phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-09 13:14:39 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: Adding OpenAI Compatible Prompts API

Browse source 
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
This commit is contained in:
Francisco Javier Arceo 2025-09-03 14:14:54 -04:00
parent 30117dea22
commit 8b00883abd
181 changed files with 21356 additions and 10332 deletions
Download patch file Download diff file Expand all files Collapse all files

423
docs/_static/llama-stack-spec.html vendored
View file

@ -633,6 +633,80 @@
}
}
},
"/v1/prompts": {
"get": {
"responses": {
"200": {
"description": "A ListPromptsResponse containing all prompts.",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/ListPromptsResponse"
}
}
}
},
"400": {
"$ref": "#/components/responses/BadRequest400"
},
"429": {
"$ref": "#/components/responses/TooManyRequests429"
},
"500": {
"$ref": "#/components/responses/InternalServerError500"
},
"default": {
"$ref": "#/components/responses/DefaultError"
}
},
"tags": [
"Prompts"
],
"description": "List all prompts.",
"parameters": []
},
"post": {
"responses": {
"200": {
"description": "The created Prompt resource.",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/Prompt"
}
}
}
},
"400": {
"$ref": "#/components/responses/BadRequest400"
},
"429": {
"$ref": "#/components/responses/TooManyRequests429"
},
"500": {
"$ref": "#/components/responses/InternalServerError500"
},
"default": {
"$ref": "#/components/responses/DefaultError"
}
},
"tags": [
"Prompts"
],
"description": "Create a new prompt.",
"parameters": [],
"requestBody": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/CreatePromptRequest"
}
}
},
"required": true
}
}
},
"/v1/agents/{agent_id}": {
"get": {
"responses": {
@ -901,6 +975,143 @@
]
}
},
"/v1/prompts/{prompt_id}": {
"get": {
"responses": {
"200": {
"description": "A Prompt resource.",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/Prompt"
}
}
}
},
"400": {
"$ref": "#/components/responses/BadRequest400"
},
"429": {
"$ref": "#/components/responses/TooManyRequests429"
},
"500": {
"$ref": "#/components/responses/InternalServerError500"
},
"default": {
"$ref": "#/components/responses/DefaultError"
}
},
"tags": [
"Prompts"
],
"description": "Get a prompt by its identifier and optional version.",
"parameters": [
{
"name": "prompt_id",
"in": "path",
"description": "The identifier of the prompt to get.",
"required": true,
"schema": {
"type": "string"
}
},
{
"name": "version",
"in": "query",
"description": "The version of the prompt to get (defaults to latest).",
"required": false,
"schema": {
"type": "string"
}
}
]
},
"post": {
"responses": {
"200": {
"description": "The updated Prompt resource with incremented version.",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/Prompt"
}
}
}
},
"400": {
"$ref": "#/components/responses/BadRequest400"
},
"429": {
"$ref": "#/components/responses/TooManyRequests429"
},
"500": {
"$ref": "#/components/responses/InternalServerError500"
},
"default": {
"$ref": "#/components/responses/DefaultError"
}
},
"tags": [
"Prompts"
],
"description": "Update an existing prompt (increments version).",
"parameters": [
{
"name": "prompt_id",
"in": "path",
"description": "The identifier of the prompt to update.",
"required": true,
"schema": {
"type": "string"
}
}
],
"requestBody": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/UpdatePromptRequest"
}
}
},
"required": true
}
},
"delete": {
"responses": {
"200": {
"description": "OK"
},
"400": {
"$ref": "#/components/responses/BadRequest400"
},
"429": {
"$ref": "#/components/responses/TooManyRequests429"
},
"500": {
"$ref": "#/components/responses/InternalServerError500"
},
"default": {
"$ref": "#/components/responses/DefaultError"
}
},
"tags": [
"Prompts"
],
"description": "Delete a prompt.",
"parameters": [
{
"name": "prompt_id",
"in": "path",
"description": "The identifier of the prompt to delete.",
"required": true,
"schema": {
"type": "string"
}
}
]
}
},
"/v1/inference/embeddings": {
"post": {
"responses": {
@ -4129,7 +4340,7 @@
"tags": [
"Files"
],
"description": "Upload a file that can be used across various endpoints.\nThe file upload should be a multipart form request with:\n- file: The File object (not file name) to be uploaded.\n- purpose: The intended purpose of the uploaded file.",
"description": "Upload a file that can be used across various endpoints.\nThe file upload should be a multipart form request with:\n- file: The File object (not file name) to be uploaded.\n- purpose: The intended purpose of the uploaded file.\n- expires_after: Optional form values describing expiration for the file. Expected expires_after[anchor] = \"created_at\", expires_after[seconds] = <int>. Seconds must be between 3600 and 2592000 (1 hour to 30 days).",
"parameters": [],
"requestBody": {
"content": {
@ -4143,11 +4354,33 @@
},
"purpose": {
"$ref": "#/components/schemas/OpenAIFilePurpose"
},
"expires_after_anchor": {
"oneOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"expires_after_seconds": {
"oneOf": [
{
"type": "integer"
},
{
"type": "null"
}
]
}
},
"required": [
"file",
"purpose"
"purpose",
"expires_after_anchor",
"expires_after_seconds"
]
}
}
@ -4985,6 +5218,59 @@
}
}
},
"/v1/prompts/{prompt_id}/default-version": {
"post": {
"responses": {
"200": {
