66 lines
3.4 KiB
Markdown
66 lines
3.4 KiB
Markdown
# MIND - Modular Inference & Node Database
|
|
Version: Milestone-1
|
|
|
|
## Setup
|
|
This will create and setup a `SQLite` database if `mind.db` doesn't
|
|
exist under [`backend/`](`backend/`).
|
|
|
|
Also see [`backend/README.md`](`backend/README.md`).
|
|
|
|
### Getting a llama.cpp instance
|
|
`llama.cpp` is included as a third-party git submodule under
|
|
[`third_party`](`third_party/`).
|
|
|
|
A script for grabbing a Qwen 3 1.7B LLM model from HuggingFace is at
|
|
[`backend/get-qwen3-1.7b.sh`](`backend/get-qwen3-1.7b.sh`).
|
|
|
|
The default location for the `Go` layer of the backend to access the LLM
|
|
service is `localhost:8081`.
|
|
|
|
*Please consider adding the `-n <num-of-tokens-to-predict>` option to
|
|
avoid infinite generation on smaller models*
|
|
|
|
### Running the backend layer
|
|
Run `go run ./backend/main.go`, which will start a backend instance at
|
|
`localhost:8080`.
|
|
|
|
Note that if `mind.db` doesn't exist in the working directory, it will
|
|
be created and be initialized by the code in
|
|
[`backend/db/migrations`](`backend/db/migrations`).
|
|
|
|
### DB-related
|
|
All db-related operations (e.g. queries) are under
|
|
[`backend/db`](`backend/db`).
|
|
|
|
## Running tests
|
|
To run tests, we provide a simple CLI-based frontend client at
|
|
[`backend/cli.py`](`backend/cli.py`).
|
|
|
|
This will include all of the features supported or under development.
|
|
|
|
## Current features (and features under development)
|
|
A short video demo of basic functionality on the CLI can be found
|
|
under [`milestone-1/demo.mp4`](`milestone-1/demo.mp4`).
|
|
|
|
The specific APIs used are given in [`backend/design.md`](`backend/design.md`).
|
|
|
|
| Action | Command / Description |
|
|
|-----------------------------------|------------------------------------------------------------------------------|
|
|
| Start conversation | `\new <title> <owner_id>` |
|
|
| Commit (prompt/answer or node) | Free text → `/completion` or `\node <user\|assistant> <content> [parent_id]` |
|
|
| Fork branch | `\branch <name> [head_node_id]` |
|
|
| Delete branch or node | `\delbranch <name>` or `\delnode <node_id>` |
|
|
| Extract subset as new tree | `\extract <title> <node_id ...>` |
|
|
| Merge two branches | `\merge <left> <right> <left-first\|right-first>` |
|
|
| Detach branch to new conversation | `\detach <branch>` |
|
|
| Append / copy tree to another | `\append-tree <src_conv> <src_branch> [dst_conv [dst_branch]]` |
|
|
| List conversations | `\listconvs <owner_id>` |
|
|
| List branches | `\listbranches <conversation_id>` |
|
|
| Linearize current branch | `\linearize` |
|
|
| Debug llama-server directly | `\llama <prompt>` |
|
|
| Switch conversation / branch | `\useconv <id>` and `\usebranch <name>` |
|
|
| Show current user | `\who` |
|
|
|
|
For a more detailed experience, it's strongly recommended to run the
|
|
backend locally and trying out the CLI.
|