
from fastapi import Body
|
||||
from pydantic import BaseModel, Field, field_validator
|
||||
from pydantic import BaseModel, Field
|
||||
from typing_extensions import TypedDict
|
||||
|
||||
from llama_stack.apis.common.content_types import ContentDelta, InterleavedContent
|
||||
from llama_stack.apis.common.responses import Order
|
||||
from llama_stack.apis.common.content_types import InterleavedContent
|
||||
from llama_stack.apis.common.responses import (
|
||||
Order,
|
||||
)
|
||||
from llama_stack.apis.common.tracing import telemetry_traceable
|
||||
from llama_stack.apis.models import Model
|
||||
from llama_stack.apis.version import LLAMA_STACK_API_V1, LLAMA_STACK_API_V1ALPHA
|
||||
from llama_stack.core.telemetry.telemetry import MetricResponseMixin
|
||||
from llama_stack.core.telemetry.trace_protocol import trace_protocol
|
||||
from llama_stack.models.llama.datatypes import (
|
||||
BuiltinTool,
|
||||
StopReason,
|
||||
ToolCall,
|
||||
ToolDefinition,
|
||||
ToolPromptFormat,
|
||||
)
|
||||
from llama_stack.schema_utils import json_schema_type, register_schema, webmethod
|
||||
|
||||
register_schema(ToolCall)
|
||||
register_schema(ToolDefinition)
|
||||
|
||||
from enum import StrEnum
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class GreedySamplingStrategy(BaseModel):
|
||||
|
|
@ -202,58 +191,6 @@ class ToolResponseMessage(BaseModel):
|
|||
content: InterleavedContent
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class CompletionMessage(BaseModel):
|
||||
"""A message containing the model's (assistant) response in a chat conversation.
|
||||
|
||||
:param role: Must be "assistant" to identify this as the model's response
|
||||
:param content: The content of the model's response
|
||||
:param stop_reason: Reason why the model stopped generating. Options are:
|
||||
- `StopReason.end_of_turn`: The model finished generating the entire response.
|
||||
- `StopReason.end_of_message`: The model finished generating but generated a partial response -- usually, a tool call. The user may call the tool and continue the conversation with the tool's response.
|
||||
- `StopReason.out_of_tokens`: The model ran out of token budget.
|
||||
:param tool_calls: List of tool calls. Each tool call is a ToolCall object.
|
||||
"""
|
||||
|
||||
role: Literal["assistant"] = "assistant"
|
||||
content: InterleavedContent
|
||||
stop_reason: StopReason
|
||||
tool_calls: list[ToolCall] | None = Field(default_factory=lambda: [])
|
||||
|
||||
|
||||
Message = Annotated[
|
||||
UserMessage | SystemMessage | ToolResponseMessage | CompletionMessage,
|
||||
Field(discriminator="role"),
|
||||
]
|
||||
register_schema(Message, name="Message")
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class ToolResponse(BaseModel):
|
||||
"""Response from a tool invocation.
|
||||
|
||||
:param call_id: Unique identifier for the tool call this response is for
|
||||
:param tool_name: Name of the tool that was invoked
|
||||
:param content: The response content from the tool
|
||||
:param metadata: (Optional) Additional metadata about the tool response
|
||||
"""
|
||||
|
||||
call_id: str
|
||||
tool_name: BuiltinTool | str
|
||||
content: InterleavedContent
|
||||
metadata: dict[str, Any] | None = None
|
||||
|
||||
@field_validator("tool_name", mode="before")
|
||||
@classmethod
|
||||
def validate_field(cls, v):
|
||||
if isinstance(v, str):
|
||||
try:
|
||||
return BuiltinTool(v)
|
||||
except ValueError:
|
||||
return v
|
||||
return v
|
||||
|
||||
|
||||
class ToolChoice(Enum):
|
||||
"""Whether tool use is required or automatic. This is a hint to the model which may not be followed. It depends on the Instruction Following capabilities of the model.
|
||||
|
||||
|
|
@ -290,22 +227,6 @@ class ChatCompletionResponseEventType(Enum):
|
|||
progress = "progress"
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class ChatCompletionResponseEvent(BaseModel):
|
||||
"""An event during chat completion generation.
|
||||
|
||||
:param event_type: Type of the event
|
||||
:param delta: Content generated since last event. This can be one or more tokens, or a tool call.
|
||||
:param logprobs: Optional log probabilities for generated tokens
|
||||
:param stop_reason: Optional reason why generation stopped, if complete
|
||||
"""
|
||||
|
||||
event_type: ChatCompletionResponseEventType
|
||||
delta: ContentDelta
|
||||
logprobs: list[TokenLogProbs] | None = None
|
||||
stop_reason: StopReason | None = None
|
||||
|
||||
|
||||
class ResponseFormatType(StrEnum):
|
||||
"""Types of formats for structured (guided) decoding.
|
||||
|
||||
|
|
@ -358,34 +279,6 @@ class CompletionRequest(BaseModel):
|
|||
logprobs: LogProbConfig | None = None
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class CompletionResponse(MetricResponseMixin):
|
||||
"""Response from a completion request.
|
||||
|
||||
:param content: The generated completion text
|
||||
:param stop_reason: Reason why generation stopped
|
||||
:param logprobs: Optional log probabilities for generated tokens
|
||||
"""
|
||||
|
||||
content: str
|
||||
stop_reason: StopReason
|
||||
logprobs: list[TokenLogProbs] | None = None
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class CompletionResponseStreamChunk(MetricResponseMixin):
|
||||
"""A chunk of a streamed completion response.
|
||||
|
||||
:param delta: New content generated since last chunk. This can be one or more tokens.
|
||||
:param stop_reason: Optional reason why generation stopped, if complete
|
||||
:param logprobs: Optional log probabilities for generated tokens
|
||||
"""
|
||||
|
||||
delta: str
|
||||
stop_reason: StopReason | None = None
|
||||
logprobs: list[TokenLogProbs] | None = None
|
||||
|
||||
|
||||
class SystemMessageBehavior(Enum):
|
||||
"""Config for how to override the default system prompt.
|
||||
|
||||
|
|
@ -399,70 +292,6 @@ class SystemMessageBehavior(Enum):
|
|||
replace = "replace"
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class ToolConfig(BaseModel):
|
||||
"""Configuration for tool use.
|
||||
|
||||
:param tool_choice: (Optional) Whether tool use is automatic, required, or none. Can also specify a tool name to use a specific tool. Defaults to ToolChoice.auto.
|
||||
:param tool_prompt_format: (Optional) Instructs the model how to format tool calls. By default, Llama Stack will attempt to use a format that is best adapted to the model.
|
||||
- `ToolPromptFormat.json`: The tool calls are formatted as a JSON object.
|
||||
- `ToolPromptFormat.function_tag`: The tool calls are enclosed in a <function=function_name> tag.
|
||||
- `ToolPromptFormat.python_list`: The tool calls are output as Python syntax -- a list of function calls.
|
||||
:param system_message_behavior: (Optional) Config for how to override the default system prompt.
|
||||
- `SystemMessageBehavior.append`: Appends the provided system message to the default system prompt.
|
||||
- `SystemMessageBehavior.replace`: Replaces the default system prompt with the provided system message. The system message can include the string
|
||||
'{{function_definitions}}' to indicate where the function definitions should be inserted.
|
||||
"""
|
||||
|
||||
tool_choice: ToolChoice | str | None = Field(default=ToolChoice.auto)
|
||||
tool_prompt_format: ToolPromptFormat | None = Field(default=None)
|
||||
system_message_behavior: SystemMessageBehavior | None = Field(default=SystemMessageBehavior.append)
|
||||
|
||||
def model_post_init(self, __context: Any) -> None:
|
||||
if isinstance(self.tool_choice, str):
|
||||
try:
|
||||
self.tool_choice = ToolChoice[self.tool_choice]
|
||||
except KeyError:
|
||||
pass
|
||||
|
||||
|
||||
# This is an internally used class
|
||||
@json_schema_type
|
||||
class ChatCompletionRequest(BaseModel):
|
||||
model: str
|
||||
messages: list[Message]
|
||||
sampling_params: SamplingParams | None = Field(default_factory=SamplingParams)
|
||||
|
||||
tools: list[ToolDefinition] | None = Field(default_factory=lambda: [])
|
||||
tool_config: ToolConfig | None = Field(default_factory=ToolConfig)
|
||||
|
||||
response_format: ResponseFormat | None = None
|
||||
stream: bool | None = False
|
||||
logprobs: LogProbConfig | None = None
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class ChatCompletionResponseStreamChunk(MetricResponseMixin):
|
||||
"""A chunk of a streamed chat completion response.
|
||||
|
||||
:param event: The event containing the new content
|
||||
"""
|
||||
|
||||
event: ChatCompletionResponseEvent
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class ChatCompletionResponse(MetricResponseMixin):
|
||||
"""Response from a chat completion request.
|
||||
|
||||
:param completion_message: The complete response message
|
||||
:param logprobs: Optional log probabilities for generated tokens
|
||||
"""
|
||||
|
||||
completion_message: CompletionMessage
|
||||
logprobs: list[TokenLogProbs] | None = None
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class EmbeddingsResponse(BaseModel):
|
||||
"""Response containing generated embeddings.
