feat (RAG): Implement configurable search mode in RAGQueryConfig

Signed-off-by: Varsha Prasad Narsing <varshaprasad96@gmail.com>

docs/_static/llama-stack-spec.html

@@ -11601,6 +11601,7 @@
                     },
                     "max_chunks": {
                         "type": "integer",
+<<<<<<< HEAD
                         "default": 5,
                         "description": "Maximum number of chunks to retrieve."
                     },
@@ -11608,6 +11609,12 @@
                         "type": "string",
                         "default": "Result {index}\nContent: {chunk.content}\nMetadata: {metadata}\n",
                         "description": "Template for formatting each retrieved chunk in the context. Available placeholders: {index} (1-based chunk ordinal), {chunk.content} (chunk content string), {metadata} (chunk metadata dict). Default: \"Result {index}\\nContent: {chunk.content}\\nMetadata: {metadata}\\n\""
+=======
+                        "default": 5
+                    },
+                    "mode": {
+                        "type": "string"
+>>>>>>> 1a0433d2 (feat (RAG): Implement configurable search mode in RAGQueryConfig)
                     }
                 },
                 "additionalProperties": false,

docs/_static/llama-stack-spec.yaml

@@ -8072,6 +8072,7 @@ components:
         max_chunks:
           type: integer
           default: 5
+<<<<<<< HEAD
           description: Maximum number of chunks to retrieve.
         chunk_template:
           type: string
@@ -8086,6 +8087,10 @@ components:
             placeholders: {index} (1-based chunk ordinal), {chunk.content} (chunk
             content string), {metadata} (chunk metadata dict). Default: "Result {index}\nContent:
             {chunk.content}\nMetadata: {metadata}\n"
+=======
+        mode:
+          type: string
+>>>>>>> 1a0433d2 (feat (RAG): Implement configurable search mode in RAGQueryConfig)
       additionalProperties: false
       required:
         - query_generator_config

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

@@ -66,6 +66,25 @@ 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 both vector-based and keyword-based (full-text) search modes.
+
+When using the RAGTool interface, you can specify the desired search behavior via the search_mode parameter in
+`RAGQueryConfig`. For example:
+
+```python
+from llama_stack.apis.tool_runtime.rag import RAGQueryConfig
+
+query_config = RAGQueryConfig(max_chunks=6, mode="vector")
+
+results = client.tool_runtime.rag_tool.query(
+    vector_db_ids=[vector_db_id],
+    content="what is torchtune",
+    query_config=query_config,
+)
+```
+
 ## Installation
 
 You can install SQLite-Vec using pip: