working server

api/README.md

@@ -56,13 +56,13 @@ Available options:
 |-----------|---------|-------------|
 | --host | 0.0.0.0 | Server host |
 | --port | 9621 | Server port |
-| --model | gemma2:2b | LLM model name |
+| --model | mistral-nemo:latest | LLM model name |
-| --embedding-model | nomic-embed-text | Embedding model name |
+| --embedding-model | bge-m3:latest | Embedding model name |
 | --ollama-host | http://localhost:11434 | Ollama host URL |
-| --working-dir | ./dickens | Working directory for RAG |
+| --working-dir | ./rag_storage | Working directory for RAG |
 | --max-async | 4 | Maximum async operations |
 | --max-tokens | 32768 | Maximum token size |
-| --embedding-dim | 768 | Embedding dimensions |
+| --embedding-dim | 1024 | Embedding dimensions |
 | --max-embed-tokens | 8192 | Maximum embedding token size |
 | --input-file | ./book.txt | Initial input file |
 | --log-level | INFO | Logging level |
@@ -79,11 +79,11 @@ python ollama_lightrag_server.py
 python ollama_lightrag_server.py --model llama2:13b --port 8080 --working-dir ./custom_rag
 ```
 
+Make sure the models are installed in your ollama instance
 ```bash
-python ollama_lightrag_server.py --model mistral-nemo:latest  --embedding-dim 1024 --embedding-model bge-m3
+python ollama_lightrag_server.py --model mistral-nemo:latest --embedding-model bge-m3  --embedding-dim 1024
 ```
 
-
 ## API Endpoints
 
 ### Query Endpoints
@@ -165,13 +165,6 @@ When the server is running, visit:
 - Swagger UI: http://localhost:9621/docs
 - ReDoc: http://localhost:9621/redoc
 
-## Contributing
-
-1. Fork the repository
-2. Create your feature branch (`git checkout -b feature/AmazingFeature`)
-3. Commit your changes (`git commit -m 'Add some AmazingFeature'`)
-4. Push to the branch (`git push origin feature/AmazingFeature`)
-5. Open a Pull Request
 
 ## License
 
@@ -182,5 +175,3 @@ This project is licensed under the MIT License - see the LICENSE file for detail
 - Built with [FastAPI](https://fastapi.tiangolo.com/)
 - Uses [LightRAG](https://github.com/HKUDS/LightRAG) for document processing
 - Powered by [Ollama](https://ollama.ai/) for LLM inference
-
-## Support

api/ollama_lightrag_server.py

@@ -13,6 +13,7 @@ from enum import Enum
 from pathlib import Path
 import shutil
 import aiofiles
+from ascii_colors import ASCIIColors, trace_exception
 
 def parse_args():
     parser = argparse.ArgumentParser(
@@ -30,17 +31,17 @@ def parse_args():
                        help='Directory containing input documents (default: ./inputs)')
     
     # Model configuration
-    parser.add_argument('--model', default='gemma2:2b', help='LLM model name (default: gemma2:2b)')
+    parser.add_argument('--model', default='mistral-nemo:latest', help='LLM model name (default: mistral-nemo:latest)')
-    parser.add_argument('--embedding-model', default='nomic-embed-text', 
+    parser.add_argument('--embedding-model', default='bge-m3:latest', 
-                       help='Embedding model name (default: nomic-embed-text)')
+                       help='Embedding model name (default: bge-m3:latest)')
     parser.add_argument('--ollama-host', default='http://localhost:11434', 
                        help='Ollama host URL (default: http://localhost:11434)')
     
     # RAG configuration
     parser.add_argument('--max-async', type=int, default=4, help='Maximum async operations (default: 4)')
     parser.add_argument('--max-tokens', type=int, default=32768, help='Maximum token size (default: 32768)')
-    parser.add_argument('--embedding-dim', type=int, default=768, 
+    parser.add_argument('--embedding-dim', type=int, default=1024, 
-                       help='Embedding dimensions (default: 768)')
+                       help='Embedding dimensions (default: 1024)')
     parser.add_argument('--max-embed-tokens', type=int, default=8192, 
                        help='Maximum embedding token size (default: 8192)')
     
@@ -150,6 +151,7 @@ def create_app(args):
                         doc_manager.mark_as_indexed(file_path)
                         logging.info(f"Indexed file: {file_path}")
                 except Exception as e:
+                    trace_exception(e)
                     logging.error(f"Error indexing file {file_path}: {str(e)}")
             
             logging.info(f"Indexed {len(new_files)} documents from {args.input_dir}")
@@ -328,7 +330,7 @@ def create_app(args):
             raise HTTPException(status_code=500, detail=str(e))
 
 
-    @app.get("/status")
+    @app.get("/health")
     async def get_status():
         """Get current system status"""
         return {

api/requirements.txt

@@ -1,3 +1,4 @@
 fastapi
 uvicorn
 python-multipart
+ascii_colors