|
||||
|
|
@ -1160,7 +989,7 @@ class OpenAIEmbeddingsRequestWithExtraBody(BaseModel, extra="allow"):
|
|||
|
||||
|
||||
@runtime_checkable
|
||||
@trace_protocol
|
||||
@telemetry_traceable
|
||||
class InferenceProvider(Protocol):
|
||||
"""
|
||||
This protocol defines the interface that should be implemented by all inference providers.
|
||||
|
|
|
|||
|
|
@ -76,7 +76,7 @@ class Inspect(Protocol):
|
|||
|
||||
List all available API routes with their methods and implementing providers.
|
||||
|
||||
:param api_filter: Optional filter to control which routes are returned. Can be an API level ('v1', 'v1alpha', 'v1beta') to show non-deprecated routes at that level, or 'deprecated' to show deprecated routes across all levels. If not specified, returns only non-deprecated v1 routes.
|
||||
:param api_filter: Optional filter to control which routes are returned. Can be an API level ('v1', 'v1alpha', 'v1beta') to show non-deprecated routes at that level, or 'deprecated' to show deprecated routes across all levels. If not specified, returns all non-deprecated routes.
|
||||
:returns: Response containing information about all available routes.
|
||||
"""
|
||||
...
|
||||
|
|
|
|||
|
|
@ -9,9 +9,9 @@ from typing import Any, Literal, Protocol, runtime_checkable
|
|||
|
||||
from pydantic import BaseModel, ConfigDict, Field, field_validator
|
||||
|
||||
from llama_stack.apis.common.tracing import telemetry_traceable
|
||||
from llama_stack.apis.resource import Resource, ResourceType
|
||||
from llama_stack.apis.version import LLAMA_STACK_API_V1
|
||||
from llama_stack.core.telemetry.trace_protocol import trace_protocol
|
||||
from llama_stack.schema_utils import json_schema_type, webmethod
|
||||
|
||||
|
||||
|
|
@ -105,7 +105,7 @@ class OpenAIListModelsResponse(BaseModel):
|
|||
|
||||
|
||||
@runtime_checkable
|
||||
@trace_protocol
|
||||
@telemetry_traceable
|
||||
class Models(Protocol):
|
||||
async def list_models(self) -> ListModelsResponse:
|
||||
"""List all models.
|
||||
|
|
@ -136,7 +136,7 @@ class Models(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/models", method="POST", level=LLAMA_STACK_API_V1)
|
||||
@webmethod(route="/models", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
async def register_model(
|
||||
self,
|
||||
model_id: str,
|
||||
|
|
@ -158,7 +158,7 @@ class Models(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/models/{model_id:path}", method="DELETE", level=LLAMA_STACK_API_V1)
|
||||
@webmethod(route="/models/{model_id:path}", method="DELETE", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
async def unregister_model(
|
||||
self,
|
||||
model_id: str,
|
||||
|
|
|
|||
|
|
@ -10,8 +10,8 @@ from typing import Protocol, runtime_checkable
|
|||
|
||||
from pydantic import BaseModel, Field, field_validator, model_validator
|
||||
|
||||
from llama_stack.apis.common.tracing import telemetry_traceable
|
||||
from llama_stack.apis.version import LLAMA_STACK_API_V1
|
||||
from llama_stack.core.telemetry.trace_protocol import trace_protocol
|
||||
from llama_stack.schema_utils import json_schema_type, webmethod
|
||||
|
||||
|
||||
|
|
@ -92,7 +92,7 @@ class ListPromptsResponse(BaseModel):
|
|||
|
||||
|
||||
@runtime_checkable
|
||||
@trace_protocol
|
||||
@telemetry_traceable
|
||||
class Prompts(Protocol):
|
||||
"""Prompts
|
||||
|
||||
|
|
|
|||
|
|
@ -9,10 +9,10 @@ from typing import Any, Protocol, runtime_checkable
|
|||
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
from llama_stack.apis.common.tracing import telemetry_traceable
|
||||
from llama_stack.apis.inference import OpenAIMessageParam
|
||||
from llama_stack.apis.shields import Shield
|
||||
from llama_stack.apis.version import LLAMA_STACK_API_V1
|
||||
from llama_stack.core.telemetry.trace_protocol import trace_protocol
|
||||
from llama_stack.schema_utils import json_schema_type, webmethod
|
||||
|
||||
|
||||
|
|
@ -94,7 +94,7 @@ class ShieldStore(Protocol):
|
|||
|
||||
|
||||
@runtime_checkable
|
||||
@trace_protocol
|
||||
@telemetry_traceable
|
||||
class Safety(Protocol):
|
||||
"""Safety
|
||||
|
||||
|
|
|
|||
|
|
@ -178,7 +178,7 @@ class ScoringFunctions(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/scoring-functions", method="POST", level=LLAMA_STACK_API_V1)
|
||||
@webmethod(route="/scoring-functions", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
async def register_scoring_function(
|
||||
self,
|
||||
scoring_fn_id: str,
|
||||
|
|
@ -199,7 +199,9 @@ class ScoringFunctions(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/scoring-functions/{scoring_fn_id:path}", method="DELETE", level=LLAMA_STACK_API_V1)
|
||||
@webmethod(
|
||||
route="/scoring-functions/{scoring_fn_id:path}", method="DELETE", level=LLAMA_STACK_API_V1, deprecated=True
|
||||
)
|
||||
async def unregister_scoring_function(self, scoring_fn_id: str) -> None:
|
||||
"""Unregister a scoring function.
|
||||
|
||||
|
|
|
|||
|
|
@ -8,9 +8,9 @@ from typing import Any, Literal, Protocol, runtime_checkable
|
|||
|
||||
from pydantic import BaseModel
|
||||
|
||||
from llama_stack.apis.common.tracing import telemetry_traceable
|
||||
from llama_stack.apis.resource import Resource, ResourceType
|
||||
from llama_stack.apis.version import LLAMA_STACK_API_V1
|
||||
from llama_stack.core.telemetry.trace_protocol import trace_protocol
|
||||
from llama_stack.schema_utils import json_schema_type, webmethod
|
||||
|
||||
|
||||
|
|
@ -48,7 +48,7 @@ class ListShieldsResponse(BaseModel):
|
|||
|
||||
|
||||
@runtime_checkable
|
||||
@trace_protocol
|
||||
@telemetry_traceable
|
||||
class Shields(Protocol):
|
||||
@webmethod(route="/shields", method="GET", level=LLAMA_STACK_API_V1)
|
||||
async def list_shields(self) -> ListShieldsResponse:
|
||||
|
|
@ -67,7 +67,7 @@ class Shields(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/shields", method="POST", level=LLAMA_STACK_API_V1)
|
||||
@webmethod(route="/shields", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
async def register_shield(
|
||||
self,
|
||||
shield_id: str,
|
||||
|
|
@ -85,7 +85,7 @@ class Shields(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/shields/{identifier:path}", method="DELETE", level=LLAMA_STACK_API_V1)
|
||||
@webmethod(route="/shields/{identifier:path}", method="DELETE", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
async def unregister_shield(self, identifier: str) -> None:
|
||||
"""Unregister a shield.
|
||||
|
||||
|
|
|
|||
|
|
@ -5,18 +5,13 @@
|
|||
# the root directory of this source tree.
|
||||
|
||||
from enum import Enum, StrEnum
|
||||
from typing import Annotated, Any, Literal, Protocol
|
||||
from typing import Annotated, Any, Literal
|
||||
|
||||
from pydantic import BaseModel, Field, field_validator
|
||||
from typing_extensions import runtime_checkable
|
||||
|
||||
from llama_stack.apis.common.content_types import URL, InterleavedContent
|
||||
from llama_stack.apis.version import LLAMA_STACK_API_V1
|
||||
from llama_stack.core.telemetry.trace_protocol import trace_protocol
|
||||
from llama_stack.schema_utils import json_schema_type, register_schema, webmethod
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class RRFRanker(BaseModel):
|
||||
"""
|
||||
Reciprocal Rank Fusion (RRF) ranker configuration.
|
||||
|
|
@ -30,7 +25,6 @@ class RRFRanker(BaseModel):
|
|||
impact_factor: float = Field(default=60.0, gt=0.0) # default of 60 for optimal performance
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class WeightedRanker(BaseModel):
|
||||
"""
|
||||
Weighted ranker configuration that combines vector and keyword scores.
|
||||
|
|
@ -55,10 +49,8 @@ Ranker = Annotated[
|
|||
RRFRanker | WeightedRanker,
|
||||
Field(discriminator="type"),
|
||||
]
|
||||
register_schema(Ranker, name="Ranker")
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class RAGDocument(BaseModel):
|
||||
"""
|
||||
A document to be used for document ingestion in the RAG Tool.
|
||||
|
|
@ -75,7 +67,6 @@ class RAGDocument(BaseModel):
|
|||
metadata: dict[str, Any] = Field(default_factory=dict)
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class RAGQueryResult(BaseModel):
|
||||
"""Result of a RAG query containing retrieved content and metadata.
