intelligence-hub
by blpancholi
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DATA_DIR | No | Base path; ChromaDB at DATA_DIR/chroma_db | ./data |
| CHUNK_SIZE | No | PDF chunking size for ingestion | 1000 |
| MODEL_NEWS | No | Expert for news (≤3B) | llama3.2:3b |
| OLLAMA_HOST | No | Ollama API URL | http://localhost:11434 |
| ROUTER_MODEL | No | Model used for domain classification (≤3B) | llama3.2:3b |
| CHUNK_OVERLAP | No | PDF chunking overlap for ingestion | 200 |
| MODEL_FINANCE | No | Expert for finance (≤3B) | qwen2.5:3b |
| MODEL_MEDICAL | No | Expert for medical (≤3B) | llama3.2:3b |
| EMBEDDING_MODEL | No | Embedding model for ChromaDB | nomic-embed-text |
| TOP_K_RETRIEVAL | No | Number of chunks to retrieve per query | 5 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityInactive
ResponsivenessNo issues