collection query fix

This commit is contained in:
Jannik Streidl 2024-02-18 09:17:43 +01:00
parent 1846c1e80d
commit bc3dd34d8b

View File

@ -29,11 +29,13 @@ from langchain_community.document_loaders import (
from langchain.text_splitter import RecursiveCharacterTextSplitter from langchain.text_splitter import RecursiveCharacterTextSplitter
from pydantic import BaseModel from pydantic import BaseModel
from typing import Optional from typing import Optional
import uuid import uuid
from utils.misc import calculate_sha256, calculate_sha256_string from utils.misc import calculate_sha256, calculate_sha256_string
from utils.utils import get_current_user, get_admin_user from utils.utils import get_current_user, get_admin_user
from config import UPLOAD_DIR, SENTENCE_TRANSFORMER_EMBED_MODEL, CHROMA_CLIENT, CHUNK_SIZE, CHUNK_OVERLAP from config import UPLOAD_DIR, SENTENCE_TRANSFORMER_EMBED_MODEL, CHROMA_CLIENT, CHUNK_SIZE, CHUNK_OVERLAP
@ -113,7 +115,7 @@ def query_doc(
# if you use docker use the model from the environment variable # if you use docker use the model from the environment variable
collection = CHROMA_CLIENT.get_collection( collection = CHROMA_CLIENT.get_collection(
name=form_data.collection_name, name=form_data.collection_name,
embedding_function=sentence_transformer_ef embedding_function=sentence_transformer_ef,
) )
else: else:
# for local development use the default model # for local development use the default model
@ -193,13 +195,13 @@ def query_collection(
if 'DOCKER_SENTENCE_TRANSFORMER_EMBED_MODEL' in os.environ: if 'DOCKER_SENTENCE_TRANSFORMER_EMBED_MODEL' in os.environ:
# if you use docker use the model from the environment variable # if you use docker use the model from the environment variable
collection = CHROMA_CLIENT.get_collection( collection = CHROMA_CLIENT.get_collection(
name=form_data.collection_name, name=collection_name,
embedding_function=sentence_transformer_ef embedding_function=sentence_transformer_ef,
) )
else: else:
# for local development use the default model # for local development use the default model
collection = CHROMA_CLIENT.get_collection( collection = CHROMA_CLIENT.get_collection(
name=form_data.collection_name, name=collection_name,
) )
result = collection.query( result = collection.query(