|
||||
|
||||
|
|
@ -87,7 +78,6 @@ class RAGQueryResult(BaseModel):
|
|||
metadata: dict[str, Any] = Field(default_factory=dict)
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class RAGQueryGenerator(Enum):
|
||||
"""Types of query generators for RAG systems.
|
||||
|
||||
|
|
@ -101,7 +91,6 @@ class RAGQueryGenerator(Enum):
|
|||
custom = "custom"
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class RAGSearchMode(StrEnum):
|
||||
"""
|
||||
Search modes for RAG query retrieval:
|
||||
|
|
@ -115,7 +104,6 @@ class RAGSearchMode(StrEnum):
|
|||
HYBRID = "hybrid"
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class DefaultRAGQueryGeneratorConfig(BaseModel):
|
||||
"""Configuration for the default RAG query generator.
|
||||
|
||||
|
|
@ -127,7 +115,6 @@ class DefaultRAGQueryGeneratorConfig(BaseModel):
|
|||
separator: str = " "
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class LLMRAGQueryGeneratorConfig(BaseModel):
|
||||
"""Configuration for the LLM-based RAG query generator.
|
||||
|
||||
|
|
@ -145,10 +132,8 @@ RAGQueryGeneratorConfig = Annotated[
|
|||
DefaultRAGQueryGeneratorConfig | LLMRAGQueryGeneratorConfig,
|
||||
Field(discriminator="type"),
|
||||
]
|
||||
register_schema(RAGQueryGeneratorConfig, name="RAGQueryGeneratorConfig")
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class RAGQueryConfig(BaseModel):
|
||||
"""
|
||||
Configuration for the RAG query generation.
|
||||
|
|
@ -181,38 +166,3 @@ class RAGQueryConfig(BaseModel):
|
|||
if len(v) == 0:
|
||||
raise ValueError("chunk_template must not be empty")
|
||||
return v
|
||||
|
||||
|
||||
@runtime_checkable
|
||||
@trace_protocol
|
||||
class RAGToolRuntime(Protocol):
|
||||
@webmethod(route="/tool-runtime/rag-tool/insert", method="POST", level=LLAMA_STACK_API_V1)
|
||||
async def insert(
|
||||
self,
|
||||
documents: list[RAGDocument],
|
||||
vector_store_id: str,
|
||||
chunk_size_in_tokens: int = 512,
|
||||
) -> None:
|
||||
"""Index documents so they can be used by the RAG system.
|
||||
|
||||
:param documents: List of documents to index in the RAG system
|
||||
:param vector_store_id: ID of the vector database to store the document embeddings
|
||||
:param chunk_size_in_tokens: (Optional) Size in tokens for document chunking during indexing
|
||||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/tool-runtime/rag-tool/query", method="POST", level=LLAMA_STACK_API_V1)
|
||||
async def query(
|
||||
self,
|
||||
content: InterleavedContent,
|
||||
vector_store_ids: list[str],
|
||||
query_config: RAGQueryConfig | None = None,
|
||||
) -> RAGQueryResult:
|
||||
"""Query the RAG system for context; typically invoked by the agent.
|
||||
|
||||
:param content: The query content to search for in the indexed documents
|
||||
:param vector_store_ids: List of vector database IDs to search within
|
||||
:param query_config: (Optional) Configuration parameters for the query operation
|
||||
:returns: RAGQueryResult containing the retrieved content and metadata
|
||||
"""
|
||||
...
|
||||
|
|
|
|||
|
|
@ -11,13 +11,11 @@ from pydantic import BaseModel
|
|||
from typing_extensions import runtime_checkable
|
||||
|
||||
from llama_stack.apis.common.content_types import URL, InterleavedContent
|
||||
from llama_stack.apis.common.tracing import telemetry_traceable
|
||||
from llama_stack.apis.resource import Resource, ResourceType
|
||||
from llama_stack.apis.version import LLAMA_STACK_API_V1
|
||||
from llama_stack.core.telemetry.trace_protocol import trace_protocol
|
||||
from llama_stack.schema_utils import json_schema_type, webmethod
|
||||
|
||||
from .rag_tool import RAGToolRuntime
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class ToolDef(BaseModel):
|
||||
|
|
@ -109,9 +107,9 @@ class ListToolDefsResponse(BaseModel):
|
|||
|
||||
|
||||
@runtime_checkable
|
||||
@trace_protocol
|
||||
@telemetry_traceable
|
||||
class ToolGroups(Protocol):
|
||||
@webmethod(route="/toolgroups", method="POST", level=LLAMA_STACK_API_V1)
|
||||
@webmethod(route="/toolgroups", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
async def register_tool_group(
|
||||
self,
|
||||
toolgroup_id: str,
|
||||
|
|
@ -169,7 +167,7 @@ class ToolGroups(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/toolgroups/{toolgroup_id:path}", method="DELETE", level=LLAMA_STACK_API_V1)
|
||||
@webmethod(route="/toolgroups/{toolgroup_id:path}", method="DELETE", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
async def unregister_toolgroup(
|
||||
self,
|
||||
toolgroup_id: str,
|
||||
|
|
@ -191,12 +189,10 @@ class SpecialToolGroup(Enum):
|
|||
|
||||
|
||||
@runtime_checkable
|
||||
@trace_protocol
|
||||
@telemetry_traceable
|
||||
class ToolRuntime(Protocol):
|
||||
tool_store: ToolStore | None = None
|
||||
|
||||
rag_tool: RAGToolRuntime | None = None
|
||||
|
||||
# TODO: This needs to be renamed once OPEN API generator name conflict issue is fixed.
|
||||
@webmethod(route="/tool-runtime/list-tools", method="GET", level=LLAMA_STACK_API_V1)
|
||||
async def list_runtime_tools(
|
||||
|
|
|
|||
|
|
@ -13,10 +13,10 @@ from typing import Annotated, Any, Literal, Protocol, runtime_checkable
|
|||
from fastapi import Body
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
from llama_stack.apis.common.tracing import telemetry_traceable
|
||||
from llama_stack.apis.inference import InterleavedContent
|
||||
from llama_stack.apis.vector_stores import VectorStore
|
||||
from llama_stack.apis.version import LLAMA_STACK_API_V1
|
||||
from llama_stack.core.telemetry.trace_protocol import trace_protocol
|
||||
from llama_stack.schema_utils import json_schema_type, webmethod
|
||||
from llama_stack.strong_typing.schema import register_schema
|
||||
|
||||
|
|
@ -260,7 +260,7 @@ class VectorStoreSearchResponsePage(BaseModel):
|
|||
"""
|
||||
|
||||
object: str = "vector_store.search_results.page"
|
||||
search_query: str
|
||||
search_query: list[str]
|
||||
data: list[VectorStoreSearchResponse]
|
||||
has_more: bool = False
|
||||
next_page: str | None = None
|
||||
|
|
@ -396,19 +396,19 @@ class VectorStoreListFilesResponse(BaseModel):
|
|||
|
||||
|
||||
@json_schema_type
|
||||
class VectorStoreFileContentsResponse(BaseModel):
|
||||
"""Response from retrieving the contents of a vector store file.
|
||||
class VectorStoreFileContentResponse(BaseModel):
|
||||
"""Represents the parsed content of a vector store file.
|
||||
|
||||
:param file_id: Unique identifier for the file
|
||||
:param filename: Name of the file
|
||||
:param attributes: Key-value attributes associated with the file
|
||||
:param content: List of content items from the file
|
||||
:param object: The object type, which is always `vector_store.file_content.page`
|
||||
:param data: Parsed content of the file
|
||||
:param has_more: Indicates if there are more content pages to fetch
|
||||
:param next_page: The token for the next page, if any
|
||||
"""
|
||||
|
||||
file_id: str
|
||||
filename: str
|
||||
attributes: dict[str, Any]
|
||||
content: list[VectorStoreContent]
|
||||
object: Literal["vector_store.file_content.page"] = "vector_store.file_content.page"
|
||||
data: list[VectorStoreContent]
|
||||
has_more: bool
|
||||
next_page: str | None = None
|
||||
|
||||
|
||||
@json_schema_type
|
||||
|
|
@ -478,7 +478,7 @@ class OpenAICreateVectorStoreRequestWithExtraBody(BaseModel, extra="allow"):
|
|||
name: str | None = None
|
||||
file_ids: list[str] | None = None
|
||||
expires_after: dict[str, Any] | None = None
|
||||
chunking_strategy: dict[str, Any] | None = None
|
||||
chunking_strategy: VectorStoreChunkingStrategy | None = None
|
||||
metadata: dict[str, Any] | None = None
|
||||
|
||||
|
||||
|
|
@ -502,7 +502,7 @@ class VectorStoreTable(Protocol):
|
|||
|
||||
|
||||
@runtime_checkable
|
||||
@trace_protocol
|
||||
@telemetry_traceable
|
||||
class VectorIO(Protocol):
|
||||
vector_store_table: VectorStoreTable | None = None
|
||||
|
||||
|
|
@ -732,12 +732,12 @@ class VectorIO(Protocol):
|
|||
self,
|
||||
vector_store_id: str,
|
||||
file_id: str,
|
||||
) -> VectorStoreFileContentsResponse:
|
||||
) -> VectorStoreFileContentResponse:
|
||||
"""Retrieves the contents of a vector store file.