"description": "The prompt with the specified version now set as default.",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/Prompt"
}
}
}
},
"400": {
"$ref": "#/components/responses/BadRequest400"
},
"429": {
"$ref": "#/components/responses/TooManyRequests429"
},
"500": {
"$ref": "#/components/responses/InternalServerError500"
},
"default": {
"$ref": "#/components/responses/DefaultError"
}
},
"tags": [
"Prompts"
],
"description": "Set which version of a prompt should be the default in get_prompt (latest).",
"parameters": [
{
"name": "prompt_id",
"in": "path",
"description": "The identifier of the prompt.",
"required": true,
"schema": {
"type": "string"
}
}
],
"requestBody": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/SetDefaultVersionRequest"
}
}
},
"required": true
}
}
},
"/v1/post-training/supervised-fine-tune": {
"post": {
"responses": {
@ -9648,6 +9934,58 @@
],
"title": "OpenAIResponseObjectStreamResponseWebSearchCallSearching"
},
"CreatePromptRequest": {
"type": "object",
"properties": {
"prompt": {
"type": "string",
"description": "The prompt text content with variable placeholders."
},
"variables": {
"type": "object",
"additionalProperties": {
"type": "string"
},
"description": "Dictionary of variable names to their default values."
}
},
"additionalProperties": false,
"required": [
"prompt"
],
"title": "CreatePromptRequest"
},
"Prompt": {
"type": "object",
"properties": {
"prompt": {
"type": "string",
"description": "The system prompt text with variable placeholders. Variables are only supported when using the Responses API."
},
"version": {
"type": "string",
"description": "Version string (integer start at 1 cast as string, incremented on save)"
},
"prompt_id": {
"type": "string",
"description": "Unique identifier formatted as 'pmpt_<48-digit-hash>'"
},
"variables": {
"type": "object",
"additionalProperties": {
"type": "string"
},
"description": "Dictionary of prompt variable names and values"
}
},
"additionalProperties": false,
"required": [
"version",
"prompt_id"
],
"title": "Prompt",
"description": "A prompt resource representing a stored OpenAI Compatible prompt template in Llama Stack."
},
"OpenAIDeleteResponseObject": {
"type": "object",
"properties": {
@ -10274,7 +10612,8 @@
"scoring_function",
"benchmark",
"tool",
"tool_group"
"tool_group",
"prompt"
],
"const": "benchmark",
"default": "benchmark",
@ -10901,7 +11240,8 @@
"scoring_function",
"benchmark",
"tool",
"tool_group"
"tool_group",
"prompt"
],
"const": "dataset",
"default": "dataset",
@ -11051,7 +11391,8 @@
"scoring_function",
"benchmark",
"tool",
"tool_group"
"tool_group",
"prompt"
],
"const": "model",
"default": "model",
@ -11316,7 +11657,8 @@
"scoring_function",
"benchmark",
"tool",
"tool_group"
"tool_group",
"prompt"
],
"const": "scoring_function",
"default": "scoring_function",
@ -11424,7 +11766,8 @@
"scoring_function",
"benchmark",
"tool",
"tool_group"
"tool_group",
"prompt"
],
"const": "shield",
"default": "shield",
@ -11669,7 +12012,8 @@
"scoring_function",
"benchmark",
"tool",
"tool_group"
"tool_group",
"prompt"
],
"const": "tool",
"default": "tool",
@ -11751,7 +12095,8 @@
"scoring_function",
"benchmark",
"tool",
"tool_group"
"tool_group",
"prompt"
],
"const": "tool_group",
"default": "tool_group",
@ -12045,7 +12390,8 @@
"scoring_function",
"benchmark",
"tool",
"tool_group"
"tool_group",
"prompt"
],
"const": "vector_db",
"default": "vector_db",
@ -12860,6 +13206,23 @@
"title": "OpenAIResponseObjectWithInput",
"description": "OpenAI response object extended with input context information."
},
"ListPromptsResponse": {
"type": "object",
"properties": {
"data": {
"type": "array",
"items": {
"$ref": "#/components/schemas/Prompt"
}
}
},
"additionalProperties": false,
"required": [
"data"
],
"title": "ListPromptsResponse",
"description": "Response model to list prompts."
},
"ListProvidersResponse": {
"type": "object",
"properties": {
@ -17106,6 +17469,20 @@
"title": "ScoreBatchResponse",
"description": "Response from batch scoring operations on datasets."
},
"SetDefaultVersionRequest": {
"type": "object",
"properties": {
"version": {
"type": "string",
"description": "The version to set as default."
}
},
"additionalProperties": false,
"required": [
"version"
],
"title": "SetDefaultVersionRequest"
},
"AlgorithmConfig": {
"oneOf": [
{
@ -17390,6 +17767,27 @@
"title": "SyntheticDataGenerationResponse",
"description": "Response from the synthetic data generation. Batch of (prompt, response, score) tuples that pass the threshold."
},
"UpdatePromptRequest": {
"type": "object",
"properties": {
"prompt": {
"type": "string",
"description": "The updated prompt text content."
},
"variables": {
"type": "object",
"additionalProperties": {
"type": "string"
},
"description": "Updated dictionary of variable names to their default values."
}
},
"additionalProperties": false,
"required": [
"prompt"
],
"title": "UpdatePromptRequest"
},
"VersionInfo": {
"type": "object",
"properties": {
@ -17515,6 +17913,10 @@
{
"name": "PostTraining (Coming Soon)"
},
{
"name": "Prompts",
"x-displayName": "Protocol for prompt management operations."
},
{
"name": "Providers",
"x-displayName": "Providers API for inspecting, listing, and modifying providers and their configurations."
@ -17565,6 +17967,7 @@
"Inspect",
"Models",
"PostTraining (Coming Soon)",
"Prompts",
"Providers",
"Safety",
"Scoring",

