ok

App/Embedding/utils/Initialize.py

@@ -50,6 +50,24 @@ def generateChunks(chunks, task_id, n=100):
 
 
 def search(query: str, task_id: str):
+    # get api key from app.pinecone.io
+    PINECONE_API_KEY = os.environ.get("PINECONE_API_KEY")
+    # find your environment next to the api key in pinecone console
+    PINECONE_ENV = os.environ.get("PINECONE_ENVIRONMENT")
+
+
+    index_name = "transcript-bits"
+    model_name = "thenlper/gte-base"
+    embeddings = HuggingFaceEmbeddings(model_name=model_name)
+
+
+    pinecone.init(api_key=PINECONE_API_KEY, environment=PINECONE_ENV)
+    vector_index = pinecone.Index(index_name=index_name)
+    docsearch = Pinecone.from_existing_index(index_name, embeddings)
+
+
+
+
     filtering_conditions = {
             "task_id": {"$eq": "task_id"},
         }
@@ -62,5 +80,19 @@ def search(query: str, task_id: str):
 
 
 def encode(temp: list[Document]):
+    PINECONE_API_KEY = os.environ.get("PINECONE_API_KEY")
+    # find your environment next to the api key in pinecone console
+    PINECONE_ENV = os.environ.get("PINECONE_ENVIRONMENT")
+
+
+    index_name = "transcript-bits"
+    model_name = "thenlper/gte-base"
+    embeddings = HuggingFaceEmbeddings(model_name=model_name)
+
+
+    pinecone.init(api_key=PINECONE_API_KEY, environment=PINECONE_ENV)
+    vector_index = pinecone.Index(index_name=index_name)
+    docsearch = Pinecone.from_existing_index(index_name, embeddings)
+
     docsearch.add_documents(temp)
     # return  embeddings.embed_documents(texts = [d.page_content for d in temp])