neonrecall
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| NEONRECALL_STORE | No | Storage backend: `sqlite` or `postgres` | sqlite |
| NEONRECALL_PG_DSN | No | Postgres DSN; matches docker-compose.yml | postgresql://neonrecall:neonrecall@localhost:5432/neonrecall |
| NEONRECALL_RERANK | No | Reranker: `none`, `lexical` (offline) or `http` (POST /rerank, Cohere/Jina/vLLM shape) | none |
| NEONRECALL_PG_TABLE | No | Postgres table name; use one table per embedding model | neonrecall_chunks |
| NEONRECALL_LLM_MODEL | No | Chat model name | llama3.1 |
| NEONRECALL_CHUNK_SIZE | No | Chunk size in characters | 800 |
| NEONRECALL_BM25_WEIGHT | No | RRF weight for the BM25 retriever | 1.0 |
| NEONRECALL_EMBED_MODEL | No | Embedding model name | nomic-embed-text |
| NEONRECALL_INGEST_ROOT | No | Root directory that `/ingest` path requests must stay inside | current dir |
| NEONRECALL_LLM_API_KEY | No | API key for the chat completions endpoint | |
| NEONRECALL_LLM_BACKEND | No | LLM backend: `extractive` or `openai` | extractive |
| NEONRECALL_SQLITE_PATH | No | SQLite database file path; `:memory:` for throwaway runs | neonrecall.db |
| NEONRECALL_LLM_BASE_URL | No | Base URL for the OpenAI-compatible chat completions endpoint | Ollama |
| NEONRECALL_CHUNK_OVERLAP | No | Chunk overlap in characters | 120 |
| NEONRECALL_EMBED_API_KEY | No | API key for the embeddings endpoint | |
| NEONRECALL_EMBED_BACKEND | No | Embedding backend: `hash` or `openai` | hash |
| NEONRECALL_VECTOR_WEIGHT | No | RRF weight for the dense vector retriever | 1.0 |
| NEONRECALL_EMBED_BASE_URL | No | Base URL for the OpenAI-compatible embeddings endpoint | Ollama |
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
ActivityMaintained
ResponsivenessNo issues