297
docs/_static/llama-stack-spec.yaml vendored
View file

@ -427,6 +427,58 @@ paths:
schema:
$ref: '#/components/schemas/CreateOpenaiResponseRequest'
required: true
/v1/prompts:
get:
responses:
'200':
description: >-
A ListPromptsResponse containing all prompts.
content:
application/json:
schema:
$ref: '#/components/schemas/ListPromptsResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Prompts
description: List all prompts.
parameters: []
post:
responses:
'200':
description: The created Prompt resource.
content:
application/json:
schema:
$ref: '#/components/schemas/Prompt'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Prompts
description: Create a new prompt.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/CreatePromptRequest'
required: true
/v1/agents/{agent_id}:
get:
responses:
@ -616,6 +668,103 @@ paths:
required: true
schema:
type: string
/v1/prompts/{prompt_id}:
get:
responses:
'200':
description: A Prompt resource.
content:
application/json:
schema:
$ref: '#/components/schemas/Prompt'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Prompts
description: >-
Get a prompt by its identifier and optional version.
parameters:
- name: prompt_id
in: path
description: The identifier of the prompt to get.
required: true
schema:
type: string
- name: version
in: query
description: >-
The version of the prompt to get (defaults to latest).
required: false
schema:
type: string
post:
responses:
'200':
description: >-
The updated Prompt resource with incremented version.
content:
application/json:
schema:
$ref: '#/components/schemas/Prompt'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Prompts
description: >-
Update an existing prompt (increments version).
parameters:
- name: prompt_id
in: path
description: The identifier of the prompt to update.
required: true
schema:
type: string
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/UpdatePromptRequest'
required: true
delete:
responses:
'200':
description: OK
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Prompts
description: Delete a prompt.
parameters:
- name: prompt_id
in: path
description: The identifier of the prompt to delete.
required: true
schema:
type: string
/v1/inference/embeddings:
post:
responses:
@ -2933,6 +3082,10 @@ paths:
- file: The File object (not file name) to be uploaded.
- purpose: The intended purpose of the uploaded file.
- expires_after: Optional form values describing expiration for the file.
Expected expires_after[anchor] = "created_at", expires_after[seconds] = <int>.
Seconds must be between 3600 and 2592000 (1 hour to 30 days).
parameters: []
requestBody:
content:
@ -2945,9 +3098,19 @@ paths:
format: binary
purpose:
$ref: '#/components/schemas/OpenAIFilePurpose'
expires_after_anchor:
oneOf:
- type: string
- type: 'null'
expires_after_seconds:
oneOf:
- type: integer
- type: 'null'
required:
- file
- purpose
- expires_after_anchor
- expires_after_seconds
required: true
/v1/openai/v1/models:
get:
@ -3532,6 +3695,43 @@ paths:
schema:
$ref: '#/components/schemas/ScoreBatchRequest'
required: true
/v1/prompts/{prompt_id}/default-version:
post:
responses:
'200':
description: >-
The prompt with the specified version now set as default.
content:
application/json:
schema:
$ref: '#/components/schemas/Prompt'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Prompts
description: >-
Set which version of a prompt should be the default in get_prompt (latest).
parameters:
- name: prompt_id
in: path
description: The identifier of the prompt.
required: true
schema:
type: string
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/SetDefaultVersionRequest'
required: true
/v1/post-training/supervised-fine-tune:
post:
responses:
@ -7134,6 +7334,53 @@ components:
- type
title: >-
OpenAIResponseObjectStreamResponseWebSearchCallSearching
CreatePromptRequest:
type: object
properties:
prompt:
type: string
description: >-
The prompt text content with variable placeholders.
variables:
type: object
additionalProperties:
type: string
description: >-
Dictionary of variable names to their default values.
additionalProperties: false
required:
- prompt
title: CreatePromptRequest
Prompt:
type: object
properties:
prompt:
type: string
description: >-
The system prompt text with variable placeholders. Variables are only
supported when using the Responses API.
version:
type: string
description: >-
Version string (integer start at 1 cast as string, incremented on save)
prompt_id:
type: string
description: >-
Unique identifier formatted as 'pmpt_<48-digit-hash>'
variables:
type: object
additionalProperties:
type: string
description: >-
Dictionary of prompt variable names and values
additionalProperties: false
required:
- version
- prompt_id
title: Prompt
description: >-
A prompt resource representing a stored OpenAI Compatible prompt template
in Llama Stack.
OpenAIDeleteResponseObject:
type: object
properties:
@ -7607,6 +7854,7 @@ components:
- benchmark
- tool
- tool_group
- prompt
const: benchmark
default: benchmark
description: The resource type, always benchmark
@ -8093,6 +8341,7 @@ components:
- benchmark
- tool
- tool_group
- prompt
const: dataset
default: dataset
description: >-
@ -8205,6 +8454,7 @@ components:
- benchmark
- tool
- tool_group
- prompt
const: model
default: model
description: >-
@ -8396,6 +8646,7 @@ components:
- benchmark
- tool
- tool_group
- prompt
const: scoring_function
default: scoring_function
description: >-
@ -8472,6 +8723,7 @@ components:
- benchmark
- tool
- tool_group
- prompt
const: shield
default: shield
description: The resource type, always shield
@ -8651,6 +8903,7 @@ components:
- benchmark
- tool
- tool_group
- prompt
const: tool
default: tool
description: Type of resource, always 'tool'
@ -8709,6 +8962,7 @@ components:
- benchmark
- tool
- tool_group
- prompt
const: tool_group
default: tool_group
description: Type of resource, always 'tool_group'
@ -8937,6 +9191,7 @@ components:
- benchmark
- tool
- tool_group
- prompt
const: vector_db
default: vector_db
description: >-
@ -9563,6 +9818,18 @@ components:
title: OpenAIResponseObjectWithInput
description: >-
OpenAI response object extended with input context information.
ListPromptsResponse:
type: object
properties:
data:
type: array
items:
$ref: '#/components/schemas/Prompt'
additionalProperties: false
required:
- data
title: ListPromptsResponse
description: Response model to list prompts.
ListProvidersResponse:
type: object
properties:
@ -12708,6 +12975,16 @@ components:
title: ScoreBatchResponse
description: >-
Response from batch scoring operations on datasets.
SetDefaultVersionRequest:
type: object
properties:
version:
type: string
description: The version to set as default.
additionalProperties: false
required:
- version
title: SetDefaultVersionRequest
AlgorithmConfig:
oneOf:
- $ref: '#/components/schemas/LoraFinetuningConfig'
@ -12904,6 +13181,22 @@ components:
description: >-
Response from the synthetic data generation. Batch of (prompt, response, score)
tuples that pass the threshold.
UpdatePromptRequest:
type: object
properties:
prompt:
type: string
description: The updated prompt text content.
variables:
type: object
additionalProperties:
type: string
description: >-
Updated dictionary of variable names to their default values.
additionalProperties: false
required:
- prompt
title: UpdatePromptRequest
VersionInfo:
type: object
properties:
@ -13015,6 +13308,9 @@ tags:
- name: Inspect
- name: Models
- name: PostTraining (Coming Soon)
- name: Prompts
x-displayName: >-
Protocol for prompt management operations.
- name: Providers
x-displayName: >-
Providers API for inspecting, listing, and modifying providers and their configurations.
@ -13042,6 +13338,7 @@ x-tagGroups:
- Inspect
- Models
- PostTraining (Coming Soon)
- Prompts
- Providers
- Safety
- Scoring