|
||||
|
||||
:param vector_store_id: The ID of the vector store containing the file to retrieve.
|
||||
:param file_id: The ID of the file to retrieve.
|
||||
:returns: A list of InterleavedContent representing the file contents.
|
||||
:returns: A VectorStoreFileContentResponse representing the file contents.
|
||||
"""
|
||||
...
|
||||
|
||||
|
|
|
|||
|
|
@ -46,6 +46,10 @@ class StackListDeps(Subcommand):
|
|||
def _run_stack_list_deps_command(self, args: argparse.Namespace) -> None:
|
||||
# always keep implementation completely silo-ed away from CLI so CLI
|
||||
# can be fast to load and reduces dependencies
|
||||
if not args.config and not args.providers:
|
||||
self.parser.print_help()
|
||||
self.parser.exit()
|
||||
|
||||
from ._list_deps import run_stack_list_deps_command
|
||||
|
||||
return run_stack_list_deps_command(args)
|
||||
|
|
|
|||
|
|
@ -9,46 +9,67 @@ from pathlib import Path
|
|||
|
||||
from llama_stack.cli.subcommand import Subcommand
|
||||
from llama_stack.cli.table import print_table
|
||||
from llama_stack.core.utils.config_dirs import DISTRIBS_BASE_DIR
|
||||
|
||||
|
||||
class StackListBuilds(Subcommand):
|
||||
"""List built stacks in .llama/distributions directory"""
|
||||
"""List available distributions (both built-in and custom)"""
|
||||
|
||||
def __init__(self, subparsers: argparse._SubParsersAction):
|
||||
super().__init__()
|
||||
self.parser = subparsers.add_parser(
|
||||
"list",
|
||||
prog="llama stack list",
|
||||
description="list the build stacks",
|
||||
description="list available distributions",
|
||||
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
|
||||
)
|
||||
self._add_arguments()
|
||||
self.parser.set_defaults(func=self._list_stack_command)
|
||||
|
||||
def _get_distribution_dirs(self) -> dict[str, Path]:
|
||||
"""Return a dictionary of distribution names and their paths"""
|
||||
distributions = {}
|
||||
dist_dir = Path.home() / ".llama" / "distributions"
|
||||
def _get_distribution_dirs(self) -> dict[str, tuple[Path, str]]:
|
||||
"""Return a dictionary of distribution names and their paths with source type
|
||||
|
||||
Returns:
|
||||
dict mapping distro name to (path, source_type) where source_type is 'built-in' or 'custom'
|
||||
"""
|
||||
distributions = {}
|
||||
|
||||
# Get built-in distributions from source code
|
||||
distro_dir = Path(__file__).parent.parent.parent / "distributions"
|
||||
if distro_dir.exists():
|
||||
for stack_dir in distro_dir.iterdir():
|
||||
if stack_dir.is_dir() and not stack_dir.name.startswith(".") and not stack_dir.name.startswith("__"):
|
||||
distributions[stack_dir.name] = (stack_dir, "built-in")
|
||||
|
||||
# Get custom/run distributions from ~/.llama/distributions
|
||||
# These override built-in ones if they have the same name
|
||||
if DISTRIBS_BASE_DIR.exists():
|
||||
for stack_dir in DISTRIBS_BASE_DIR.iterdir():
|
||||
if stack_dir.is_dir() and not stack_dir.name.startswith("."):
|
||||
# Clean up the name (remove llamastack- prefix if present)
|
||||
name = stack_dir.name.replace("llamastack-", "")
|
||||
distributions[name] = (stack_dir, "custom")
|
||||
|
||||
if dist_dir.exists():
|
||||
for stack_dir in dist_dir.iterdir():
|
||||
if stack_dir.is_dir():
|
||||
distributions[stack_dir.name] = stack_dir
|
||||
return distributions
|
||||
|
||||
def _list_stack_command(self, args: argparse.Namespace) -> None:
|
||||
distributions = self._get_distribution_dirs()
|
||||
|
||||
if not distributions:
|
||||
print("No stacks found in ~/.llama/distributions")
|
||||
print("No distributions found")
|
||||
return
|
||||
|
||||
headers = ["Stack Name", "Path"]
|
||||
headers.extend(["Build Config", "Run Config"])
|
||||
headers = ["Stack Name", "Source", "Path", "Build Config", "Run Config"]
|
||||
rows = []
|
||||
for name, path in distributions.items():
|
||||
row = [name, str(path)]
|
||||
for name, (path, source_type) in sorted(distributions.items()):
|
||||
row = [name, source_type, str(path)]
|
||||
# Check for build and run config files
|
||||
# For built-in distributions, configs are named build.yaml and run.yaml
|
||||
# For custom distributions, configs are named {name}-build.yaml and {name}-run.yaml
|
||||
if source_type == "built-in":
|
||||
build_config = "Yes" if (path / "build.yaml").exists() else "No"
|
||||
run_config = "Yes" if (path / "run.yaml").exists() else "No"
|
||||
else:
|
||||
build_config = "Yes" if (path / f"{name}-build.yaml").exists() else "No"
|
||||
run_config = "Yes" if (path / f"{name}-run.yaml").exists() else "No"
|
||||
row.extend([build_config, run_config])
|
||||
|
|
|
|||
|
|
@ -253,7 +253,7 @@ class StackRun(Subcommand):
|
|||
)
|
||||
return
|
||||
|
||||
ui_dir = REPO_ROOT / "llama_stack" / "ui"
|
||||
ui_dir = REPO_ROOT / "llama_stack_ui"
|
||||
logs_dir = Path("~/.llama/ui/logs").expanduser()
|
||||
try:
|
||||
# Create logs directory if it doesn't exist
|
||||
|
|
|
|||
|
|
@ -15,7 +15,6 @@ from llama_stack.apis.inspect import (
|
|||
RouteInfo,
|
||||
VersionInfo,
|
||||
)
|
||||
from llama_stack.apis.version import LLAMA_STACK_API_V1
|
||||
from llama_stack.core.datatypes import StackRunConfig
|
||||
from llama_stack.core.external import load_external_apis
|
||||
from llama_stack.core.server.routes import get_all_api_routes
|
||||
|
|
@ -46,8 +45,8 @@ class DistributionInspectImpl(Inspect):
|
|||
# Helper function to determine if a route should be included based on api_filter
|
||||
def should_include_route(webmethod) -> bool:
|
||||
if api_filter is None:
|
||||
# Default: only non-deprecated v1 APIs
|
||||
return not webmethod.deprecated and webmethod.level == LLAMA_STACK_API_V1
|
||||
# Default: only non-deprecated APIs
|
||||
return not webmethod.deprecated
|
||||
elif api_filter == "deprecated":
|
||||
# Special filter: show deprecated routes regardless of their actual level
|
||||
return bool(webmethod.deprecated)
|
||||
|
|
|
|||
|
|
@ -18,14 +18,21 @@ from typing import Any, TypeVar, Union, get_args, get_origin
|
|||
import httpx
|
||||
import yaml
|
||||
from fastapi import Response as FastAPIResponse
|
||||
from llama_stack_client import (
|
||||
|
||||
try:
|
||||
from llama_stack_client import (
|
||||
NOT_GIVEN,
|
||||
APIResponse,
|
||||
AsyncAPIResponse,
|
||||
AsyncLlamaStackClient,
|
||||
AsyncStream,
|
||||
LlamaStackClient,
|
||||
)
|
||||
)
|
||||
except ImportError as e:
|
||||
raise ImportError(
|
||||
"llama-stack-client is not installed. Please install it with `uv pip install llama-stack[client]`."
