phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-12 12:06:04 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

chore: Rename RagTool FileSearchTool

Browse source 
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
This commit is contained in:
Francisco Javier Arceo 2025-10-24 16:52:58 -04:00
parent 4566eebe05
commit 2d9163529a
288 changed files with 16985 additions and 2071 deletions
Download patch file Download diff file Expand all files Collapse all files

14
llama_stack/providers/registry/vector_io.py
View file

@ -241,33 +241,33 @@ Two ranker types are supported:
- alpha=1: Only use vector scores
- alpha=0.5: Equal weight to both (default)
Example using RAGQueryConfig with different search modes:
Example using FileSearchConfig with different search modes:
```python
from llama_stack.apis.tools import RAGQueryConfig, RRFRanker, WeightedRanker
from llama_stack.apis.tools import FileSearchConfig, RRFRanker, WeightedRanker
# Vector search
config = RAGQueryConfig(mode="vector", max_chunks=5)
config = FileSearchConfig(mode="vector", max_chunks=5)
# Keyword search
config = RAGQueryConfig(mode="keyword", max_chunks=5)
config = FileSearchConfig(mode="keyword", max_chunks=5)
# Hybrid search with custom RRF ranker
config = RAGQueryConfig(
config = FileSearchConfig(
mode="hybrid",
max_chunks=5,
ranker=RRFRanker(impact_factor=50.0), # Custom impact factor
)
# Hybrid search with weighted ranker
config = RAGQueryConfig(
config = FileSearchConfig(
mode="hybrid",
max_chunks=5,
ranker=WeightedRanker(alpha=0.7), # 70% vector, 30% keyword
)
# Hybrid search with default RRF ranker
config = RAGQueryConfig(
config = FileSearchConfig(
mode="hybrid", max_chunks=5
) # Will use RRF with impact_factor=60.0
```