9
docs/source/contributing/testing/record-replay.md
View file

@ -40,18 +40,15 @@ The system patches OpenAI and Ollama client methods to intercept calls before th
### Storage Architecture
Recordings use a two-tier storage system optimized for both speed and debuggability:
Recordings are stored as JSON files in the recording directory. They are looked up by their request hash.
```
recordings/
├── index.sqlite # Fast lookup by request hash
└── responses/
├── abc123def456.json # Individual response files
└── def789ghi012.json
```
**SQLite index** enables O(log n) hash lookups and metadata queries without loading response bodies.
**JSON files** store complete request/response pairs in human-readable format for debugging.
## Recording Modes
@ -166,8 +163,8 @@ This preserves type safety - when replayed, you get the same Pydantic objects wi
Control recording behavior globally:
```bash
export LLAMA_STACK_TEST_INFERENCE_MODE=replay
export LLAMA_STACK_TEST_RECORDING_DIR=/path/to/recordings
export LLAMA_STACK_TEST_INFERENCE_MODE=replay # this is the default
export LLAMA_STACK_TEST_RECORDING_DIR=/path/to/recordings # default is tests/integration/recordings
pytest tests/integration/
```

1
docs/source/distributions/self_hosted_distro/nvidia.md
View file

@ -50,6 +50,7 @@ The following models are available by default:
- `meta/llama-3.2-11b-vision-instruct `
- `meta/llama-3.2-90b-vision-instruct `
- `meta/llama-3.3-70b-instruct `
- `nvidia/vila `
- `nvidia/llama-3.2-nv-embedqa-1b-v2 `
- `nvidia/nv-embedqa-e5-v5 `
- `nvidia/nv-embedqa-mistral-7b-v2 `

