Update app.py

app.py

@@ -1,59 +1,65 @@
-from flask import Flask, request, jsonify
-import logging
 import os
+import logging
+import dotenv
+import yaml
 import zipfile
+import pandas as pd
+from flask import Flask, request, jsonify
 from langchain_community.vectorstores import FAISS
 from langchain_community.document_loaders import CSVLoader
 from langchain_community.embeddings import HuggingFaceEmbeddings
 from langchain.prompts import PromptTemplate
 from langchain.llms import HuggingFaceHub
-import dotenv
-import yaml
-
-# Initialize Flask app
-app = Flask(__name__)
 
 # Load environment variables
 dotenv.load_dotenv()
 
+# Load Config
 def load_config():
     with open("yaml-editor-online.yaml", "r") as f:
-        return yaml.safe_load(f)
+        config = yaml.safe_load(f)
+    return config
 
-hf_token = os.getenv("HUGGING")
 config = load_config()
+hf_token = os.getenv("HUGGING")
+
+# Logging setup
 logging.basicConfig(level=logging.INFO)
-embeddings_model = HuggingFaceEmbeddings(model_name=config["embedding_model"])
 
-# Unzip FAISS index
-zip_file = "faiss_index.zip"
-if os.path.exists(zip_file):
-    with zipfile.ZipFile(zip_file, 'r') as zip_ref:
-        zip_ref.extractall(".")
-    print("Unzipping completed successfully.")
+# Flask App
+app = Flask(__name__)
 
-# Create vector database if not found
 def create_vector_db():
+    """Creates FAISS vector database from disease.csv."""
     try:
+        if not os.path.exists("disease.csv"):
+            logging.error("CSV file not found!")
+            return
+        
+        df = pd.read_csv("disease.csv")
+        if "Disease Information" not in df.columns:
+            logging.error("Column 'Disease Information' not found in CSV!")
+            return
+        
         loader = CSVLoader(file_path="disease.csv", source_column="Disease Information")
         data = loader.load()
+        
+        embeddings_model = HuggingFaceEmbeddings(model_name=config["embedding_model"])
         vectordb = FAISS.from_documents(documents=data, embedding=embeddings_model)
         vectordb.save_local(config["vector_db_path"])
+        
         logging.info("Vector database successfully created and saved.")
     except Exception as e:
         logging.error("Error creating vector database:", exc_info=e)
 
-if not os.path.exists(config["vector_db_path"]):
-    logging.info(f"Vector database not found at {config['vector_db_path']}, creating it now.")
-    create_vector_db()
-
-# Function to handle query requests
 def get_qa_chain(query):
+    """Retrieves relevant documents and generates an answer using LLM."""
     try:
         if not os.path.exists(config["vector_db_path"]):
             logging.error(f"FAISS index path does not exist: {config['vector_db_path']}")
             return "Error: No data found."
 
+        embeddings_model = HuggingFaceEmbeddings(model_name=config["embedding_model"])
         vectordb = FAISS.load_local(
             config["vector_db_path"], embeddings_model, allow_dangerous_deserialization=True
         )
@@ -90,18 +96,24 @@ def get_qa_chain(query):
         logging.error("Error getting response:", exc_info=e)
         return "Sorry, there was an error processing your request."
 
-# Define API route
 @app.route("/query", methods=["POST"])
-def query_api():
-    data = request.get_json()
-    query = data.get("query", "").strip()
-
-    if not query:
-        return jsonify({"error": "Query parameter is required."}), 400
+def query():
+    """API endpoint for answering disease-related queries."""
+    data = request.json
+    user_query = data.get("query", "")
     
-    response = get_qa_chain(query)
+    if not user_query:
+        return jsonify({"error": "No query provided"}), 400
+
+    response = get_qa_chain(user_query)
     return jsonify({"response": response})
 
-# Run Flask app
 if __name__ == "__main__":
-    app.run(host="0.0.0.0", port=5000, threaded=True)
+    # If FAISS index is missing, create it
+    if not os.path.exists(config["vector_db_path"]):
+        logging.info(f"Vector database not found at {config['vector_db_path']}, creating it now.")
+        create_vector_db()
+    
+    # Run Flask server on Hugging Face-compatible settings
+    from waitress import serve
+    serve(app, host="0.0.0.0", port=7860)