File size: 1,167 Bytes
9bd9e22
3f4ffb7
fad2247
c32bf6e
2cc8ae2
0e01434
2cc8ae2
 
51456ff
2cc8ae2
 
42b1ea0
 
fad2247
 
 
 
 
 
 
 
 
 
 
51456ff
fad2247
2cc8ae2
fad2247
 
 
 
 
 
 
 
 
 
 
 
db1ad09
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
from langchain_community.embeddings import HuggingFaceEmbeddings, HuggingFaceInferenceAPIEmbeddings
from langchain_community.vectorstores import Chroma, Qdrant
from qdrant_client import QdrantClient
from qdrant_client.models import Distance, VectorParams
from dotenv import load_dotenv
import os

provider_retrieval_model = "HF"
embeddingmodel = "sentence-transformers/all-MiniLM-l6-v2"
load_dotenv()
HF_Token = os.environ.get("HF_TOKEN")
client_path = "./vectorstore/"
collection_name = "collection"
provider_retrieval_model = "HF"

def create_vectorstore(docs):
    
    if provider_retrieval_model == "HF":
      qdrantClient = QdrantClient(path=client_path, prefer_grpc=True)
    
      embeddings = HuggingFaceInferenceAPIEmbeddings(
          api_key=HF_Token, model_name=embeddingmodel
      )
    
      dim = 384
    

    
    qdrantClient.create_collection(
        collection_name=collection_name,
        vectors_config=VectorParams(size=dim, distance=Distance.COSINE),
    )
    
    vectorstore = Qdrant(
        client=qdrantClient,
        collection_name=collection_name,
        embeddings=embeddings,
    )
    
    vectorstore.add_documents(docs)