73
docs/source/providers/vector_io/remote_pgvector.md
View file

@ -12,6 +12,60 @@ That means you'll get fast and efficient vector retrieval.
- Easy to use
- Fully integrated with Llama Stack
There are three implementations of search for PGVectoIndex available:
1. Vector Search:
- How it works:
- Uses PostgreSQL's vector extension (pgvector) to perform similarity search
- Compares query embeddings against stored embeddings using Cosine distance or other distance metrics
- Eg. SQL query: SELECT document, embedding <=> %s::vector AS distance FROM table ORDER BY distance
-Characteristics:
- Semantic understanding - finds documents similar in meaning even if they don't share keywords
- Works with high-dimensional vector embeddings (typically 768, 1024, or higher dimensions)
- Best for: Finding conceptually related content, handling synonyms, cross-language search
2. Keyword Search
- How it works:
- Uses PostgreSQL's full-text search capabilities with tsvector and ts_rank
- Converts text to searchable tokens using to_tsvector('english', text). Default language is English.
- Eg. SQL query: SELECT document, ts_rank(tokenized_content, plainto_tsquery('english', %s)) AS score
- Characteristics:
- Lexical matching - finds exact keyword matches and variations
- Uses GIN (Generalized Inverted Index) for fast text search performance
- Scoring: Uses PostgreSQL's ts_rank function for relevance scoring
- Best for: Exact term matching, proper names, technical terms, Boolean-style queries
3. Hybrid Search
- How it works:
- Combines both vector and keyword search results
- Runs both searches independently, then merges results using configurable reranking
- Two reranking strategies available:
- Reciprocal Rank Fusion (RRF) - (default: 60.0)
- Weighted Average - (default: 0.5)
- Characteristics:
- Best of both worlds: semantic understanding + exact matching
- Documents appearing in both searches get boosted scores
- Configurable balance between semantic and lexical matching
- Best for: General-purpose search where you want both precision and recall
4. Database Schema
The PGVector implementation stores data optimized for all three search types:
CREATE TABLE vector_store_xxx (
id TEXT PRIMARY KEY,
document JSONB, -- Original document
embedding vector(dimension), -- For vector search
content_text TEXT, -- Raw text content
tokenized_content TSVECTOR -- For keyword search
);
-- Indexes for performance
CREATE INDEX content_gin_idx ON table USING GIN(tokenized_content); -- Keyword search
-- Vector index created automatically by pgvector
## Usage
To use PGVector in your Llama Stack project, follow these steps:
@ -20,6 +74,25 @@ To use PGVector in your Llama Stack project, follow these steps:
2. Configure your Llama Stack project to use pgvector. (e.g. remote::pgvector).
3. Start storing and querying vectors.
## This is an example how you can set up your environment for using PGVector
1. Export env vars:
```bash
export ENABLE_PGVECTOR=true
export PGVECTOR_HOST=localhost
export PGVECTOR_PORT=5432
export PGVECTOR_DB=llamastack
export PGVECTOR_USER=llamastack
export PGVECTOR_PASSWORD=llamastack
```
2. Create DB:
```bash
psql -h localhost -U postgres -c "CREATE ROLE llamastack LOGIN PASSWORD 'llamastack';"
psql -h localhost -U postgres -c "CREATE DATABASE llamastack OWNER llamastack;"
psql -h localhost -U llamastack -d llamastack -c "CREATE EXTENSION IF NOT EXISTS vector;"
```
## Installation
You can install PGVector using docker:

1
docs/source/providers/vector_io/remote_weaviate.md
View file

@ -17,6 +17,7 @@ Weaviate supports:
- Metadata filtering
- Multi-modal retrieval
## Usage
To use Weaviate in your Llama Stack project, follow these steps:

1
docs/source/references/llama_stack_client_cli_reference.md
View file

@ -478,7 +478,6 @@ llama-stack-client scoring_functions list
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━┓
┃ identifier ┃ provider_id ┃ description ┃ type ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━┩
│ basic::bfcl │ basic │ BFCL complex scoring │ scoring_function │
│ basic::docvqa │ basic │ DocVQA Visual Question & Answer scoring function │ scoring_function │
│ basic::equality │ basic │ Returns 1.0 if the input is equal to the target, 0.0 │ scoring_function │
│ │ │ otherwise. │ │