mirror of
https://github.com/QuivrHQ/quivr.git
synced 2024-12-15 17:43:03 +03:00
36b008e0eb
to return a list of DocumentAnswer objects # Description Please include a summary of the changes and the related issue. Please also include relevant motivation and context. ## Checklist before requesting a review Please delete options that are not relevant. - [ ] My code follows the style guidelines of this project - [ ] I have performed a self-review of my code - [ ] I have commented hard-to-understand areas - [ ] I have ideally added tests that prove my fix is effective or that my feature works - [ ] New and existing unit tests pass locally with my changes - [ ] Any dependent changes have been merged ## Screenshots (if appropriate):
62 lines
1.7 KiB
Python
62 lines
1.7 KiB
Python
from typing import Any, List
|
|
|
|
from langchain.docstore.document import Document
|
|
from langchain.embeddings.base import Embeddings
|
|
from langchain.vectorstores import SupabaseVectorStore
|
|
from supabase.client import Client
|
|
|
|
|
|
class CustomSupabaseVectorStore(SupabaseVectorStore):
|
|
"""A custom vector store that uses the match_vectors table instead of the vectors table."""
|
|
|
|
brain_id: str = "none"
|
|
|
|
def __init__(
|
|
self,
|
|
client: Client,
|
|
embedding: Embeddings,
|
|
table_name: str,
|
|
brain_id: str = "none",
|
|
):
|
|
super().__init__(client, embedding, table_name)
|
|
self.brain_id = brain_id
|
|
|
|
def similarity_search(
|
|
self,
|
|
query: str,
|
|
k: int = 6,
|
|
table: str = "match_vectors",
|
|
threshold: float = 0.5,
|
|
**kwargs: Any
|
|
) -> List[Document]:
|
|
vectors = self._embedding.embed_documents([query])
|
|
query_embedding = vectors[0]
|
|
res = self._client.rpc(
|
|
table,
|
|
{
|
|
"query_embedding": query_embedding,
|
|
"match_count": k,
|
|
"p_brain_id": str(self.brain_id),
|
|
},
|
|
).execute()
|
|
|
|
match_result = [
|
|
(
|
|
Document(
|
|
metadata={
|
|
**search.get("metadata", {}),
|
|
"id": search.get("id", ""),
|
|
"similarity": search.get("similarity", 0.0),
|
|
},
|
|
page_content=search.get("content", ""),
|
|
),
|
|
search.get("similarity", 0.0),
|
|
)
|
|
for search in res.data
|
|
if search.get("content")
|
|
]
|
|
|
|
documents = [doc for doc, _ in match_result]
|
|
|
|
return documents
|