phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 12:07:34 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

api and provider codegen fixes

Browse source
This commit is contained in:
Alexey Rybak 2025-09-23 09:25:57 -07:00
parent dcc065933e
commit 293d40f91c
3 changed files with 9 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/providers/registry/vector_io.py
View file

@ -410,7 +410,7 @@ There are three implementations of search for PGVectoIndex available:
- 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
- Eg. SQL query: SELECT document, embedding &lt;=&gt; %s::vector AS distance FROM table ORDER BY distance
-Characteristics:
- Semantic understanding - finds documents similar in meaning even if they don't share keywords