|
||||
) from e
|
||||
|
||||
from pydantic import BaseModel, TypeAdapter
|
||||
from rich.console import Console
|
||||
from termcolor import cprint
|
||||
|
|
|
|||
|
|
@ -397,6 +397,18 @@ async def instantiate_provider(
|
|||
impl.__provider_spec__ = provider_spec
|
||||
impl.__provider_config__ = config
|
||||
|
||||
# Apply tracing if telemetry is enabled and any base class has __marked_for_tracing__ marker
|
||||
if run_config.telemetry.enabled:
|
||||
traced_classes = [
|
||||
base for base in reversed(impl.__class__.__mro__) if getattr(base, "__marked_for_tracing__", False)
|
||||
]
|
||||
|
||||
if traced_classes:
|
||||
from llama_stack.core.telemetry.trace_protocol import trace_protocol
|
||||
|
||||
for cls in traced_classes:
|
||||
trace_protocol(cls)
|
||||
|
||||
protocols = api_protocol_map_for_compliance_check(run_config)
|
||||
additional_protocols = additional_protocols_map()
|
||||
# TODO: check compliance for special tool groups
|
||||
|
|
|
|||
|
|
@ -45,6 +45,7 @@ async def get_routing_table_impl(
|
|||
raise ValueError(f"API {api.value} not found in router map")
|
||||
|
||||
impl = api_to_tables[api.value](impls_by_provider_id, dist_registry, policy)
|
||||
|
||||
await impl.initialize()
|
||||
return impl
|
||||
|
||||
|
|
@ -92,5 +93,6 @@ async def get_auto_router_impl(
|
|||
api_to_dep_impl["safety_config"] = run_config.safety
|
||||
|
||||
impl = api_to_routers[api.value](routing_table, **api_to_dep_impl)
|
||||
|
||||
await impl.initialize()
|
||||
return impl
|
||||
|
|
|
|||
|
|
@ -190,7 +190,7 @@ class InferenceRouter(Inference):
|
|||
|
||||
response = await provider.openai_completion(params)
|
||||
response.model = request_model_id
|
||||
if self.telemetry_enabled:
|
||||
if self.telemetry_enabled and response.usage is not None:
|
||||
metrics = self._construct_metrics(
|
||||
prompt_tokens=response.usage.prompt_tokens,
|
||||
completion_tokens=response.usage.completion_tokens,
|
||||
|
|
@ -253,7 +253,7 @@ class InferenceRouter(Inference):
|
|||
if self.store:
|
||||
asyncio.create_task(self.store.store_chat_completion(response, params.messages))
|
||||
|
||||
if self.telemetry_enabled:
|
||||
if self.telemetry_enabled and response.usage is not None:
|
||||
metrics = self._construct_metrics(
|
||||
prompt_tokens=response.usage.prompt_tokens,
|
||||
completion_tokens=response.usage.completion_tokens,
|
||||
|
|
|
|||
|
|
@ -6,7 +6,7 @@
|
|||
|
||||
from typing import Any
|
||||
|
||||
from llama_stack.apis.inference import Message
|
||||
from llama_stack.apis.inference import OpenAIMessageParam
|
||||
from llama_stack.apis.safety import RunShieldResponse, Safety
|
||||
from llama_stack.apis.safety.safety import ModerationObject
|
||||
from llama_stack.apis.shields import Shield
|
||||
|
|
@ -52,7 +52,7 @@ class SafetyRouter(Safety):
|
|||
async def run_shield(
|
||||
self,
|
||||
shield_id: str,
|
||||
messages: list[Message],
|
||||
messages: list[OpenAIMessageParam],
|
||||
params: dict[str, Any] = None,
|
||||
) -> RunShieldResponse:
|
||||
logger.debug(f"SafetyRouter.run_shield: {shield_id}")
|
||||
|
|
|
|||
|
|
@ -8,14 +8,9 @@ from typing import Any
|
|||
|
||||
from llama_stack.apis.common.content_types import (
|
||||
URL,
|
||||
InterleavedContent,
|
||||
)
|
||||
from llama_stack.apis.tools import (
|
||||
ListToolDefsResponse,
|
||||
RAGDocument,
|
||||
RAGQueryConfig,
|
||||
RAGQueryResult,
|
||||
RAGToolRuntime,
|
||||
ToolRuntime,
|
||||
)
|
||||
from llama_stack.log import get_logger
|
||||
|
|
@ -26,36 +21,6 @@ logger = get_logger(name=__name__, category="core::routers")
|
|||
|
||||
|
||||
class ToolRuntimeRouter(ToolRuntime):
|
||||
class RagToolImpl(RAGToolRuntime):
|
||||
def __init__(
|
||||
self,
|
||||
routing_table: ToolGroupsRoutingTable,
|
||||
) -> None:
|
||||
logger.debug("Initializing ToolRuntimeRouter.RagToolImpl")
|
||||
self.routing_table = routing_table
|
||||
|
||||
async def query(
|
||||
self,
|
||||
content: InterleavedContent,
|
||||
vector_store_ids: list[str],
|
||||
query_config: RAGQueryConfig | None = None,
|
||||
) -> RAGQueryResult:
|
||||
logger.debug(f"ToolRuntimeRouter.RagToolImpl.query: {vector_store_ids}")
|
||||
provider = await self.routing_table.get_provider_impl("knowledge_search")
|
||||
return await provider.query(content, vector_store_ids, query_config)
|
||||
|
||||
async def insert(
|
||||
self,
|
||||
documents: list[RAGDocument],
|
||||
vector_store_id: str,
|
||||
chunk_size_in_tokens: int = 512,
|
||||
) -> None:
|
||||
logger.debug(
|
||||
f"ToolRuntimeRouter.RagToolImpl.insert: {vector_store_id}, {len(documents)} documents, chunk_size={chunk_size_in_tokens}"
|
||||
)
|
||||
provider = await self.routing_table.get_provider_impl("insert_into_memory")
|
||||
return await provider.insert(documents, vector_store_id, chunk_size_in_tokens)
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
routing_table: ToolGroupsRoutingTable,
|
||||
|
|
@ -63,11 +28,6 @@ class ToolRuntimeRouter(ToolRuntime):
|
|||
logger.debug("Initializing ToolRuntimeRouter")
|
||||
self.routing_table = routing_table
|
||||
|
||||
# HACK ALERT this should be in sync with "get_all_api_endpoints()"
|
||||
self.rag_tool = self.RagToolImpl(routing_table)
|
||||
for method in ("query", "insert"):
|
||||
setattr(self, f"rag_tool.{method}", getattr(self.rag_tool, method))
|
||||
|
||||
async def initialize(self) -> None:
|
||||
logger.debug("ToolRuntimeRouter.initialize")
|
||||
pass
|
||||
|
|
|
|||
|
|
@ -20,9 +20,11 @@ from llama_stack.apis.vector_io import (
|
|||
SearchRankingOptions,
|
||||
VectorIO,
|
||||
VectorStoreChunkingStrategy,
|
||||
VectorStoreChunkingStrategyStatic,
|
||||
VectorStoreChunkingStrategyStaticConfig,
|
||||
VectorStoreDeleteResponse,
|
||||
VectorStoreFileBatchObject,
|
||||
VectorStoreFileContentsResponse,
|
||||
VectorStoreFileContentResponse,
|
||||
VectorStoreFileDeleteResponse,
|
||||
VectorStoreFileObject,
|
||||
VectorStoreFilesListInBatchResponse,
|
||||
|
|
@ -167,6 +169,13 @@ class VectorIORouter(VectorIO):
|
|||
if embedding_dimension is not None:
|
||||
params.model_extra["embedding_dimension"] = embedding_dimension
|
||||
|
||||
# Set chunking strategy explicitly if not provided
|
||||
if params.chunking_strategy is None or params.chunking_strategy.type == "auto":
|
||||
# actualize the chunking strategy to static
|
||||
params.chunking_strategy = VectorStoreChunkingStrategyStatic(
|
||||
static=VectorStoreChunkingStrategyStaticConfig()
|
||||
)
|
||||
|
||||
return await provider.openai_create_vector_store(params)
|
||||
|
||||
async def openai_list_vector_stores(
|
||||
|
|
@ -283,6 +292,8 @@ class VectorIORouter(VectorIO):
|
|||
chunking_strategy: VectorStoreChunkingStrategy | None = None,
|
||||
) -> VectorStoreFileObject:
|
||||
logger.debug(f"VectorIORouter.openai_attach_file_to_vector_store: {vector_store_id}, {file_id}")
|
||||
if chunking_strategy is None or chunking_strategy.type == "auto":
|
||||
chunking_strategy = VectorStoreChunkingStrategyStatic(static=VectorStoreChunkingStrategyStaticConfig())
|
||||
provider = await self.routing_table.get_provider_impl(vector_store_id)
|
||||
return await provider.openai_attach_file_to_vector_store(
|
||||
vector_store_id=vector_store_id,
|
||||
|
|
@ -327,7 +338,7 @@ class VectorIORouter(VectorIO):
|
|||
self,
|
||||
vector_store_id: str,
|
||||
file_id: str,
|
||||
) -> VectorStoreFileContentsResponse:
|
||||
) -> VectorStoreFileContentResponse:
|
||||
logger.debug(f"VectorIORouter.openai_retrieve_vector_store_file_contents: {vector_store_id}, {file_id}")
|
||||
provider = await self.routing_table.get_provider_impl(vector_store_id)
|
||||
return await provider.openai_retrieve_vector_store_file_contents(
|
||||
|
|
|
|||
|
|
@ -15,7 +15,7 @@ from llama_stack.apis.vector_io.vector_io import (
|
|||
SearchRankingOptions,
|
||||
VectorStoreChunkingStrategy,
|
||||
VectorStoreDeleteResponse,
|
||||
VectorStoreFileContentsResponse,
|
||||
VectorStoreFileContentResponse,
|
||||
VectorStoreFileDeleteResponse,
|
||||
VectorStoreFileObject,
|
||||
VectorStoreFileStatus,
|
||||
|
|
@ -195,7 +195,7 @@ class VectorStoresRoutingTable(CommonRoutingTableImpl):
|
|||
self,
|
||||
vector_store_id: str,
|
||||
file_id: str,
