phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-17 10:28:11 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: Implement hybrid search in SQLite-vec

Browse source 
Signed-off-by: Varsha Prasad Narsing <varshaprasad96@gmail.com>
This commit is contained in:
Varsha Prasad Narsing 2025-05-29 14:32:54 -07:00
parent 941f505eb0
commit eab85a7121
13 changed files with 335 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/apis/tools/rag_tool.py
View file

@ -76,7 +76,7 @@ class RAGQueryConfig(BaseModel):
:param chunk_template: 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"
:param mode: Search mode for retrieval—either "vector" or "keyword". Default "vector".
:param mode: Search mode for retrieval—either "vector", "keyword", or "hybrid". Default "vector".
"""
# This config defines how a query is generated using the messages