did it work?

App/Embedding/utils/Initialize.py

@@ -1,6 +1,6 @@
 from langchain.embeddings import HuggingFaceEmbeddings
 from langchain.docstore.document import Document
-from langchain.vectorstores import Pinecone
+from langchain_pinecone import PineconeVectorStore
 from pinecone import ServerlessSpec
 import pinecone
 import os
@@ -18,28 +18,29 @@ def initDocument():
     model_name = "thenlper/gte-base"
     embeddings = HuggingFaceEmbeddings(model_name=model_name)
 
+    pc = pinecone.Pinecone(api_key=PINECONE_API_KEY, environment=PINECONE_ENV)
+    
     try:
-        pc=pinecone.Pinecone(api_key=PINECONE_API_KEY, environment=PINECONE_ENV)
-        vector_index = pc.Index(index_name)
-    except:
-        pc.create_index(name=index_name,
-        dimension=768,
-        metric="cosine",
-        spec=ServerlessSpec(cloud="aws", region="us-east-1")
+        index = pc.Index(index_name)
+    except pinecone.core.client.exceptions.NotFoundException:
+        pc.create_index(
+            name=index_name,
+            dimension=768,
+            metric="cosine",
+            spec=ServerlessSpec(cloud="aws", region="us-east-1")
         )
-    
-
-    #docsearch = Pinecone.from_existing_index(index_name, embeddings)
+        index = pc.Index(index_name)
 
-    return pc
+    vector_store = PineconeVectorStore(index=index, embedding=embeddings)
+    return vector_store
 
 
 
 
 async def delete_documents(task_id):
-    docsearch=initDocument()
+    vector_store = initDocument()
 
-    docsearch.delete(
+    vector_store.delete(
         filter={
             "task_id": {"$eq": task_id},
         }
@@ -68,12 +69,12 @@ def generateChunks(chunks, task_id, n=100):
 
 
 def search(query: str, task_id: str):
-    docsearch=initDocument()
+    vector_store = initDocument()
 
     filtering_conditions = {
             "task_id": {"$eq": task_id},
         }
-    data =docsearch.similarity_search(query, k=3, filter=filtering_conditions)
+    data =vector_store.similarity_search(query, k=3, filter=filtering_conditions)
     return [
         {"text": d.page_content, "start": d.metadata["start"], "end": d.metadata["end"]}
         for d in data
@@ -82,8 +83,8 @@ def search(query: str, task_id: str):
 
 
 def encode(temp: list[Document]):
-    docsearch=initDocument()
-    docsearch.add_documents(temp)
+    vector_store = initDocument()
+    vector_store.add_documents(temp)
     # return  embeddings.embed_documents(texts = [d.page_content for d in temp])
 
 

requirements.txt

@@ -1,6 +1,6 @@
 asyncpg==0.27.0
 databases==0.7.0
-fastapi==0.92.0
+fastapi
 orm==0.3.
 transformers
 faster-whisper
@@ -13,7 +13,7 @@ typesystem==0.3.1
 Werkzeug==2.2.2
 passlib                # for password hashing
 pydantic[email]
-uvicorn==0.21.1
+uvicorn
 ujson
 yt-dlp
 psutil
@@ -27,12 +27,12 @@ telethon
 fastapi-jwt-auth
 bcrypt
 aiomysql
-
+langchain-pinecone
 asyncpg
 sentence_transformers
 google-generativeai
 openai
 tiktoken
-langchain==0.0.336
+langchain
 mysqlclient
-pinecone-client[grpc]==3.1.0
+pinecone-client[grpc]