Add application file

Dockerfile

@@ -0,0 +1,12 @@
+FROM python:3.11-slim
+
+WORKDIR /
+
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY . .
+
+EXPOSE 7860
+
+CMD ["uvicorn", "app.api:app", "--host", "0.0.0.0", "--port", "7860"]

api.py

@@ -0,0 +1,130 @@
+from flask import Flask, request, jsonify
+from flask_cors import CORS
+import sys
+import os
+
+# Add the src/python directory to the path so we can import our modules
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
+
+from src.python.vector_store import VectorStore
+from backend.embedder_wrapper import SyncEmbedder
+from src.python.config import OPENAI_API_KEY, QDRANT_URL, QDRANT_API_KEY, COLLECTION_NAME
+import logging
+
+# Configure logging
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+app = Flask(__name__)
+CORS(app, origins=["http://localhost:3000", "http://localhost:5000", "http://127.0.0.1:3000", "http://127.0.0.1:5000"], supports_credentials=True, allow_headers=["Content-Type", "Authorization"])
+
+# Initialize our components
+try:
+    vector_store = VectorStore()
+    embedder = SyncEmbedder()
+    logger.info("Service initialized successfully")
+    logger.info(f"Connected to Qdrant at: {QDRANT_URL}")
+except Exception as e:
+    logger.error(f"Failed to initialize services: {str(e)}")
+    raise
+
+@app.route('/chat', methods=['POST'])
+def chat():
+    """
+    Chat endpoint that takes user query and returns a response based on RAG
+    Expected JSON format: {"message": "user question"}
+    """
+    try:
+        data = request.get_json()
+
+        if not data or 'message' not in data:
+            return jsonify({'error': 'Message field is required'}), 400
+
+        user_message = data['message']
+
+        # Create embedding for the user message
+        try:
+            query_embedding = embedder.embed_text(user_message)
+        except Exception as e:
+            logger.error(f"Error creating embedding: {str(e)}")
+            return jsonify({'error': f'Error processing your message: {str(e)}'}), 500
+
+        # Search for similar documents in the vector store
+        try:
+            similar_docs = vector_store.search_similar(query_embedding, top_k=5)
+        except Exception as e:
+            logger.error(f"Error searching for documents: {str(e)}")
+            return jsonify({'error': f'Error retrieving documents: {str(e)}'}), 500
+
+        # Format the retrieved documents as context
+        context = "\n".join([doc['content'] for doc in similar_docs])
+
+        # Prepare the prompt for the LLM
+        if context.strip() == "":
+            # If no context is found, let the model respond without it
+            prompt = f"""
+            Please answer the following question. If you don't know the answer, please say so.
+
+            Question: {user_message}
+            Answer:
+            """
+        else:
+            prompt = f"""
+            Answer the question based on the context provided.
+            If the answer is not in the context, say "I don't have enough information to answer that question."
+
+            Context: {context}
+
+            Question: {user_message}
+            Answer:
+            """
+
+        # Use OpenAI API to generate the response
+        try:
+            from openai import OpenAI
+
+            client = OpenAI(api_key=OPENAI_API_KEY)
+
+            response = client.chat.completions.create(
+                model="gpt-3.5-turbo",
+                messages=[{"role": "user", "content": prompt}],
+                temperature=0.3,
+                max_tokens=500
+            )
+
+            bot_response = response.choices[0].message.content.strip()
+        except Exception as e:
+            logger.error(f"Error calling LLM: {str(e)}")
+            return jsonify({'error': f'Error generating response: {str(e)}'}), 500
+
+        return jsonify({
+            'response': bot_response,
+            'sources': [doc.get('source', '') for doc in similar_docs],
+            'scores': [doc.get('score', 0.0) for doc in similar_docs],
+            'retrieved_context': context
+        })
+
+    except Exception as e:
+        logger.error(f"Unexpected error in chat endpoint: {str(e)}")
+        return jsonify({'error': str(e)}), 500
+
+
+@app.route('/health', methods=['GET'])
+def health():
+    """Health check endpoint"""
+    return jsonify({'status': 'healthy'})
+
+
+@app.route('/documents/count', methods=['GET'])
+def document_count():
+    """Get the count of documents in the vector store"""
+    try:
+        count = vector_store.get_all_documents_count()
+        return jsonify({'count': count})
+    except Exception as e:
+        logger.error(f"Error getting document count: {str(e)}")
+        return jsonify({'error': str(e)}), 500
+
+
+if __name__ == '__main__':
+    app.run(debug=True, host='0.0.0.0', port=5000)

requirements.txt

@@ -0,0 +1,8 @@
+Flask>=2.3.0
+Flask-CORS>=4.0.0
+openai>=1.0.0
+qdrant-client>=1.6.0
+python-dotenv>=1.0.0
+tiktoken>=0.5.0
+langchain>=0.0.335
+langchain-openai>=0.0.5