Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LLM_MODEL | No | Google LLM model | gemini-1.5-flash |
| CHUNK_SIZE | No | Size of text chunks in characters | 1000 |
| QDRANT_PATH | No | Path to Qdrant storage | ./qdrant_storage |
| FASTAPI_HOST | No | FastAPI server host | 0.0.0.0 |
| FASTAPI_PORT | No | FastAPI server port | 8000 |
| CHUNK_OVERLAP | No | Overlap between chunks | 200 |
| TOP_K_RESULTS | No | Number of chunks to retrieve | 5 |
| GOOGLE_API_KEY | Yes | Google AI Studio API key (required) | |
| EMBEDDING_MODEL | No | Google embedding model | text-embedding-004 |
| QDRANT_COLLECTION_NAME | No | Qdrant collection name | documents |
Schema
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |