File size: 2,814 Bytes
0181645 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 |
# qdrant_utils.py contains utility functions to interact with Qdrant, a vector similarity search engine.
from qdrant_client import QdrantClient
from qdrant_client.http import models
import os
import logging
import uuid
# Initialize logging
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
qdrant_client = QdrantClient(
url=os.getenv('QDRANT_URL'),
api_key=os.getenv('QDRANT_API_KEY')
)
def create_collection_if_not_exists(collection_name, vector_size):
try:
# Check if collection exists
collections = qdrant_client.get_collections().collections
if not any(collection.name == collection_name for collection in collections):
# Create the collection if it doesn't exist
qdrant_client.create_collection(
collection_name=collection_name,
vectors_config=models.VectorParams(size=vector_size, distance=models.Distance.COSINE)
)
logging.info(f"Created new collection: {collection_name}")
else:
logging.info(f"Collection {collection_name} already exists")
except Exception as e:
logging.error(f"Error creating collection: {str(e)}")
raise
def store_embeddings(chunks, embeddings, user_id, data_source_id, file_id, organization_id, s3_bucket_key, total_tokens):
try:
collection_name = "embed" # Name of the collection in Qdrant
vector_size = len(embeddings[0])
# Ensure the collection exists
create_collection_if_not_exists(collection_name, vector_size)
# Prepare points for Qdrant
points = []
for i, (chunk, embedding) in enumerate(zip(chunks, embeddings)):
chunk_id = str(uuid.uuid4()) # Generate a unique ID for each chunk
points.append(
models.PointStruct(
id=chunk_id,
vector=embedding.tolist(), # Convert numpy array to list
payload={
"user_id": user_id,
"data_source_id": data_source_id,
"file_id": file_id,
"organization_id": organization_id,
"chunk_index": i,
"chunk_text": chunk,
"s3_bucket_key": s3_bucket_key,
"total_tokens": total_tokens
}
)
)
# Store embeddings in Qdrant
qdrant_client.upsert(
collection_name=collection_name,
points=points
)
logging.info(f"Successfully stored {len(points)} embeddings")
except Exception as e:
logging.error(f"Error storing embeddings in Qdrant: {str(e)}")
raise |