Merge branch 'main' into nvidia-e2e-notebook

docs/_static/llama-stack-spec.yaml

@@ -2263,6 +2263,43 @@ paths:
             schema:
               $ref: '#/components/schemas/LogEventRequest'
         required: true
+  /v1/openai/v1/vector_stores/{vector_store_id}/files:
+    post:
+      responses:
+        '200':
+          description: >-
+            A VectorStoreFileObject representing the attached file.
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/VectorStoreFileObject'
+        '400':
+          $ref: '#/components/responses/BadRequest400'
+        '429':
+          $ref: >-
+            #/components/responses/TooManyRequests429
+        '500':
+          $ref: >-
+            #/components/responses/InternalServerError500
+        default:
+          $ref: '#/components/responses/DefaultError'
+      tags:
+        - VectorIO
+      description: Attach a file to a vector store.
+      parameters:
+        - name: vector_store_id
+          in: path
+          description: >-
+            The ID of the vector store to attach the file to.
+          required: true
+          schema:
+            type: string
+      requestBody:
+        content:
+          application/json:
+            schema:
+              $ref: '#/components/schemas/OpenaiAttachFileToVectorStoreRequest'
+        required: true
   /v1/openai/v1/completions:
     post:
       responses:
@@ -2294,6 +2331,91 @@ paths:
             schema:
               $ref: '#/components/schemas/OpenaiCompletionRequest'
         required: true
+  /v1/openai/v1/vector_stores:
+    get:
+      responses:
+        '200':
+          description: >-
+            A VectorStoreListResponse containing the list of vector stores.
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/VectorStoreListResponse'
+        '400':
+          $ref: '#/components/responses/BadRequest400'
+        '429':
+          $ref: >-
+            #/components/responses/TooManyRequests429
+        '500':
+          $ref: >-
+            #/components/responses/InternalServerError500
+        default:
+          $ref: '#/components/responses/DefaultError'
+      tags:
+        - VectorIO
+      description: Returns a list of vector stores.
+      parameters:
+        - name: limit
+          in: query
+          description: >-
+            A limit on the number of objects to be returned. Limit can range between
+            1 and 100, and the default is 20.
+          required: false
+          schema:
+            type: integer
+        - name: order
+          in: query
+          description: >-
+            Sort order by the `created_at` timestamp of the objects. `asc` for ascending
+            order and `desc` for descending order.
+          required: false
+          schema:
+            type: string
+        - name: after
+          in: query
+          description: >-
+            A cursor for use in pagination. `after` is an object ID that defines your
+            place in the list.
+          required: false
+          schema:
+            type: string
+        - name: before
+          in: query
+          description: >-
+            A cursor for use in pagination. `before` is an object ID that defines
+            your place in the list.
+          required: false
+          schema:
+            type: string
+    post:
+      responses:
+        '200':
+          description: >-
+            A VectorStoreObject representing the created vector store.
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/VectorStoreObject'
+        '400':
+          $ref: '#/components/responses/BadRequest400'
+        '429':
+          $ref: >-
+            #/components/responses/TooManyRequests429
+        '500':
+          $ref: >-
+            #/components/responses/InternalServerError500
+        default:
+          $ref: '#/components/responses/DefaultError'
+      tags:
+        - VectorIO
+      description: Creates a vector store.
+      parameters: []
+      requestBody:
+        content:
+          application/json:
+            schema:
+              $ref: '#/components/schemas/OpenaiCreateVectorStoreRequest'
+        required: true
   /v1/openai/v1/files/{file_id}:
     get:
       responses:
@@ -2356,6 +2478,100 @@ paths:
           required: true
           schema:
             type: string
+  /v1/openai/v1/vector_stores/{vector_store_id}:
+    get:
+      responses:
+        '200':
+          description: >-
+            A VectorStoreObject representing the vector store.
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/VectorStoreObject'
+        '400':
+          $ref: '#/components/responses/BadRequest400'
+        '429':
+          $ref: >-
+            #/components/responses/TooManyRequests429
+        '500':
+          $ref: >-
+            #/components/responses/InternalServerError500
+        default:
+          $ref: '#/components/responses/DefaultError'
+      tags:
+        - VectorIO
+      description: Retrieves a vector store.
+      parameters:
+        - name: vector_store_id
+          in: path
+          description: The ID of the vector store to retrieve.
+          required: true
+          schema:
+            type: string
+    post:
+      responses:
+        '200':
+          description: >-
+            A VectorStoreObject representing the updated vector store.
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/VectorStoreObject'
+        '400':
+          $ref: '#/components/responses/BadRequest400'
+        '429':
+          $ref: >-
+            #/components/responses/TooManyRequests429
+        '500':
+          $ref: >-
+            #/components/responses/InternalServerError500
+        default:
+          $ref: '#/components/responses/DefaultError'
+      tags:
+        - VectorIO
+      description: Updates a vector store.
+      parameters:
+        - name: vector_store_id
