mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
feat: support postgresql inference store (#2310)
Some checks failed
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 3s
Integration Tests / test-matrix (http, post_training) (push) Failing after 11s
Integration Tests / test-matrix (library, inference) (push) Failing after 13s
Integration Tests / test-matrix (http, providers) (push) Failing after 15s
Integration Tests / test-matrix (http, tool_runtime) (push) Failing after 16s
Integration Tests / test-matrix (http, datasets) (push) Failing after 18s
Integration Tests / test-matrix (http, scoring) (push) Failing after 16s
Integration Tests / test-matrix (http, agents) (push) Failing after 19s
Integration Tests / test-matrix (library, datasets) (push) Failing after 16s
Integration Tests / test-matrix (http, inspect) (push) Failing after 18s
Integration Tests / test-matrix (library, agents) (push) Failing after 18s
Integration Tests / test-matrix (http, inference) (push) Failing after 20s
Integration Tests / test-matrix (library, inspect) (push) Failing after 9s
Integration Tests / test-matrix (library, post_training) (push) Failing after 10s
Integration Tests / test-matrix (library, tool_runtime) (push) Failing after 8s
Test External Providers / test-external-providers (venv) (push) Failing after 8s
Integration Tests / test-matrix (library, scoring) (push) Failing after 9s
Integration Tests / test-matrix (library, providers) (push) Failing after 11s
Unit Tests / unit-tests (3.11) (push) Failing after 8s
Unit Tests / unit-tests (3.10) (push) Failing after 8s
Unit Tests / unit-tests (3.12) (push) Failing after 8s
Unit Tests / unit-tests (3.13) (push) Failing after 8s
Pre-commit / pre-commit (push) Successful in 57s
Some checks failed
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 3s
Integration Tests / test-matrix (http, post_training) (push) Failing after 11s
Integration Tests / test-matrix (library, inference) (push) Failing after 13s
Integration Tests / test-matrix (http, providers) (push) Failing after 15s
Integration Tests / test-matrix (http, tool_runtime) (push) Failing after 16s
Integration Tests / test-matrix (http, datasets) (push) Failing after 18s
Integration Tests / test-matrix (http, scoring) (push) Failing after 16s
Integration Tests / test-matrix (http, agents) (push) Failing after 19s
Integration Tests / test-matrix (library, datasets) (push) Failing after 16s
Integration Tests / test-matrix (http, inspect) (push) Failing after 18s
Integration Tests / test-matrix (library, agents) (push) Failing after 18s
Integration Tests / test-matrix (http, inference) (push) Failing after 20s
Integration Tests / test-matrix (library, inspect) (push) Failing after 9s
Integration Tests / test-matrix (library, post_training) (push) Failing after 10s
Integration Tests / test-matrix (library, tool_runtime) (push) Failing after 8s
Test External Providers / test-external-providers (venv) (push) Failing after 8s
Integration Tests / test-matrix (library, scoring) (push) Failing after 9s
Integration Tests / test-matrix (library, providers) (push) Failing after 11s
Unit Tests / unit-tests (3.11) (push) Failing after 8s
Unit Tests / unit-tests (3.10) (push) Failing after 8s
Unit Tests / unit-tests (3.12) (push) Failing after 8s
Unit Tests / unit-tests (3.13) (push) Failing after 8s
Pre-commit / pre-commit (push) Successful in 57s
# What does this PR do? * Added support postgresql inference store * Added 'oracle' template that demos how to config postgresql stores (except for telemetry, which is not supported currently) ## Test Plan llama stack build --template oracle --image-type conda --run LLAMA_STACK_CONFIG=http://localhost:8321 pytest -s -v tests/integration/ --text-model accounts/fireworks/models/llama-v3p3-70b-instruct -k 'inference_store'
This commit is contained in:
parent
168c7113df
commit
2603f10f95
32 changed files with 516 additions and 53 deletions
224
llama_stack/templates/postgres-demo/run.yaml
Normal file
224
llama_stack/templates/postgres-demo/run.yaml
Normal file
|
@ -0,0 +1,224 @@
|
|||
version: '2'
|
||||
image_name: postgres-demo
|
||||
apis:
|
||||