|
||||
) -> VectorStoreFileContentsResponse:
|
||||
) -> VectorStoreFileContentResponse:
|
||||
await self.assert_action_allowed("read", "vector_store", vector_store_id)
|
||||
provider = await self.get_provider_impl(vector_store_id)
|
||||
return await provider.openai_retrieve_vector_store_file_contents(
|
||||
|
|
|
|||
|
|
@ -13,7 +13,6 @@ from aiohttp import hdrs
|
|||
from starlette.routing import Route
|
||||
|
||||
from llama_stack.apis.datatypes import Api, ExternalApiSpec
|
||||
from llama_stack.apis.tools import RAGToolRuntime, SpecialToolGroup
|
||||
from llama_stack.core.resolver import api_protocol_map
|
||||
from llama_stack.schema_utils import WebMethod
|
||||
|
||||
|
|
@ -25,33 +24,16 @@ RouteImpls = dict[str, PathImpl]
|
|||
RouteMatch = tuple[EndpointFunc, PathParams, str, WebMethod]
|
||||
|
||||
|
||||
def toolgroup_protocol_map():
|
||||
return {
|
||||
SpecialToolGroup.rag_tool: RAGToolRuntime,
|
||||
}
|
||||
|
||||
|
||||
def get_all_api_routes(
|
||||
external_apis: dict[Api, ExternalApiSpec] | None = None,
|
||||
) -> dict[Api, list[tuple[Route, WebMethod]]]:
|
||||
apis = {}
|
||||
|
||||
protocols = api_protocol_map(external_apis)
|
||||
toolgroup_protocols = toolgroup_protocol_map()
|
||||
for api, protocol in protocols.items():
|
||||
routes = []
|
||||
protocol_methods = inspect.getmembers(protocol, predicate=inspect.isfunction)
|
||||
|
||||
# HACK ALERT
|
||||
if api == Api.tool_runtime:
|
||||
for tool_group in SpecialToolGroup:
|
||||
sub_protocol = toolgroup_protocols[tool_group]
|
||||
sub_protocol_methods = inspect.getmembers(sub_protocol, predicate=inspect.isfunction)
|
||||
for name, method in sub_protocol_methods:
|
||||
if not hasattr(method, "__webmethod__"):
|
||||
continue
|
||||
protocol_methods.append((f"{tool_group.value}.{name}", method))
|
||||
|
||||
for name, method in protocol_methods:
|
||||
# Get all webmethods for this method (supports multiple decorators)
|
||||
webmethods = getattr(method, "__webmethods__", [])
|
||||
|
|
|
|||
|
|
@ -31,7 +31,7 @@ from llama_stack.apis.safety import Safety
|
|||
from llama_stack.apis.scoring import Scoring
|
||||
from llama_stack.apis.scoring_functions import ScoringFunctions
|
||||
from llama_stack.apis.shields import Shields
|
||||
from llama_stack.apis.tools import RAGToolRuntime, ToolGroups, ToolRuntime
|
||||
from llama_stack.apis.tools import ToolGroups, ToolRuntime
|
||||
from llama_stack.apis.vector_io import VectorIO
|
||||
from llama_stack.core.conversations.conversations import ConversationServiceConfig, ConversationServiceImpl
|
||||
from llama_stack.core.datatypes import Provider, SafetyConfig, StackRunConfig, VectorStoresConfig
|
||||
|
|
@ -78,7 +78,6 @@ class LlamaStack(
|
|||
Inspect,
|
||||
ToolGroups,
|
||||
ToolRuntime,
|
||||
RAGToolRuntime,
|
||||
Files,
|
||||
Prompts,
|
||||
Conversations,
|
||||
|
|
|
|||
|
|
@ -163,47 +163,6 @@ class MetricEvent(EventCommon):
|
|||
unit: str
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class MetricInResponse(BaseModel):
|
||||
"""A metric value included in API responses.
|
||||
:param metric: The name of the metric
|
||||
:param value: The numeric value of the metric
|
||||
:param unit: (Optional) The unit of measurement for the metric value
|
||||
"""
|
||||
|
||||
metric: str
|
||||
value: int | float
|
||||
unit: str | None = None
|
||||
|
||||
|
||||
# This is a short term solution to allow inference API to return metrics
|
||||
# The ideal way to do this is to have a way for all response types to include metrics
|
||||
# and all metric events logged to the telemetry API to be included with the response
|
||||
# To do this, we will need to augment all response types with a metrics field.
|
||||
# We have hit a blocker from stainless SDK that prevents us from doing this.
|
||||
# The blocker is that if we were to augment the response types that have a data field
|
||||
# in them like so
|
||||
# class ListModelsResponse(BaseModel):
|
||||
# metrics: Optional[List[MetricEvent]] = None
|
||||
# data: List[Models]
|
||||
# ...
|
||||
# The client SDK will need to access the data by using a .data field, which is not
|
||||
# ergonomic. Stainless SDK does support unwrapping the response type, but it
|
||||
# requires that the response type to only have a single field.
|
||||
|
||||
# We will need a way in the client SDK to signal that the metrics are needed
|
||||
# and if they are needed, the client SDK has to return the full response type
|
||||
# without unwrapping it.
|
||||
|
||||
|
||||
class MetricResponseMixin(BaseModel):
|
||||
"""Mixin class for API responses that can include metrics.
|
||||
:param metrics: (Optional) List of metrics associated with the API response
|
||||
"""
|
||||
|
||||
metrics: list[MetricInResponse] | None = None
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class StructuredLogType(Enum):
|
||||
"""The type of structured log event payload.
|
||||
|
|
@ -427,6 +386,7 @@ _GLOBAL_STORAGE: dict[str, dict[str | int, Any]] = {
|
|||
"counters": {},
|
||||
"gauges": {},
|
||||
"up_down_counters": {},
|
||||
"histograms": {},
|
||||
}
|
||||
_global_lock = threading.Lock()
|
||||
_TRACER_PROVIDER = None
|
||||
|
|
@ -540,6 +500,16 @@ class Telemetry:
|
|||
)
|
||||
return cast(metrics.ObservableGauge, _GLOBAL_STORAGE["gauges"][name])
|
||||
|
||||
def _get_or_create_histogram(self, name: str, unit: str) -> metrics.Histogram:
|
||||
assert self.meter is not None
|
||||
if name not in _GLOBAL_STORAGE["histograms"]:
|
||||
_GLOBAL_STORAGE["histograms"][name] = self.meter.create_histogram(
|
||||
name=name,
|
||||
unit=unit,
|
||||
description=f"Histogram for {name}",
|
||||
)
|
||||
return cast(metrics.Histogram, _GLOBAL_STORAGE["histograms"][name])
|
||||
|
||||
def _log_metric(self, event: MetricEvent) -> None:
|
||||
# Add metric as an event to the current span
|
||||
try:
|
||||
|
|
@ -571,7 +541,16 @@ class Telemetry:
|
|||
# Log to OpenTelemetry meter if available
|
||||
if self.meter is None:
|
||||
return
|
||||
if isinstance(event.value, int):
|
||||
|
||||
# Use histograms for token-related metrics (per-request measurements)
|
||||
# Use counters for other cumulative metrics
|
||||
token_metrics = {"prompt_tokens", "completion_tokens", "total_tokens"}
|
||||
|
||||
if event.metric in token_metrics:
|
||||
# Token metrics are per-request measurements, use histogram
|
||||
histogram = self._get_or_create_histogram(event.metric, event.unit)
|
||||
histogram.record(event.value, attributes=_clean_attributes(event.attributes))
|
||||
elif isinstance(event.value, int):
|
||||
counter = self._get_or_create_counter(event.metric, event.unit)
|
||||
counter.add(event.value, attributes=_clean_attributes(event.attributes))
|
||||
elif isinstance(event.value, float):
|
||||
|
|
|
|||
|
|
@ -129,6 +129,15 @@ def trace_protocol[T: type[Any]](cls: T) -> T:
|
|||
else:
|
||||
return sync_wrapper
|
||||
|
||||
# Wrap methods on the class itself (for classes applied at runtime)
|
||||
# Skip if already wrapped (indicated by __wrapped__ attribute)
|
||||
for name, method in vars(cls).items():
|
||||
if inspect.isfunction(method) and not name.startswith("_"):
|
||||
if not hasattr(method, "__wrapped__"):
|
||||
wrapped = trace_method(method)
|
||||
setattr(cls, name, wrapped) # noqa: B010
|
||||
|
||||
# Also set up __init_subclass__ for future subclasses
|
||||
original_init_subclass = cast(Callable[..., Any] | None, getattr(cls, "__init_subclass__", None))
|
||||
|
||||
def __init_subclass__(cls_child: type[Any], **kwargs: Any) -> None: # noqa: N807
|
||||
|
|
|
|||
|
|
@ -1,11 +0,0 @@
|
|||
# More info on playground configuration can be found here:
|
||||
# https://llama-stack.readthedocs.io/en/latest/playground
|
||||
|
||||
FROM python:3.12-slim
|
||||
WORKDIR /app
|
||||
COPY . /app/
|
||||
RUN /usr/local/bin/python -m pip install --upgrade pip && \
|
||||
/usr/local/bin/pip3 install -r requirements.txt
|
||||
EXPOSE 8501
|
||||
|
||||
ENTRYPOINT ["streamlit", "run", "app.py", "--server.port=8501", "--server.address=0.0.0.0"]
|
||||
|
|
@ -1,50 +0,0 @@
|
|||
# (Experimental) LLama Stack UI
|
||||
|
||||
## Docker Setup
|
||||
|
||||
:warning: This is a work in progress.