+          in: path
+          description: The ID of the vector store to update.
+          required: true
+          schema:
+            type: string
+      requestBody:
+        content:
+          application/json:
+            schema:
+              $ref: '#/components/schemas/OpenaiUpdateVectorStoreRequest'
+        required: true
+    delete:
+      responses:
+        '200':
+          description: >-
+            A VectorStoreDeleteResponse indicating the deletion status.
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/VectorStoreDeleteResponse'
+        '400':
+          $ref: '#/components/responses/BadRequest400'
+        '429':
+          $ref: >-
+            #/components/responses/TooManyRequests429
+        '500':
+          $ref: >-
+            #/components/responses/InternalServerError500
+        default:
+          $ref: '#/components/responses/DefaultError'
+      tags:
+        - VectorIO
+      description: Delete a vector store.
+      parameters:
+        - name: vector_store_id
+          in: path
+          description: The ID of the vector store to delete.
+          required: true
+          schema:
+            type: string
   /v1/openai/v1/embeddings:
     post:
       responses:
@@ -2546,6 +2762,46 @@ paths:
           required: true
           schema:
             type: string
+  /v1/openai/v1/vector_stores/{vector_store_id}/search:
+    post:
+      responses:
+        '200':
+          description: >-
+            A VectorStoreSearchResponse containing the search results.
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/VectorStoreSearchResponsePage'
+        '400':
+          $ref: '#/components/responses/BadRequest400'
+        '429':
+          $ref: >-
+            #/components/responses/TooManyRequests429
+        '500':
+          $ref: >-
+            #/components/responses/InternalServerError500
+        default:
+          $ref: '#/components/responses/DefaultError'
+      tags:
+        - VectorIO
+      description: >-
+        Search for chunks in a vector store.
+
+        Searches a vector store for relevant chunks based on a query and optional
+        file attribute filters.
+      parameters:
+        - name: vector_store_id
+          in: path
+          description: The ID of the vector store to search.
+          required: true
+          schema:
+            type: string
+      requestBody:
+        content:
+          application/json:
+            schema:
+              $ref: '#/components/schemas/OpenaiSearchVectorStoreRequest'
+        required: true
   /v1/post-training/preference-optimize:
     post:
       responses:
@@ -4802,6 +5058,7 @@ components:
     OpenAIResponseInput:
       oneOf:
         - $ref: '#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall'
+        - $ref: '#/components/schemas/OpenAIResponseOutputMessageFileSearchToolCall'
         - $ref: '#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall'
         - $ref: '#/components/schemas/OpenAIResponseInputFunctionToolCallOutput'
         - $ref: '#/components/schemas/OpenAIResponseMessage'
@@ -4896,10 +5153,23 @@ components:
           type: string
           const: file_search
           default: file_search
-        vector_store_id:
+        vector_store_ids:
           type: array
           items:
             type: string
+        filters:
+          type: object
+          additionalProperties:
+            oneOf:
+              - type: 'null'
+              - type: boolean
+              - type: number
+              - type: string
+              - type: array
+              - type: object
+        max_num_results:
+          type: integer
+          default: 10
         ranking_options:
           type: object
           properties:
@@ -4913,7 +5183,7 @@ components:
       additionalProperties: false
       required:
         - type
-        - vector_store_id
+        - vector_store_ids
       title: OpenAIResponseInputToolFileSearch
     OpenAIResponseInputToolFunction:
       type: object
@@ -5075,6 +5345,41 @@ components:
         - type
       title: >-
         OpenAIResponseOutputMessageContentOutputText
+    "OpenAIResponseOutputMessageFileSearchToolCall":
+      type: object
+      properties:
+        id:
+          type: string
+        queries:
+          type: array
+          items:
+            type: string
+        status:
+          type: string
+        type:
+          type: string
+          const: file_search_call
+          default: file_search_call
+        results:
+          type: array
+          items:
+            type: object
+            additionalProperties:
+              oneOf:
+                - type: 'null'
+                - type: boolean
+                - type: number
+                - type: string
+                - type: array
+                - type: object
+      additionalProperties: false
+      required:
+        - id
+        - queries
+        - status
+        - type
+      title: >-
+        OpenAIResponseOutputMessageFileSearchToolCall
     "OpenAIResponseOutputMessageFunctionToolCall":
       type: object
       properties:
@@ -5272,6 +5577,7 @@ components:
       oneOf:
         - $ref: '#/components/schemas/OpenAIResponseMessage'
         - $ref: '#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall'
+        - $ref: '#/components/schemas/OpenAIResponseOutputMessageFileSearchToolCall'
         - $ref: '#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall'
         - $ref: '#/components/schemas/OpenAIResponseOutputMessageMCPCall'
         - $ref: '#/components/schemas/OpenAIResponseOutputMessageMCPListTools'
@@ -5280,6 +5586,7 @@ components:
         mapping:
           message: '#/components/schemas/OpenAIResponseMessage'
           web_search_call: '#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall'
