first commit, Naive RAG implemented

app.py

@@ -1,28 +1,83 @@
+import os
 from flask import Flask, request, jsonify
 import logging
+import openai
+from llama_index.core import Settings
+from llama_index.llms.openai import OpenAI
+from llama_index.vector_stores.pinecone import PineconeVectorStore
+from llama_index.core import VectorStoreIndex, StorageContext
+from dotenv import load_dotenv
+from pinecone import Pinecone  # Correct import
+
+load_dotenv()
 
 app = Flask(__name__)
+app.debug = True
 
 # Configure logging
 logging.basicConfig(level=logging.DEBUG)
 
-@app.route('/')
-def hello_world():
-    return 'Hello, World!'
+# Set up OpenAI API key
+openai.api_key = os.getenv('OPENAI_API_KEY')
+
+# Initialize Pinecone
+pc = Pinecone(
+    api_key=os.getenv('PINECONE_API_KEY')
+)
+
+# Name of your existing Pinecone index
+PINECONE_INDEX_NAME = os.getenv('PINECONE_INDEX')
+
+# Initialize Pinecone index
+pinecone_index = pc.Index(PINECONE_INDEX_NAME)
+
+# Set up LlamaIndex global settings
+Settings.llm = OpenAI(
+    model=os.getenv('OPENAI_MODEL', 'gpt-3.5-turbo'),  # Default to 'gpt-3.5-turbo' if not specified
+    temperature=0
+)
+
+# Set up Pinecone Vector Store
+vector_store = PineconeVectorStore(
+    pinecone_index=pinecone_index,
+    namespace=None  # Specify a namespace if used during ingestion
+)
+
+# Create Storage Context with the Vector Store
+storage_context = StorageContext.from_defaults(vector_store=vector_store)
+
+# Initialize LlamaIndex with the existing Pinecone vector store
+index = VectorStoreIndex.from_vector_store(
+    vector_store=vector_store,
+    storage_context=storage_context
+)
 
 @app.route('/run/predict', methods=['POST'])
 def predict():
     try:
         data = request.json
         app.logger.debug(f"Received data: {data}")
-        response = {
-            "data": data
-        }
-        return jsonify(response)
+
+        if not data:
+            app.logger.error("No data provided in the request.")
+            return jsonify({'error': 'No data provided.'}), 400
+
+        user_query = data.get('query')
+
+        if not user_query:
+            app.logger.error("No query provided in the request.")
+            return jsonify({'error': 'No query provided.'}), 400
+
+        # Perform the query using LlamaIndex
+        response = index.as_query_engine().query(user_query)
+        # app.logger.debug(f"Generated response: {response}")
+
+        return jsonify({'response': str(response)})
+
     except Exception as e:
         app.logger.error(f"Error processing request: {e}")
-        return jsonify({"error": "An error occurred"}), 500
+        return jsonify({"error": "An error occurred while processing the request"}), 500
 
 if __name__ == '__main__':
     from os import environ
-    app.run(host='0.0.0.0', port=int(environ.get('PORT', 5000)))
+    app.run(host='0.0.0.0', port=int(environ.get('PORT', 7860)))

requirements.txt

@@ -1,9 +1,85 @@
+aiohappyeyeballs==2.4.0
+aiohttp==3.10.5
+aiosignal==1.3.1
+annotated-types==0.7.0
+anyio==4.5.0
+async-timeout==4.0.3
+attrs==24.2.0
+beautifulsoup4==4.12.3
 blinker==1.8.2
+certifi==2024.8.30
+charset-normalizer==3.3.2
 click==8.1.7
+dataclasses-json==0.6.7
+Deprecated==1.2.14
+dirtyjson==1.0.8
+distro==1.9.0
+exceptiongroup==1.2.2
 Flask==3.0.3
+frozenlist==1.4.1
+fsspec==2024.9.0
+greenlet==3.1.0
 gunicorn==23.0.0
+h11==0.14.0
+httpcore==1.0.5
+httpx==0.27.2
+idna==3.10
 itsdangerous==2.2.0
 Jinja2==3.1.4
+jiter==0.5.0
+joblib==1.4.2
+llama-cloud==0.0.17
+llama-index==0.11.10
+llama-index-agent-openai==0.3.3
+llama-index-cli==0.3.1
+llama-index-core==0.11.10
+llama-index-embeddings-openai==0.2.5
+llama-index-indices-managed-llama-cloud==0.3.1
+llama-index-legacy==0.9.48.post3
+llama-index-llms-openai==0.2.9
+llama-index-multi-modal-llms-openai==0.2.1
+llama-index-program-openai==0.2.0
+llama-index-question-gen-openai==0.2.0
+llama-index-readers-file==0.2.2
+llama-index-readers-llama-parse==0.3.0
+llama-index-vector-stores-pinecone==0.2.1
+llama-parse==0.5.6
 MarkupSafe==2.1.5
+marshmallow==3.22.0
+multidict==6.1.0
+mypy-extensions==1.0.0
+nest-asyncio==1.6.0
+networkx==3.3
+nltk==3.9.1
+numpy==1.26.4
+openai==1.46.1
 packaging==24.1
+pandas==2.2.2
+pillow==10.4.0
+pinecone-client==5.0.1
+pinecone-plugin-inference==1.1.0
+pinecone-plugin-interface==0.0.7
+pydantic==2.9.2
+pydantic_core==2.23.4
+pypdf==4.3.1
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+pytz==2024.2
+PyYAML==6.0.2
+regex==2024.9.11
+requests==2.32.3
+six==1.16.0
+sniffio==1.3.1
+soupsieve==2.6
+SQLAlchemy==2.0.35
+striprtf==0.0.26
+tenacity==8.5.0
+tiktoken==0.7.0
+tqdm==4.66.5
+typing-inspect==0.9.0
+typing_extensions==4.12.2
+tzdata==2024.1
+urllib3==2.2.3
 Werkzeug==3.0.4
+wrapt==1.16.0
+yarl==1.11.1