Update app.py

app.py

@@ -6,20 +6,41 @@ from transformers import pipeline
 import numpy as np
 import tempfile
 import openai
-import pinecone  # Added Pinecone import
+from pinecone.grpc import PineconeGRPC as Pinecone  # Corrected Pinecone import
+from pinecone import ServerlessSpec
 import streamlit as st
 from PIL import Image
 from gtts import gTTS 
 from io import BytesIO
+import time  # For delay during index readiness check
 
 # Pinecone and OpenAI setup
-pinecone.init(api_key=os.getenv("PINECONE_API_KEY"), environment=os.getenv("PINECONE_ENVIRONMENT"))  # Initialize Pinecone
-openai.api_key = os.getenv("OpenAI_API")  # Initialize OpenAI
+pinecone_api_key = os.getenv("PINECONE_API_KEY")
+openai.api_key = os.getenv("OPENAI_API_KEY")
 
-# Create Pinecone index if it does not exist
+# Initialize Pinecone client
+pc = Pinecone(api_key=pinecone_api_key)
+
+# Create or retrieve Pinecone index
 index_name = "farming-assistant"
-if index_name not in pinecone.list_indexes():
-    pinecone.create_index(index_name, dimension=1536, metric="cosine")  # Adjust dimension as per embedding model
+dimension = 1536  # Adjust dimension to match OpenAI embeddings
+
+if not pc.has_index(index_name):
+    pc.create_index(
+        name=index_name,
+        dimension=dimension,
+        metric="cosine",
+        spec=ServerlessSpec(
+            cloud='aws',
+            region='us-east-1'
+        )
+    )
+
+# Wait for the index to be ready
+while not pc.describe_index(index_name).status['ready']:
+    time.sleep(1)
+
+index = pc.Index(index_name)  # Corrected method to connect to the index
 
 master_prompt = """
 As a Natural Farming Fertilizers Assistant, you will assist the user with any farming-related question, always willing to answer any question and provide useful organic farming advice in the following format.
@@ -40,8 +61,12 @@ def generate_response(question):
     )["data"][0]["embedding"]
 
     # Query Pinecone for relevant documents
-    index = pinecone.Index(index_name)
-    query_result = index.query(vector=query_embedding, top_k=5, include_metadata=True)
+    query_result = index.query(
+        vector=query_embedding,
+        top_k=5,
+        include_metadata=True,
+        namespace="farming-assistant"
+    )
     
     # Extract relevant information
     contexts = [match["metadata"]["text"] for match in query_result["matches"]]
@@ -58,6 +83,13 @@ def generate_response(question):
 
     return response
 
+def upsert_vectors(vectors):
+    # Upsert vectors into Pinecone index
+    index.upsert(
+        vectors=vectors,
+        namespace="farming-assistant"
+    )
+
 def launch_bot():
     if 'cfg' not in st.session_state:
         questions = list(eval(os.environ['examples']))
@@ -75,7 +107,7 @@ def launch_bot():
 
     # Left side content
     with st.sidebar:
-        image = Image.open('Vectara-logo.png')
+        image = Image.open('Pinecone-logo.png')  # Update with appropriate logo
         st.markdown(f"## Welcome to {cfg.title}\n\n"
                     f"This demo uses an AI organic farming expert and carefully curated library system to achieve greater accuracy in agronomics and agricultural methodology. Created by Copyleft Cultivars, a nonprofit, we hope you enjoy this beta-test early access version.\n\n")