- agents
|
||||
- inference
|
||||
- safety
|
||||
- telemetry
|
||||
- tool_runtime
|
||||
- vector_io
|
||||
providers:
|
||||
inference:
|
||||
- provider_id: fireworks
|
||||
provider_type: remote::fireworks
|
||||
config:
|
||||
url: https://api.fireworks.ai/inference/v1
|
||||
api_key: ${env.FIREWORKS_API_KEY:}
|
||||
- provider_id: vllm-inference
|
||||
provider_type: remote::vllm
|
||||
config:
|
||||
url: ${env.VLLM_URL:http://localhost:8000/v1}
|
||||
max_tokens: ${env.VLLM_MAX_TOKENS:4096}
|
||||
api_token: ${env.VLLM_API_TOKEN:fake}
|
||||
tls_verify: ${env.VLLM_TLS_VERIFY:true}
|
||||
vector_io:
|
||||
- provider_id: ${env.ENABLE_CHROMADB+chromadb}
|
||||
provider_type: remote::chromadb
|
||||
config:
|
||||
url: ${env.CHROMADB_URL:}
|
||||
safety:
|
||||
- provider_id: llama-guard
|
||||
provider_type: inline::llama-guard
|
||||
config:
|
||||
excluded_categories: []
|
||||
agents:
|
||||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
persistence_store:
|
||||
type: postgres
|
||||
host: ${env.POSTGRES_HOST:localhost}
|
||||
port: ${env.POSTGRES_PORT:5432}
|
||||
db: ${env.POSTGRES_DB:llamastack}
|
||||
user: ${env.POSTGRES_USER:llamastack}
|
||||
password: ${env.POSTGRES_PASSWORD:llamastack}
|
||||
responses_store:
|
||||
type: postgres
|
||||
host: ${env.POSTGRES_HOST:localhost}
|
||||
port: ${env.POSTGRES_PORT:5432}
|
||||
db: ${env.POSTGRES_DB:llamastack}
|
||||
user: ${env.POSTGRES_USER:llamastack}
|
||||
password: ${env.POSTGRES_PASSWORD:llamastack}
|
||||
telemetry:
|
||||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
service_name: ${env.OTEL_SERVICE_NAME:}
|
||||
sinks: ${env.TELEMETRY_SINKS:console}
|
||||
tool_runtime:
|
||||
- provider_id: brave-search
|
||||
provider_type: remote::brave-search
|
||||
config:
|
||||
api_key: ${env.BRAVE_SEARCH_API_KEY:}
|
||||
max_results: 3
|
||||
- provider_id: tavily-search
|
||||
provider_type: remote::tavily-search
|
||||
config:
|
||||
api_key: ${env.TAVILY_SEARCH_API_KEY:}
|
||||
max_results: 3
|
||||
- provider_id: rag-runtime
|
||||
provider_type: inline::rag-runtime
|
||||
config: {}
|
||||
- provider_id: model-context-protocol
|
||||
provider_type: remote::model-context-protocol
|
||||
config: {}
|
||||
metadata_store:
|
||||
type: postgres
|
||||
host: ${env.POSTGRES_HOST:localhost}
|
||||
port: ${env.POSTGRES_PORT:5432}
|
||||
db: ${env.POSTGRES_DB:llamastack}
|
||||
user: ${env.POSTGRES_USER:llamastack}
|
||||
password: ${env.POSTGRES_PASSWORD:llamastack}
|
||||
table_name: llamastack_kvstore
|
||||
inference_store:
|
||||
type: postgres
|
||||
host: ${env.POSTGRES_HOST:localhost}
|
||||
port: ${env.POSTGRES_PORT:5432}
|
||||
db: ${env.POSTGRES_DB:llamastack}
|
||||
user: ${env.POSTGRES_USER:llamastack}
|
||||
password: ${env.POSTGRES_PASSWORD:llamastack}
|
||||
models:
|
||||
- metadata: {}
|
||||
model_id: accounts/fireworks/models/llama-v3p1-8b-instruct
|
||||
provider_id: fireworks
|
||||
provider_model_id: accounts/fireworks/models/llama-v3p1-8b-instruct
|
||||
model_type: llm
|
||||
- metadata: {}
|
||||
model_id: meta-llama/Llama-3.1-8B-Instruct
|
||||
provider_id: fireworks
|
||||
provider_model_id: accounts/fireworks/models/llama-v3p1-8b-instruct
|
||||
model_type: llm
|
||||
- metadata: {}
|
||||
model_id: accounts/fireworks/models/llama-v3p1-70b-instruct
|
||||
provider_id: fireworks
|
||||
provider_model_id: accounts/fireworks/models/llama-v3p1-70b-instruct
|
||||
model_type: llm
|
||||
- metadata: {}
|
||||
model_id: meta-llama/Llama-3.1-70B-Instruct
|
||||
provider_id: fireworks
|
||||
provider_model_id: accounts/fireworks/models/llama-v3p1-70b-instruct
|
||||
model_type: llm
|
||||
- metadata: {}
|
||||
model_id: accounts/fireworks/models/llama-v3p1-405b-instruct
|
||||
provider_id: fireworks
|
||||
provider_model_id: accounts/fireworks/models/llama-v3p1-405b-instruct
|
||||
model_type: llm
|
||||
- metadata: {}
|
||||
model_id: meta-llama/Llama-3.1-405B-Instruct-FP8
|
||||
provider_id: fireworks
|
||||
provider_model_id: accounts/fireworks/models/llama-v3p1-405b-instruct
|
||||
model_type: llm
|
||||
- metadata: {}
|
||||
model_id: accounts/fireworks/models/llama-v3p2-3b-instruct