+          file_search_call: '#/components/schemas/OpenAIResponseOutputMessageFileSearchToolCall'
           function_call: '#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall'
           mcp_call: '#/components/schemas/OpenAIResponseOutputMessageMCPCall'
           mcp_list_tools: '#/components/schemas/OpenAIResponseOutputMessageMCPListTools'
@@ -7511,6 +7818,9 @@ components:
           type: boolean
           description: >-
             Whether there are more items available after this set
+        url:
+          type: string
+          description: The URL for accessing this list
       additionalProperties: false
       required:
         - data
@@ -8032,6 +8342,148 @@ components:
         - event
         - ttl_seconds
       title: LogEventRequest
+    VectorStoreChunkingStrategy:
+      oneOf:
+        - $ref: '#/components/schemas/VectorStoreChunkingStrategyAuto'
+        - $ref: '#/components/schemas/VectorStoreChunkingStrategyStatic'
+      discriminator:
+        propertyName: type
+        mapping:
+          auto: '#/components/schemas/VectorStoreChunkingStrategyAuto'
+          static: '#/components/schemas/VectorStoreChunkingStrategyStatic'
+    VectorStoreChunkingStrategyAuto:
+      type: object
+      properties:
+        type:
+          type: string
+          const: auto
+          default: auto
+      additionalProperties: false
+      required:
+        - type
+      title: VectorStoreChunkingStrategyAuto
+    VectorStoreChunkingStrategyStatic:
+      type: object
+      properties:
+        type:
+          type: string
+          const: static
+          default: static
+        static:
+          $ref: '#/components/schemas/VectorStoreChunkingStrategyStaticConfig'
+      additionalProperties: false
+      required:
+        - type
+        - static
+      title: VectorStoreChunkingStrategyStatic
+    VectorStoreChunkingStrategyStaticConfig:
+      type: object
+      properties:
+        chunk_overlap_tokens:
+          type: integer
+          default: 400
+        max_chunk_size_tokens:
+          type: integer
+          default: 800
+      additionalProperties: false
+      required:
+        - chunk_overlap_tokens
+        - max_chunk_size_tokens
+      title: VectorStoreChunkingStrategyStaticConfig
+    OpenaiAttachFileToVectorStoreRequest:
+      type: object
+      properties:
+        file_id:
+          type: string
+          description: >-
+            The ID of the file to attach to the vector store.
+        attributes:
+          type: object
+          additionalProperties:
+            oneOf:
+              - type: 'null'
+              - type: boolean
+              - type: number
+              - type: string
+              - type: array
+              - type: object
+          description: >-
+            The key-value attributes stored with the file, which can be used for filtering.
+        chunking_strategy:
+          $ref: '#/components/schemas/VectorStoreChunkingStrategy'
+          description: >-
+            The chunking strategy to use for the file.
+      additionalProperties: false
+      required:
+        - file_id
+      title: OpenaiAttachFileToVectorStoreRequest
+    VectorStoreFileLastError:
+      type: object
+      properties:
+        code:
+          oneOf:
+            - type: string
+              const: server_error
+            - type: string
+              const: rate_limit_exceeded
+        message:
+          type: string
+      additionalProperties: false
+      required:
+        - code
+        - message
+      title: VectorStoreFileLastError
+    VectorStoreFileObject:
+      type: object
+      properties:
+        id:
+          type: string
+        object:
+          type: string
+          default: vector_store.file
+        attributes:
+          type: object
+          additionalProperties:
+            oneOf:
+              - type: 'null'
+              - type: boolean
+              - type: number
+              - type: string
+              - type: array
+              - type: object
+        chunking_strategy:
+          $ref: '#/components/schemas/VectorStoreChunkingStrategy'
+        created_at:
+          type: integer
+        last_error:
+          $ref: '#/components/schemas/VectorStoreFileLastError'
+        status:
+          oneOf:
+            - type: string
+              const: completed
+            - type: string
+              const: in_progress
+            - type: string
+              const: cancelled
+            - type: string
+              const: failed
+        usage_bytes:
+          type: integer
+          default: 0
+        vector_store_id:
+          type: string
+      additionalProperties: false
+      required:
+        - id
+        - object
+        - attributes
+        - chunking_strategy
+        - created_at
+        - status
+        - usage_bytes
+        - vector_store_id
+      title: VectorStoreFileObject
+      description: OpenAI Vector Store File object.
     OpenAIJSONSchema:
       type: object
       properties:
@@ -8454,6 +8906,10 @@ components:
             type: string
         prompt_logprobs:
           type: integer
+        suffix:
+          type: string
+          description: >-
+            (Optional) The suffix that should be appended to the completion.
       additionalProperties: false
       required:
         - model
@@ -8505,6 +8961,133 @@ components:
       title: OpenAICompletionChoice
       description: >-
         A choice from an OpenAI-compatible completion response.
+    OpenaiCreateVectorStoreRequest:
+      type: object
+      properties:
+        name:
+          type: string
+          description: A name for the vector store.
+        file_ids:
+          type: array
+          items:
+            type: string
+          description: >-
+            A list of File IDs that the vector store should use. Useful for tools
