Spaces:
Sleeping
Sleeping
import logging | |
from qdrant_client import QdrantClient | |
from qdrant_client.http.models import Filter, FieldCondition | |
class QdrantSearcher: | |
def __init__(self, encoder, qdrant_url, access_token): | |
self.encoder = encoder | |
self.client = QdrantClient(url=qdrant_url, api_key=access_token) | |
def search_documents(self, collection_name, query, user_id, limit=3): | |
logging.info("Starting document search") | |
query_vector = self.encoder.encode(query).tolist() | |
query_filter = Filter(must=[FieldCondition(key="user_id", match={"value": user_id})]) | |
try: | |
hits = self.client.search( | |
collection_name=collection_name, | |
query_vector=query_vector, | |
limit=limit, | |
query_filter=query_filter | |
) | |
except Exception as e: | |
logging.error(f"Error during Qdrant search: {e}") | |
return None, str(e) | |
if not hits: | |
logging.info("No documents found for the given query") | |
return None, "No documents found for the given query." | |
hits_list = [] | |
for hit in hits: | |
hit_info = { | |
"id": hit.id, | |
"score": hit.score, | |
"file_id": hit.payload.get('file_id'), | |
"organization_id": hit.payload.get('organization_id'), | |
"chunk_index": hit.payload.get('chunk_index'), | |
"chunk_text": hit.payload.get('chunk_text'), | |
"s3_bucket_key": hit.payload.get('s3_bucket_key') | |
} | |
hits_list.append(hit_info) | |
logging.info(f"Document search completed with {len(hits_list)} hits") | |
return hits_list, None | |