|
||||
|
||||
## Developer Setup
|
||||
|
||||
1. Start up Llama Stack API server. More details [here](https://llamastack.github.io/latest/getting_started/index.htmll).
|
||||
|
||||
```
|
||||
llama stack list-deps together | xargs -L1 uv pip install
|
||||
|
||||
llama stack run together
|
||||
```
|
||||
|
||||
2. (Optional) Register datasets and eval tasks as resources. If you want to run pre-configured evaluation flows (e.g. Evaluations (Generation + Scoring) Page).
|
||||
|
||||
```bash
|
||||
llama-stack-client datasets register \
|
||||
--dataset-id "mmlu" \
|
||||
--provider-id "huggingface" \
|
||||
--url "https://huggingface.co/datasets/llamastack/evals" \
|
||||
--metadata '{"path": "llamastack/evals", "name": "evals__mmlu__details", "split": "train"}' \
|
||||
--schema '{"input_query": {"type": "string"}, "expected_answer": {"type": "string", "chat_completion_input": {"type": "string"}}}'
|
||||
```
|
||||
|
||||
```bash
|
||||
llama-stack-client benchmarks register \
|
||||
--eval-task-id meta-reference-mmlu \
|
||||
--provider-id meta-reference \
|
||||
--dataset-id mmlu \
|
||||
--scoring-functions basic::regex_parser_multiple_choice_answer
|
||||
```
|
||||
|
||||
3. Start Streamlit UI
|
||||
|
||||
```bash
|
||||
uv run --with ".[ui]" streamlit run llama_stack.core/ui/app.py
|
||||
```
|
||||
|
||||
## Environment Variables
|
||||
|
||||
| Environment Variable | Description | Default Value |
|
||||
|----------------------------|------------------------------------|---------------------------|
|
||||
| LLAMA_STACK_ENDPOINT | The endpoint for the Llama Stack | http://localhost:8321 |
|
||||
| FIREWORKS_API_KEY | API key for Fireworks provider | (empty string) |
|
||||
| TOGETHER_API_KEY | API key for Together provider | (empty string) |
|
||||
| SAMBANOVA_API_KEY | API key for SambaNova provider | (empty string) |
|
||||
| OPENAI_API_KEY | API key for OpenAI provider | (empty string) |
|
||||
|
|
@ -1,55 +0,0 @@
|
|||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
import streamlit as st
|
||||
|
||||
|
||||
def main():
|
||||
# Evaluation pages
|
||||
application_evaluation_page = st.Page(
|
||||
"page/evaluations/app_eval.py",
|
||||
title="Evaluations (Scoring)",
|
||||
icon="📊",
|
||||
default=False,
|
||||
)
|
||||
native_evaluation_page = st.Page(
|
||||
"page/evaluations/native_eval.py",
|
||||
title="Evaluations (Generation + Scoring)",
|
||||
icon="📊",
|
||||
default=False,
|
||||
)
|
||||
|
||||
# Playground pages
|
||||
chat_page = st.Page("page/playground/chat.py", title="Chat", icon="💬", default=True)
|
||||
rag_page = st.Page("page/playground/rag.py", title="RAG", icon="💬", default=False)
|
||||
tool_page = st.Page("page/playground/tools.py", title="Tools", icon="🛠", default=False)
|
||||
|
||||
# Distribution pages
|
||||
resources_page = st.Page("page/distribution/resources.py", title="Resources", icon="🔍", default=False)
|
||||
provider_page = st.Page(
|
||||
"page/distribution/providers.py",
|
||||
title="API Providers",
|
||||
icon="🔍",
|
||||
default=False,
|
||||
)
|
||||
|
||||
pg = st.navigation(
|
||||
{
|
||||
"Playground": [
|
||||
chat_page,
|
||||
rag_page,
|
||||
tool_page,
|
||||
application_evaluation_page,
|
||||
native_evaluation_page,
|
||||
],
|
||||
"Inspect": [provider_page, resources_page],
|
||||
},
|
||||
expanded=False,
|
||||
)
|
||||
pg.run()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
|
|
@ -1,32 +0,0 @@
|
|||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
import os
|
||||
|
||||
from llama_stack_client import LlamaStackClient
|
||||
|
||||
|
||||
class LlamaStackApi:
|
||||
def __init__(self):
|
||||
self.client = LlamaStackClient(
|
||||
base_url=os.environ.get("LLAMA_STACK_ENDPOINT", "http://localhost:8321"),
|
||||
provider_data={
|
||||
"fireworks_api_key": os.environ.get("FIREWORKS_API_KEY", ""),
|
||||
"together_api_key": os.environ.get("TOGETHER_API_KEY", ""),
|
||||
"sambanova_api_key": os.environ.get("SAMBANOVA_API_KEY", ""),
|
||||
"openai_api_key": os.environ.get("OPENAI_API_KEY", ""),
|
||||
"tavily_search_api_key": os.environ.get("TAVILY_SEARCH_API_KEY", ""),
|
||||
},
|
||||
)
|
||||
|
||||
def run_scoring(self, row, scoring_function_ids: list[str], scoring_params: dict | None):
|
||||
"""Run scoring on a single row"""
|
||||
if not scoring_params:
|
||||
scoring_params = dict.fromkeys(scoring_function_ids)
|
||||
return self.client.scoring.score(input_rows=[row], scoring_functions=scoring_params)
|
||||
|
||||
|
||||
llama_stack_api = LlamaStackApi()
|
||||
|
|
@ -1,42 +0,0 @@
|
|||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
import base64
|
||||
import os
|
||||
|
||||
import pandas as pd
|
||||
import streamlit as st
|
||||
|
||||
|
||||
def process_dataset(file):
|
||||
if file is None:
|
||||
return "No file uploaded", None
|
||||
|
||||
try:
|
||||
# Determine file type and read accordingly
|
||||
file_ext = os.path.splitext(file.name)[1].lower()
|
||||
if file_ext == ".csv":
|
||||
df = pd.read_csv(file)
|
||||
elif file_ext in [".xlsx", ".xls"]:
|
||||
df = pd.read_excel(file)
|
||||
else:
|
||||
return "Unsupported file format. Please upload a CSV or Excel file.", None
|
||||
|
||||
return df
|
||||
|
||||
except Exception as e:
|
||||
st.error(f"Error processing file: {str(e)}")
|
||||
return None
|
||||
|
||||
|
||||
def data_url_from_file(file) -> str:
|
||||
file_content = file.getvalue()
|
||||
base64_content = base64.b64encode(file_content).decode("utf-8")
|
||||
mime_type = file.type
|
||||
|
||||
data_url = f"data:{mime_type};base64,{base64_content}"
|
||||
|
||||
return data_url
|
||||
|
|
@ -1,5 +0,0 @@
|
|||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
|
@ -1,18 +0,0 @@
|
|||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
import streamlit as st
|
||||
|
||||
from llama_stack.core.ui.modules.api import llama_stack_api
|
||||
|
||||
|
||||
def datasets():
|
||||
st.header("Datasets")
|
||||
|
||||
datasets_info = {d.identifier: d.to_dict() for d in llama_stack_api.client.datasets.list()}
|
||||
if len(datasets_info) > 0:
|
||||
selected_dataset = st.selectbox("Select a dataset", list(datasets_info.keys()))
|
||||
st.json(datasets_info[selected_dataset], expanded=True)
|
||||
|
|
@ -1,20 +0,0 @@
|
|||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
import streamlit as st
|
||||
|
||||
from llama_stack.core.ui.modules.api import llama_stack_api
|
||||
|
||||
|
||||
def benchmarks():
|
||||
# Benchmarks Section
|
||||
st.header("Benchmarks")
|
||||
|
||||
benchmarks_info = {d.identifier: d.to_dict() for d in llama_stack_api.client.benchmarks.list()}
|
||||
|
||||
if len(benchmarks_info) > 0:
|
||||
selected_benchmark = st.selectbox("Select an eval task", list(benchmarks_info.keys()), key="benchmark_inspect")
|
||||
st.json(benchmarks_info[selected_benchmark], expanded=True)
|
||||
|
|
@ -1,18 +0,0 @@
|
|||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
import streamlit as st
|
||||
|
||||
from llama_stack.core.ui.modules.api import llama_stack_api
|
||||
|
||||
|
||||
def models():
|
||||
# Models Section
|
||||
st.header("Models")
|
||||
models_info = {m.id: m.model_dump() for m in llama_stack_api.client.models.list()}
|
||||
|
||||
selected_model = st.selectbox("Select a model", list(models_info.keys()))
|
||||
st.json(models_info[selected_model])
|
||||
|
|
@ -1,27 +0,0 @@
|
|||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
import streamlit as st
|
||||
|
||||
from llama_stack.core.ui.modules.api import llama_stack_api
|
||||
|
||||
|
||||
def providers():
|
||||
st.header("🔍 API Providers")
|
||||
apis_providers_lst = llama_stack_api.client.providers.list()
|
||||
api_to_providers = {}
|
||||
for api_provider in apis_providers_lst:
|
||||
if api_provider.api in api_to_providers:
|
||||