+            like `file_search` that can access files.
+        expires_after:
+          type: object
+          additionalProperties:
+            oneOf:
+              - type: 'null'
+              - type: boolean
+              - type: number
+              - type: string
+              - type: array
+              - type: object
+          description: >-
+            The expiration policy for a vector store.
+        chunking_strategy:
+          type: object
+          additionalProperties:
+            oneOf:
+              - type: 'null'
+              - type: boolean
+              - type: number
+              - type: string
+              - type: array
+              - type: object
+          description: >-
+            The chunking strategy used to chunk the file(s). If not set, will use
+            the `auto` strategy.
+        metadata:
+          type: object
+          additionalProperties:
+            oneOf:
+              - type: 'null'
+              - type: boolean
+              - type: number
+              - type: string
+              - type: array
+              - type: object
+          description: >-
+            Set of 16 key-value pairs that can be attached to an object.
+        embedding_model:
+          type: string
+          description: >-
+            The embedding model to use for this vector store.
+        embedding_dimension:
+          type: integer
+          description: >-
+            The dimension of the embedding vectors (default: 384).
+        provider_id:
+          type: string
+          description: >-
+            The ID of the provider to use for this vector store.
+        provider_vector_db_id:
+          type: string
+          description: >-
+            The provider-specific vector database ID.
+      additionalProperties: false
+      required:
+        - name
+      title: OpenaiCreateVectorStoreRequest
+    VectorStoreObject:
+      type: object
+      properties:
+        id:
+          type: string
+        object:
+          type: string
+          default: vector_store
+        created_at:
+          type: integer
+        name:
+          type: string
+        usage_bytes:
+          type: integer
+          default: 0
+        file_counts:
+          type: object
+          additionalProperties:
+            type: integer
+        status:
+          type: string
+          default: completed
+        expires_after:
+          type: object
+          additionalProperties:
+            oneOf:
+              - type: 'null'
+              - type: boolean
+              - type: number
+              - type: string
+              - type: array
+              - type: object
+        expires_at:
+          type: integer
+        last_active_at:
+          type: integer
+        metadata:
+          type: object
+          additionalProperties:
+            oneOf:
+              - type: 'null'
+              - type: boolean
+              - type: number
+              - type: string
+              - type: array
+              - type: object
+      additionalProperties: false
+      required:
+        - id
+        - object
+        - created_at
+        - usage_bytes
+        - file_counts
+        - status
+        - metadata
+      title: VectorStoreObject
+      description: OpenAI Vector Store object.
     OpenAIFileDeleteResponse:
       type: object
       properties:
@@ -8528,6 +9111,24 @@ components:
       title: OpenAIFileDeleteResponse
       description: >-
         Response for deleting a file in OpenAI Files API.
+    VectorStoreDeleteResponse:
+      type: object
+      properties:
+        id:
+          type: string
+        object:
+          type: string
+          default: vector_store.deleted
+        deleted:
+          type: boolean
+          default: true
+      additionalProperties: false
+      required:
+        - id
+        - object
+        - deleted
+      title: VectorStoreDeleteResponse
+      description: Response from deleting a vector store.
     OpenaiEmbeddingsRequest:
       type: object
       properties:
@@ -8751,9 +9352,179 @@ components:
       required:
         - data
       title: OpenAIListModelsResponse
+    VectorStoreListResponse:
+      type: object
+      properties:
+        object:
+          type: string
+          default: list
+        data:
+          type: array
+          items:
+            $ref: '#/components/schemas/VectorStoreObject'
+        first_id:
+          type: string
+        last_id:
+          type: string
+        has_more:
+          type: boolean
+          default: false
+      additionalProperties: false
+      required:
+        - object
+        - data
+        - has_more
+      title: VectorStoreListResponse
+      description: Response from listing vector stores.
     Response:
       type: object
       title: Response
+    OpenaiSearchVectorStoreRequest:
+      type: object
+      properties:
+        query:
+          oneOf:
+            - type: string
+            - type: array
+              items:
+                type: string
+          description: >-
+            The query string or array for performing the search.
+        filters:
+          type: object
+          additionalProperties:
+            oneOf:
+              - type: 'null'
+              - type: boolean
+              - type: number
+              - type: string
+              - type: array
+              - type: object
+          description: >-
+            Filters based on file attributes to narrow the search results.
+        max_num_results:
+          type: integer
+          description: >-
+            Maximum number of results to return (1 to 50 inclusive, default 10).
+        ranking_options:
+          type: object
+          additionalProperties:
+            oneOf:
