Update app/main.py

app/main.py

@@ -1,82 +1,82 @@
-from twilio.rest import Client
-import yaml
-import json
-import os
-
-import yaml
-import json
-from langchain.embeddings import OpenAIEmbeddings
-from langchain_community.vectorstores import Chroma
-from helper import retrieve_relevant_context, generate_response_with_context
-
-# Load relevant API Keys
-file_path = './Config/API_KEYS.yml'
-
-with open(file_path, 'r') as file:
-    api_keys = yaml.safe_load(file)
-
-
-# Extract openai username and key
-openai_key = api_keys['OPEN_AI']['Key']
-
-os.environ["OPENAI_API_KEY"] = openai_key
-
-
-
-# Extract openai username and key
-account_sid = api_keys['TWILIO']['account_sid']
-auth_token = api_keys['TWILIO']['auth_token']
-
-account_sid = account_sid
-auth_token = auth_token
-
-# Define the persist directory
-persist_directory = './vector_db/chroma_v01'
-
-# Initialize the embeddings model
-embedding_model = OpenAIEmbeddings()
-
-### Vectorstores
-from langchain_community.vectorstores import Chroma
-
-# Load the Chroma vector store
-vectordb = Chroma(persist_directory=persist_directory, embedding_function=embedding_model)
-
-
-#setup Twilio client
-client = Client(account_sid, auth_token)
-
-
-from flask import Flask, request, redirect
-from twilio.twiml.messaging_response import MessagingResponse
-print("flask app is running")
-app = Flask(__name__)
-
-@app.route("/whatsapp", methods=['GET', 'POST'])
-def incoming_sms():
-    """Send a dynamic reply to an incoming text message"""
-    # Get the message the user sent our Twilio number
-    body = request.values.get('Body', None)
-    print("body :",body)
-    
-    ##### Process incoming text #############
-    incoming_msg = body.strip()
-    if not incoming_msg:
-        return str(MessagingResponse())
-
-    # Generate response using the RAG-powered system
-    retrieved_texts = retrieve_relevant_context(vectordb, incoming_msg)
-    context = "\n".join(retrieved_texts)
-    response = generate_response_with_context(incoming_msg, context)
-    print("response :",response)
-    ##### Process incoming text Done #############
-    
-    
-    # Start our TwiML response
-    resp = MessagingResponse()
-    print("TwiML resp :", resp)
-    resp.message(response)
-    return str(resp)
-
-if __name__ == "__main__":
-    app.run(port=5000, debug=True)
+from twilio.rest import Client
+import yaml
+import json
+import os
+
+import yaml
+import json
+from langchain.embeddings import OpenAIEmbeddings
+from langchain_community.vectorstores import Chroma
+from helper import retrieve_relevant_context, generate_response_with_context
+
+# Load relevant API Keys
+file_path = '../Config/API_KEYS.yml'
+
+with open(file_path, 'r') as file:
+    api_keys = yaml.safe_load(file)
+
+
+# Extract openai username and key
+openai_key = api_keys['OPEN_AI']['Key']
+
+os.environ["OPENAI_API_KEY"] = openai_key
+
+
+
+# Extract openai username and key
+account_sid = api_keys['TWILIO']['account_sid']
+auth_token = api_keys['TWILIO']['auth_token']
+
+account_sid = account_sid
+auth_token = auth_token
+
+# Define the persist directory
+persist_directory = '../vector_db/chroma_v01'
+
+# Initialize the embeddings model
+embedding_model = OpenAIEmbeddings()
+
+### Vectorstores
+from langchain_community.vectorstores import Chroma
+
+# Load the Chroma vector store
+vectordb = Chroma(persist_directory=persist_directory, embedding_function=embedding_model)
+
+
+#setup Twilio client
+client = Client(account_sid, auth_token)
+
+
+from flask import Flask, request, redirect
+from twilio.twiml.messaging_response import MessagingResponse
+print("flask app is running")
+app = Flask(__name__)
+
+@app.route("/whatsapp", methods=['GET', 'POST'])
+def incoming_sms():
+    """Send a dynamic reply to an incoming text message"""
+    # Get the message the user sent our Twilio number
+    body = request.values.get('Body', None)
+    print("body :",body)
+    
+    ##### Process incoming text #############
+    incoming_msg = body.strip()
+    if not incoming_msg:
+        return str(MessagingResponse())
+
+    # Generate response using the RAG-powered system
+    retrieved_texts = retrieve_relevant_context(vectordb, incoming_msg)
+    context = "\n".join(retrieved_texts)
+    response = generate_response_with_context(incoming_msg, context)
+    print("response :",response)
+    ##### Process incoming text Done #############
+    
+    
+    # Start our TwiML response
+    resp = MessagingResponse()
+    print("TwiML resp :", resp)
+    resp.message(response)
+    return str(resp)
+
+if __name__ == "__main__":
+    app.run(port=5000, debug=True)