api_to_providers[api_provider.api].append(api_provider)
|
||||
else:
|
||||
api_to_providers[api_provider.api] = [api_provider]
|
||||
|
||||
for api in api_to_providers.keys():
|
||||
st.markdown(f"###### {api}")
|
||||
st.dataframe([x.to_dict() for x in api_to_providers[api]], width=500)
|
||||
|
||||
|
||||
providers()
|
||||
|
|
@ -1,48 +0,0 @@
|
|||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
from streamlit_option_menu import option_menu
|
||||
|
||||
from llama_stack.core.ui.page.distribution.datasets import datasets
|
||||
from llama_stack.core.ui.page.distribution.eval_tasks import benchmarks
|
||||
from llama_stack.core.ui.page.distribution.models import models
|
||||
from llama_stack.core.ui.page.distribution.scoring_functions import scoring_functions
|
||||
from llama_stack.core.ui.page.distribution.shields import shields
|
||||
|
||||
|
||||
def resources_page():
|
||||
options = [
|
||||
"Models",
|
||||
"Shields",
|
||||
"Scoring Functions",
|
||||
"Datasets",
|
||||
"Benchmarks",
|
||||
]
|
||||
icons = ["magic", "shield", "file-bar-graph", "database", "list-task"]
|
||||
selected_resource = option_menu(
|
||||
None,
|
||||
options,
|
||||
icons=icons,
|
||||
orientation="horizontal",
|
||||
styles={
|
||||
"nav-link": {
|
||||
"font-size": "12px",
|
||||
},
|
||||
},
|
||||
)
|
||||
if selected_resource == "Benchmarks":
|
||||
benchmarks()
|
||||
elif selected_resource == "Datasets":
|
||||
datasets()
|
||||
elif selected_resource == "Models":
|
||||
models()
|
||||
elif selected_resource == "Scoring Functions":
|
||||
scoring_functions()
|
||||
elif selected_resource == "Shields":
|
||||
shields()
|
||||
|
||||
|
||||
resources_page()
|
||||
|
|
@ -1,18 +0,0 @@
|
|||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
import streamlit as st
|
||||
|
||||
from llama_stack.core.ui.modules.api import llama_stack_api
|
||||
|
||||
|
||||
def scoring_functions():
|
||||
st.header("Scoring Functions")
|
||||
|
||||
scoring_functions_info = {s.identifier: s.to_dict() for s in llama_stack_api.client.scoring_functions.list()}
|
||||
|
||||
selected_scoring_function = st.selectbox("Select a scoring function", list(scoring_functions_info.keys()))
|
||||
st.json(scoring_functions_info[selected_scoring_function], expanded=True)
|
||||
|
|
@ -1,19 +0,0 @@
|
|||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
import streamlit as st
|
||||
|
||||
from llama_stack.core.ui.modules.api import llama_stack_api
|
||||
|
||||
|
||||
def shields():
|
||||
# Shields Section
|
||||
st.header("Shields")
|
||||
|
||||
shields_info = {s.identifier: s.to_dict() for s in llama_stack_api.client.shields.list()}
|
||||
|
||||
selected_shield = st.selectbox("Select a shield", list(shields_info.keys()))
|
||||
st.json(shields_info[selected_shield])
|
||||
|
|
@ -1,5 +0,0 @@
|
|||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
|
@ -1,143 +0,0 @@
|
|||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
import json
|
||||
|
||||
import pandas as pd
|
||||
import streamlit as st
|
||||
|
||||
from llama_stack.core.ui.modules.api import llama_stack_api
|
||||
from llama_stack.core.ui.modules.utils import process_dataset
|
||||
|
||||
|
||||
def application_evaluation_page():
|
||||
st.set_page_config(page_title="Evaluations (Scoring)", page_icon="🦙")
|
||||
st.title("📊 Evaluations (Scoring)")
|
||||
|
||||
# File uploader
|
||||
uploaded_file = st.file_uploader("Upload Dataset", type=["csv", "xlsx", "xls"])
|
||||
|
||||
if uploaded_file is None:
|
||||
st.error("No file uploaded")
|
||||
return
|
||||
|
||||
# Process uploaded file
|
||||
df = process_dataset(uploaded_file)
|
||||
if df is None:
|
||||
st.error("Error processing file")
|
||||
return
|
||||
|
||||
# Display dataset information
|
||||
st.success("Dataset loaded successfully!")
|
||||
|
||||
# Display dataframe preview
|
||||
st.subheader("Dataset Preview")
|
||||
st.dataframe(df)
|
||||
|
||||
# Select Scoring Functions to Run Evaluation On
|
||||
st.subheader("Select Scoring Functions")
|
||||
scoring_functions = llama_stack_api.client.scoring_functions.list()
|
||||
scoring_functions = {sf.identifier: sf for sf in scoring_functions}
|
||||
scoring_functions_names = list(scoring_functions.keys())
|
||||
selected_scoring_functions = st.multiselect(
|
||||
"Choose one or more scoring functions",
|
||||
options=scoring_functions_names,
|
||||
help="Choose one or more scoring functions.",
|
||||
)
|
||||
|
||||
available_models = llama_stack_api.client.models.list()
|
||||
available_models = [m.identifier for m in available_models]
|
||||
|
||||
scoring_params = {}
|
||||
if selected_scoring_functions:
|
||||
st.write("Selected:")
|
||||
for scoring_fn_id in selected_scoring_functions:
|
||||
scoring_fn = scoring_functions[scoring_fn_id]
|
||||
st.write(f"- **{scoring_fn_id}**: {scoring_fn.description}")
|
||||
new_params = None
|
||||
if scoring_fn.params:
|
||||
new_params = {}
|
||||
for param_name, param_value in scoring_fn.params.to_dict().items():
|
||||
if param_name == "type":
|
||||
new_params[param_name] = param_value
|
||||
continue
|
||||
|
||||
if param_name == "judge_model":
|
||||
value = st.selectbox(
|
||||
f"Select **{param_name}** for {scoring_fn_id}",
|
||||
options=available_models,
|
||||
index=0,
|
||||
key=f"{scoring_fn_id}_{param_name}",
|
||||
)
|
||||
new_params[param_name] = value
|
||||
else:
|
||||
value = st.text_area(
|
||||
f"Enter value for **{param_name}** in {scoring_fn_id} in valid JSON format",
|
||||
value=json.dumps(param_value, indent=2),
|
||||
height=80,
|
||||
)
|
||||
try:
|
||||
new_params[param_name] = json.loads(value)
|
||||
except json.JSONDecodeError:
|
||||
st.error(f"Invalid JSON for **{param_name}** in {scoring_fn_id}")
|
||||
|
||||
st.json(new_params)
|
||||
scoring_params[scoring_fn_id] = new_params
|
||||
|
||||
# Add run evaluation button & slider
|
||||
total_rows = len(df)
|
||||
num_rows = st.slider("Number of rows to evaluate", 1, total_rows, total_rows)
|
||||
|
||||
if st.button("Run Evaluation"):
|
||||
progress_text = "Running evaluation..."
|
||||
progress_bar = st.progress(0, text=progress_text)
|
||||
rows = df.to_dict(orient="records")
|
||||
if num_rows < total_rows:
|
||||
rows = rows[:num_rows]
|
||||
|
||||
# Create separate containers for progress text and results
|
||||
progress_text_container = st.empty()
|
||||
results_container = st.empty()
|
||||
output_res = {}
|
||||
for i, r in enumerate(rows):
|
||||
# Update progress
|
||||
progress = i / len(rows)
|
||||
progress_bar.progress(progress, text=progress_text)
|
||||
|
||||
# Run evaluation for current row
|
||||
score_res = llama_stack_api.run_scoring(
|
||||
r,
|
||||
scoring_function_ids=selected_scoring_functions,
|
||||
scoring_params=scoring_params,
|
||||
)
|
||||
|
||||
for k in r.keys():
|
||||
if k not in output_res:
|
||||
output_res[k] = []
|
||||
output_res[k].append(r[k])
|
||||
|
||||
for fn_id in selected_scoring_functions:
|
||||
if fn_id not in output_res:
|
||||
output_res[fn_id] = []
|
||||
output_res[fn_id].append(score_res.results[fn_id].score_rows[0])
|
||||
|
||||
# Display current row results using separate containers
|
||||
progress_text_container.write(f"Expand to see current processed result ({i + 1} / {len(rows)})")
|
||||
results_container.json(
|
||||
score_res.to_json(),
|
||||
expanded=2,
|
||||
)
|
||||
|
||||
progress_bar.progress(1.0, text="Evaluation complete!")
|
||||
|
||||
# Display results in dataframe
|
||||
if output_res:
|
||||
output_df = pd.DataFrame(output_res)
|
||||
st.subheader("Evaluation Results")
|
||||
st.dataframe(output_df)
|
||||
|
||||
|
||||
application_evaluation_page()
|
||||
Some files were not shown because too many files have changed in this diff Show more
Loading…
Add table
Add a link
Reference in a new issue