+              - type: 'null'
+              - type: boolean
+              - type: number
+              - type: string
+              - type: array
+              - type: object
+          description: >-
+            Ranking options for fine-tuning the search results.
+        rewrite_query:
+          type: boolean
+          description: >-
+            Whether to rewrite the natural language query for vector search (default
+            false)
+      additionalProperties: false
+      required:
+        - query
+      title: OpenaiSearchVectorStoreRequest
+    VectorStoreContent:
+      type: object
+      properties:
+        type:
+          type: string
+          const: text
+        text:
+          type: string
+      additionalProperties: false
+      required:
+        - type
+        - text
+      title: VectorStoreContent
+    VectorStoreSearchResponse:
+      type: object
+      properties:
+        file_id:
+          type: string
+        filename:
+          type: string
+        score:
+          type: number
+        attributes:
+          type: object
+          additionalProperties:
+            oneOf:
+              - type: string
+              - type: number
+              - type: boolean
+        content:
+          type: array
+          items:
+            $ref: '#/components/schemas/VectorStoreContent'
+      additionalProperties: false
+      required:
+        - file_id
+        - filename
+        - score
+        - content
+      title: VectorStoreSearchResponse
+      description: Response from searching a vector store.
+    VectorStoreSearchResponsePage:
+      type: object
+      properties:
+        object:
+          type: string
+          default: vector_store.search_results.page
+        search_query:
+          type: string
+        data:
+          type: array
+          items:
+            $ref: '#/components/schemas/VectorStoreSearchResponse'
+        has_more:
+          type: boolean
+          default: false
+        next_page:
+          type: string
+      additionalProperties: false
+      required:
+        - object
+        - search_query
+        - data
+        - has_more
+      title: VectorStoreSearchResponsePage
+      description: Response from searching a vector store.
+    OpenaiUpdateVectorStoreRequest:
+      type: object
+      properties:
+        name:
+          type: string
+          description: The name of the vector store.
+        expires_after:
+          type: object
+          additionalProperties:
+            oneOf:
+              - type: 'null'
+              - type: boolean
+              - type: number
+              - type: string
+              - type: array
+              - type: object
+          description: >-
+            The expiration policy for a vector store.
+        metadata:
+          type: object
+          additionalProperties:
+            oneOf:
+              - type: 'null'
+              - type: boolean
+              - type: number
+              - type: string
+              - type: array
+              - type: object
+          description: >-
+            Set of 16 key-value pairs that can be attached to an object.
+      additionalProperties: false
+      title: OpenaiUpdateVectorStoreRequest
     DPOAlignmentConfig:
       type: object
       properties:
@@ -8992,7 +9763,13 @@ components:
         mode:
           type: string
           description: >-
-            Search mode for retrieval—either "vector" or "keyword". Default "vector".
+            Search mode for retrieval—either "vector", "keyword", or "hybrid". Default
+            "vector".
+        ranker:
+          $ref: '#/components/schemas/Ranker'
+          description: >-
+            Configuration for the ranker to use in hybrid search. Defaults to RRF
+            ranker.
       additionalProperties: false
       required:
         - query_generator_config
@@ -9011,6 +9788,58 @@ components:
         mapping:
           default: '#/components/schemas/DefaultRAGQueryGeneratorConfig'
           llm: '#/components/schemas/LLMRAGQueryGeneratorConfig'
+    RRFRanker:
+      type: object
+      properties:
+        type:
+          type: string
+          const: rrf
+          default: rrf
+          description: The type of ranker, always "rrf"
+        impact_factor:
+          type: number
+          default: 60.0
+          description: >-
+            The impact factor for RRF scoring. Higher values give more weight to higher-ranked
+            results. Must be greater than 0. Default of 60 is from the original RRF
+            paper (Cormack et al., 2009).
+      additionalProperties: false
+      required:
+        - type
+        - impact_factor
+      title: RRFRanker
+      description: >-
+        Reciprocal Rank Fusion (RRF) ranker configuration.
+    Ranker:
+      oneOf:
+        - $ref: '#/components/schemas/RRFRanker'
+        - $ref: '#/components/schemas/WeightedRanker'
+      discriminator:
+        propertyName: type
+        mapping:
+          rrf: '#/components/schemas/RRFRanker'
+          weighted: '#/components/schemas/WeightedRanker'
+    WeightedRanker:
+      type: object
+      properties:
+        type:
+          type: string
+          const: weighted
+          default: weighted
+          description: The type of ranker, always "weighted"
+        alpha:
+          type: number
+          default: 0.5
+          description: >-
+            Weight factor between 0 and 1. 0 means only use keyword scores, 1 means
+            only use vector scores, values in between blend both scores.
+      additionalProperties: false
+      required:
+        - type
+        - alpha
+      title: WeightedRanker
+      description: >-
+        Weighted ranker configuration that combines vector and keyword scores.
     QueryRequest:
       type: object
       properties:

