feat: Implement Pinecone vector store integration

- Update config.py with Pinecone settings and model configurations
- Implement VectorStore class with Pinecone backend
- Add comprehensive vector operations (add, search, delete)
- Set up proper error handling and metadata management
- Add .gitignore for Python project

simple_test.py

@@ -0,0 +1,49 @@
+import requests
+import json
+
+def test_model(prompt):
+    """Test the model with a simple prompt."""
+    url = "http://localhost:8000/direct-model"
+    
+    payload = {
+        "prompt": prompt,
+        "max_length": 200,
+        "num_return_sequences": 1,
+        "temperature": 0.7,
+        "top_p": 0.9
+    }
+    
+    print(f"Sending prompt: '{prompt}'")
+    
+    try:
+        response = requests.post(url, json=payload)
+        
+        if response.status_code == 200:
+            result = response.json()
+            print("\nGenerated text:")
+            print(result["generated_texts"][0])
+        else:
+            print(f"Error: {response.status_code}")
+            print(response.text)
+    except Exception as e:
+        print(f"Error: {str(e)}")
+        print("Make sure the FastAPI server is running on http://localhost:8000")
+
+def main():
+    print("Simple LLM Test")
+    print("===============")
+    print("Enter your prompt (or 'quit' to exit):")
+    
+    while True:
+        prompt = input("\n> ")
+        
+        if prompt.lower() in ["quit", "exit", "q"]:
+            break
+        
+        if not prompt.strip():
+            continue
+        
+        test_model(prompt)
+
+if __name__ == "__main__":
+    main()