Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/nicolay-r/bulk-chain
A no-string framework for reasoning over your tabular data rows with any provided LLM
https://github.com/nicolay-r/bulk-chain
bulk bulk-operation chain-of-thought chain-of-thought-reasoning chatgpt cot gpt inference llm pipeline reasoning spreadsheet sqlite3
Last synced: about 1 month ago
JSON representation
A no-string framework for reasoning over your tabular data rows with any provided LLM
- Host: GitHub
- URL: https://github.com/nicolay-r/bulk-chain
- Owner: nicolay-r
- License: mit
- Created: 2024-04-08T19:49:06.000Z (10 months ago)
- Default Branch: master
- Last Pushed: 2024-12-09T17:04:30.000Z (about 1 month ago)
- Last Synced: 2024-12-09T18:20:22.494Z (about 1 month ago)
- Topics: bulk, bulk-operation, chain-of-thought, chain-of-thought-reasoning, chatgpt, cot, gpt, inference, llm, pipeline, reasoning, spreadsheet, sqlite3
- Language: Python
- Homepage: https://x.com/nicolayr_/status/1847969224636961033
- Size: 77.1 KB
- Stars: 3
- Watchers: 2
- Forks: 0
- Open Issues: 13
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-sentiment-attitude-extraction - [github
- awesome-sentiment-attitude-extraction - [github
README
# bulk-chain 0.24.3
[](https://colab.research.google.com/github/nicolay-r/bulk-chain/blob/master/bulk_chain_tutorial.ipynb)
[](https://x.com/nicolayr_/status/1847969224636961033)
[](https://pypistats.org/packages/bulk-chain)
A lightweight, no-strings-attached **[Chain-of-Thought](https://arxiv.org/abs/2201.11903) framework** for your LLM, ensuring reliable results for bulk input requests stored in `CSV` / `JSONL` / `sqlite`.
It allows applying series of prompts formed into `schema` (See [related section](#chain-of-thought-schema))
### Features
* ✅ **No-strings**: you're free to LLM dependencies and flexible `venv` customization.
* ✅ **Provides iterator over infinite amount of input contexts** served in `CSV`/`JSONL`.
* ✅ **Progress caching**: withstanding exception during LLM calls by using `sqlite3` engine for caching LLM answers;
* ✅ **Support schemas descriptions** for Chain-of-Thought concept.
# Installation
```bash
pip install bulk-chain
```
## Chain-of-Thought Schema
To declare Chain-of-Though (CoT) schema, this project exploits `JSON` format.
This format adopts `name` field for declaring a name and `schema` is a list of CoT instructions for the Large Language Model.
Each step represents a dictionary with `prompt` and `out` keys that corresponds to the input prompt and output variable name respectively.
All the variable names are expected to be mentioned in `{}`.
Below, is an example on how to declare your own schema:
```python
{
"name": "schema-name",
"schema": [
{"prompt": "Given the question '{text}', let's think step-by-step.",
"out": "steps"},
{"prompt": "For the question '{text}' the reasoining steps are '{steps}'. what would be an answer?",
"out": "answer"},
]
}
```
Another templates are available [here](/ext/schema/thor_cot_schema.json).
# Usage
Just **three** simple steps:
1. Define your [CoT Schema](#chain-of-thought-schema), or fetch it as shown below:
```bash
!wget https://raw.githubusercontent.com/nicolay-r/bulk-chain/refs/heads/master/ext/schema/default.json
```
2. Fetch or write your own **model** or pick the one [preset here](/ext/):
```bash
!wget https://raw.githubusercontent.com/nicolay-r/bulk-chain/refs/heads/master/ext/flan_t5.py
```
3. Launch inference in (chat mode):
```bash
!python -m bulk_chain.infer \
--schema "default.json" \
--adapter "dynamic:flan_t5.py:FlanT5" \
%%m \
--device "cpu" \
--temp 0.1
```
# Embed your LLM
All you have to do is to implement `BaseLM` class, that includes:
* `__init__` -- for initialization;
* `ask(prompt)` -- infer your model with the given `prompt`.
See examples with models [here](/ext).