docs/source/distributions/configuration.md

@@ -56,10 +56,10 @@ shields: []
 server:
   port: 8321
   auth:
-    provider_type: "kubernetes"
+    provider_type: "oauth2_token"
     config:
-      api_server_url: "https://kubernetes.default.svc"
-      ca_cert_path: "/path/to/ca.crt"
+      jwks:
+        uri: "https://my-token-issuing-svc.com/jwks"
 ```
 
 Let's break this down into the different sections. The first section specifies the set of APIs that the stack server will serve:
@@ -132,16 +132,52 @@ The server supports multiple authentication providers:
 
 #### OAuth 2.0/OpenID Connect Provider with Kubernetes
 
-The Kubernetes cluster must be configured to use a service account for authentication.
+The server can be configured to use service account tokens for authorization, validating these against the Kubernetes API server, e.g.:
+```yaml
+server:
+  auth:
+    provider_type: "oauth2_token"
+    config:
+      jwks:
+        uri: "https://kubernetes.default.svc:8443/openid/v1/jwks"
+	token: "${env.TOKEN:}"
+        key_recheck_period: 3600
+      tls_cafile: "/path/to/ca.crt"
+      issuer: "https://kubernetes.default.svc"
+      audience: "https://kubernetes.default.svc"
+```
+
+To find your cluster's jwks uri (from which the public key(s) to verify the token signature are obtained), run:
+```
+kubectl get --raw /.well-known/openid-configuration| jq -r .jwks_uri
+```
+
+For the tls_cafile, you can use the CA certificate of the OIDC provider:
+```bash
+kubectl config view --minify -o jsonpath='{.clusters[0].cluster.certificate-authority}'
+```
+
+For the issuer, you can use the OIDC provider's URL:
+```bash
+kubectl get --raw /.well-known/openid-configuration| jq .issuer
+```
+
+The audience can be obtained from a token, e.g. run:
+```bash
+kubectl create token default --duration=1h | cut -d. -f2 | base64 -d | jq .aud
+```
+
+The jwks token is used to authorize access to the jwks endpoint. You can obtain a token by running:
 