|
||||
provider_id: fireworks
|
||||
provider_model_id: accounts/fireworks/models/llama-v3p2-3b-instruct
|
||||
model_type: llm
|
||||
- metadata: {}
|
||||
model_id: meta-llama/Llama-3.2-3B-Instruct
|
||||
provider_id: fireworks
|
||||
provider_model_id: accounts/fireworks/models/llama-v3p2-3b-instruct
|
||||
model_type: llm
|
||||
- metadata: {}
|
||||
model_id: accounts/fireworks/models/llama-v3p2-11b-vision-instruct
|
||||
provider_id: fireworks
|
||||
provider_model_id: accounts/fireworks/models/llama-v3p2-11b-vision-instruct
|
||||
model_type: llm
|
||||
- metadata: {}
|
||||
model_id: meta-llama/Llama-3.2-11B-Vision-Instruct
|
||||
provider_id: fireworks
|
||||
provider_model_id: accounts/fireworks/models/llama-v3p2-11b-vision-instruct
|
||||
model_type: llm
|
||||
- metadata: {}
|
||||
model_id: accounts/fireworks/models/llama-v3p2-90b-vision-instruct
|
||||
provider_id: fireworks
|
||||
provider_model_id: accounts/fireworks/models/llama-v3p2-90b-vision-instruct
|
||||
model_type: llm
|
||||
- metadata: {}
|
||||
model_id: meta-llama/Llama-3.2-90B-Vision-Instruct
|
||||
provider_id: fireworks
|
||||
provider_model_id: accounts/fireworks/models/llama-v3p2-90b-vision-instruct
|
||||
model_type: llm
|
||||
- metadata: {}
|
||||
model_id: accounts/fireworks/models/llama-v3p3-70b-instruct
|
||||
provider_id: fireworks
|
||||
provider_model_id: accounts/fireworks/models/llama-v3p3-70b-instruct
|
||||
model_type: llm
|
||||
- metadata: {}
|
||||
model_id: meta-llama/Llama-3.3-70B-Instruct
|
||||
provider_id: fireworks
|
||||
provider_model_id: accounts/fireworks/models/llama-v3p3-70b-instruct
|
||||
model_type: llm
|
||||
- metadata: {}
|
||||
model_id: accounts/fireworks/models/llama-guard-3-8b
|
||||
provider_id: fireworks
|
||||
provider_model_id: accounts/fireworks/models/llama-guard-3-8b
|
||||
model_type: llm
|
||||
- metadata: {}
|
||||
model_id: meta-llama/Llama-Guard-3-8B
|
||||
provider_id: fireworks
|
||||
provider_model_id: accounts/fireworks/models/llama-guard-3-8b
|
||||
model_type: llm
|
||||
- metadata: {}
|
||||
model_id: accounts/fireworks/models/llama-guard-3-11b-vision
|
||||
provider_id: fireworks
|
||||
provider_model_id: accounts/fireworks/models/llama-guard-3-11b-vision
|
||||
model_type: llm
|
||||
- metadata: {}
|
||||
model_id: meta-llama/Llama-Guard-3-11B-Vision
|
||||
provider_id: fireworks
|
||||
provider_model_id: accounts/fireworks/models/llama-guard-3-11b-vision
|
||||
model_type: llm
|
||||
- metadata: {}
|
||||
model_id: accounts/fireworks/models/llama4-scout-instruct-basic
|
||||
provider_id: fireworks
|
||||
provider_model_id: accounts/fireworks/models/llama4-scout-instruct-basic
|
||||
model_type: llm
|
||||
- metadata: {}
|
||||
model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
|
||||
provider_id: fireworks
|
||||
provider_model_id: accounts/fireworks/models/llama4-scout-instruct-basic
|
||||
model_type: llm
|
||||
- metadata: {}
|
||||
model_id: accounts/fireworks/models/llama4-maverick-instruct-basic
|
||||
provider_id: fireworks
|
||||
provider_model_id: accounts/fireworks/models/llama4-maverick-instruct-basic
|
||||
model_type: llm
|
||||
- metadata: {}
|
||||
model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct
|
||||
provider_id: fireworks
|
||||
provider_model_id: accounts/fireworks/models/llama4-maverick-instruct-basic
|
||||
model_type: llm
|
||||
- metadata:
|
||||
embedding_dimension: 768
|
||||
context_length: 8192
|
||||
model_id: nomic-ai/nomic-embed-text-v1.5
|
||||
provider_id: fireworks
|
||||
provider_model_id: nomic-ai/nomic-embed-text-v1.5
|
||||
model_type: embedding
|
||||
- metadata: {}
|
||||
model_id: ${env.INFERENCE_MODEL}
|
||||
provider_id: vllm-inference
|
||||
model_type: llm
|
||||
shields:
|
||||
- shield_id: meta-llama/Llama-Guard-3-8B
|
||||
vector_dbs: []
|
||||
datasets: []
|
||||
scoring_fns: []
|
||||
benchmarks: []
|
||||
tool_groups:
|
||||
- toolgroup_id: builtin::websearch
|
||||
provider_id: tavily-search
|
||||
- toolgroup_id: builtin::rag
|
||||
provider_id: rag-runtime
|
||||
server:
|
||||
port: 8321
|
Loading…
Add table
Add a link
Reference in a new issue