Post
1923
π’For those who wish to quick start with reasoning / cot application over rows of tabular data but with minimal dependencies, this post would be valuable.
π I found that the problem is that given a bulk of Chain-of-Though (CoT) π queries for remotely accessed LLM π€ (like openrouter / Replicate / OpenAI) might result in connection loss which may lead exception π₯ and challenges with generated content restoration.
Here, is where I contribute with the bulk-chain.
β https://github.com/nicolay-r/bulk-chain
Currently working on 0.24.3 version, in which I am happy to announce the API for developing your apps that are based on CoT schema declaration in JSON (details in attached images πΈ)
All you have to do is:
β 1. Declare CoT-schema in json
β 2. Declare the model or use the preset
β 3. Launch code
One example is to use ReplicateIO provider:
https://github.com/nicolay-r/bulk-chain/blob/master/ext/replicate.py
Each model has a wrapped call for inference in try-catch block
π I found that the problem is that given a bulk of Chain-of-Though (CoT) π queries for remotely accessed LLM π€ (like openrouter / Replicate / OpenAI) might result in connection loss which may lead exception π₯ and challenges with generated content restoration.
Here, is where I contribute with the bulk-chain.
β https://github.com/nicolay-r/bulk-chain
Currently working on 0.24.3 version, in which I am happy to announce the API for developing your apps that are based on CoT schema declaration in JSON (details in attached images πΈ)
All you have to do is:
β 1. Declare CoT-schema in json
β 2. Declare the model or use the preset
β 3. Launch code
One example is to use ReplicateIO provider:
https://github.com/nicolay-r/bulk-chain/blob/master/ext/replicate.py
Each model has a wrapped call for inference in try-catch block