 ```bash
 kubectl create namespace llama-stack
 kubectl create serviceaccount llama-stack-auth -n llama-stack
-kubectl create rolebinding llama-stack-auth-rolebinding --clusterrole=admin --serviceaccount=llama-stack:llama-stack-auth -n llama-stack
 kubectl create token llama-stack-auth -n llama-stack > llama-stack-auth-token
+export TOKEN=$(cat llama-stack-auth-token)
 ```
 
-Make sure the `kube-apiserver` runs with `--anonymous-auth=true` to allow unauthenticated requests
+Alternatively, you can configure the jwks endpoint to allow anonymous access. To do this, make sure
+the `kube-apiserver` runs with `--anonymous-auth=true` to allow unauthenticated requests
 and that the correct RoleBinding is created to allow the service account to access the necessary
 resources. If that is not the case, you can create a RoleBinding for the service account to access
 the necessary resources:
@@ -175,35 +211,6 @@ And then apply the configuration:
 kubectl apply -f allow-anonymous-openid.yaml
 ```
 
-Validates tokens against the Kubernetes API server through the OIDC provider:
-```yaml
-server:
-  auth:
-    provider_type: "oauth2_token"
-    config:
-      jwks:
-        uri: "https://kubernetes.default.svc"
-        key_recheck_period: 3600
-      tls_cafile: "/path/to/ca.crt"
-      issuer: "https://kubernetes.default.svc"
-      audience: "https://kubernetes.default.svc"
-```
-
-To find your cluster's audience, run:
-```bash
-kubectl create token default --duration=1h | cut -d. -f2 | base64 -d | jq .aud
-```
-
-For the issuer, you can use the OIDC provider's URL:
-```bash
-kubectl get --raw /.well-known/openid-configuration| jq .issuer
-```
-
-For the tls_cafile, you can use the CA certificate of the OIDC provider:
-```bash
-kubectl config view --minify -o jsonpath='{.clusters[0].cluster.certificate-authority}'
-```
-
 The provider extracts user information from the JWT token:
 - Username from the `sub` claim becomes a role
 - Kubernetes groups become teams

docs/source/distributions/self_hosted_distro/ollama.md

@@ -18,6 +18,7 @@ The `llamastack/distribution-ollama` distribution consists of the following prov
 | agents | `inline::meta-reference` |
 | datasetio | `remote::huggingface`, `inline::localfs` |
 | eval | `inline::meta-reference` |
+| files | `inline::localfs` |
 | inference | `remote::ollama` |
 | post_training | `inline::huggingface` |
 | safety | `inline::llama-guard` |

docs/source/providers/vector_io/sqlite-vec.md

@@ -66,25 +66,126 @@ To use sqlite-vec in your Llama Stack project, follow these steps:
 2. Configure your Llama Stack project to use SQLite-Vec.
 3. Start storing and querying vectors.
 
-## Supported Search Modes
+The SQLite-vec provider supports three search modes:
 
-The sqlite-vec provider supports both vector-based and keyword-based (full-text) search modes.
-
-When using the RAGTool interface, you can specify the desired search behavior via the `mode` parameter in
-`RAGQueryConfig`. For example:
+1. **Vector Search** (`mode="vector"`): Performs pure vector similarity search using the embeddings.
+2. **Keyword Search** (`mode="keyword"`): Performs full-text search using SQLite's FTS5.
+3. **Hybrid Search** (`mode="hybrid"`): Combines both vector and keyword search for better results. First performs keyword search to get candidate matches, then applies vector similarity search on those candidates.
 
