mirror of
https://github.com/QuivrHQ/quivr.git
synced 2024-12-30 02:22:13 +03:00
4a305a854e
# 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):
55 lines
1.7 KiB
Python
55 lines
1.7 KiB
Python
from uuid import UUID
|
|
|
|
from attr import dataclass
|
|
from logger import get_logger
|
|
from models.settings import get_embeddings, get_supabase_client
|
|
from repository.files.generate_file_signed_url import generate_file_signed_url
|
|
from vectorstore.supabase import CustomSupabaseVectorStore
|
|
|
|
logger = get_logger(__name__)
|
|
|
|
|
|
@dataclass
|
|
class DocumentAnswer:
|
|
file_name: str
|
|
file_sha1: str
|
|
file_size: int
|
|
file_url: str = ""
|
|
file_id: str = ""
|
|
file_similarity: float = 0.0
|
|
|
|
|
|
def get_question_context_from_brain(brain_id: UUID, question: str) -> str:
|
|
# TODO: Move to AnswerGenerator service
|
|
supabase_client = get_supabase_client()
|
|
embeddings = get_embeddings()
|
|
|
|
vector_store = CustomSupabaseVectorStore(
|
|
supabase_client,
|
|
embeddings,
|
|
table_name="vectors",
|
|
brain_id=str(brain_id),
|
|
)
|
|
documents = vector_store.similarity_search(question, k=20, threshold=0.8)
|
|
|
|
answers = []
|
|
file_sha1s = []
|
|
for document in documents:
|
|
if document.metadata["file_sha1"] not in file_sha1s:
|
|
file_sha1s.append(document.metadata["file_sha1"])
|
|
file_path_in_storage = f"{brain_id}/{document.metadata['file_name']}"
|
|
answers.append(
|
|
DocumentAnswer(
|
|
file_name=document.metadata["file_name"],
|
|
file_sha1=document.metadata["file_sha1"],
|
|
file_size=document.metadata["file_size"],
|
|
file_id=document.metadata["id"],
|
|
file_similarity=document.metadata["similarity"],
|
|
file_url=generate_file_signed_url(file_path_in_storage).get(
|
|
"signedURL", ""
|
|
),
|
|
),
|
|
)
|
|
|
|
return answers
|