+Example with hybrid search:
 ```python
-from llama_stack.apis.tool_runtime.rag import RAGQueryConfig
+response = await vector_io.query_chunks(
+    vector_db_id="my_db",
+    query="your query here",
+    params={"mode": "hybrid", "max_chunks": 3, "score_threshold": 0.7},
+)
 
-query_config = RAGQueryConfig(max_chunks=6, mode="vector")
+# Using RRF ranker
+response = await vector_io.query_chunks(
+    vector_db_id="my_db",
+    query="your query here",
+    params={
+        "mode": "hybrid",
+        "max_chunks": 3,
+        "score_threshold": 0.7,
+        "ranker": {"type": "rrf", "impact_factor": 60.0},
+    },
+)
 
-results = client.tool_runtime.rag_tool.query(
-    vector_db_ids=[vector_db_id],
-    content="what is torchtune",
-    query_config=query_config,
+# Using weighted ranker
+response = await vector_io.query_chunks(
+    vector_db_id="my_db",
+    query="your query here",
+    params={
+        "mode": "hybrid",
+        "max_chunks": 3,
+        "score_threshold": 0.7,
+        "ranker": {"type": "weighted", "alpha": 0.7},  # 70% vector, 30% keyword
+    },
 )
 ```
 
+Example with explicit vector search:
+```python
+response = await vector_io.query_chunks(
+    vector_db_id="my_db",
+    query="your query here",
+    params={"mode": "vector", "max_chunks": 3, "score_threshold": 0.7},
+)
+```
+
+Example with keyword search:
+```python
+response = await vector_io.query_chunks(
+    vector_db_id="my_db",
+    query="your query here",
+    params={"mode": "keyword", "max_chunks": 3, "score_threshold": 0.7},
+)
+```
+
+## Supported Search Modes
+
+The SQLite vector store supports three search modes:
+
+1. **Vector Search** (`mode="vector"`): Uses vector similarity to find relevant chunks
+2. **Keyword Search** (`mode="keyword"`): Uses keyword matching to find relevant chunks
+3. **Hybrid Search** (`mode="hybrid"`): Combines both vector and keyword scores using a ranker
+
+### Hybrid Search
+
+Hybrid search combines the strengths of both vector and keyword search by:
+- Computing vector similarity scores
+- Computing keyword match scores
+- Using a ranker to combine these scores
+
+Two ranker types are supported:
+
+1. **RRF (Reciprocal Rank Fusion)**:
+   - Combines ranks from both vector and keyword results
+   - Uses an impact factor (default: 60.0) to control the weight of higher-ranked results
+   - Good for balancing between vector and keyword results
+   - The default impact factor of 60.0 comes from the original RRF paper by Cormack et al. (2009) [^1], which found this value to provide optimal performance across various retrieval tasks
+
+2. **Weighted**:
+   - Linearly combines normalized vector and keyword scores
+   - Uses an alpha parameter (0-1) to control the blend:
+     - alpha=0: Only use keyword scores
+     - alpha=1: Only use vector scores
+     - alpha=0.5: Equal weight to both (default)
+
+Example using RAGQueryConfig with different search modes:
+
+```python
+from llama_stack.apis.tools import RAGQueryConfig, RRFRanker, WeightedRanker
+
+# Vector search
+config = RAGQueryConfig(mode="vector", max_chunks=5)
+
+# Keyword search
+config = RAGQueryConfig(mode="keyword", max_chunks=5)
+
+# Hybrid search with custom RRF ranker
+config = RAGQueryConfig(
+    mode="hybrid",
+    max_chunks=5,
+    ranker=RRFRanker(impact_factor=50.0),  # Custom impact factor
+)
+
+# Hybrid search with weighted ranker
+config = RAGQueryConfig(
+    mode="hybrid",
+    max_chunks=5,
+    ranker=WeightedRanker(alpha=0.7),  # 70% vector, 30% keyword
+)
+
+# Hybrid search with default RRF ranker
+config = RAGQueryConfig(
+    mode="hybrid", max_chunks=5
+)  # Will use RRF with impact_factor=60.0
+```
+
+Note: The ranker configuration is only used in hybrid mode. For vector or keyword modes, the ranker parameter is ignored.
+
 ## Installation
 
 You can install SQLite-Vec using pip:
@@ -96,3 +197,5 @@ pip install sqlite-vec
 ## Documentation
 
 See [sqlite-vec's GitHub repo](https://github.com/asg017/sqlite-vec/tree/main) for more details about sqlite-vec in general.
+
+[^1]: Cormack, G. V., Clarke, C. L., & Buettcher, S. (2009). [Reciprocal rank fusion outperforms condorcet and individual rank learning methods](https://dl.acm.org/doi/10.1145/1571941.1572114). In Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval (pp. 758-759).