bulk-chain 1.2.0

Third-party providers hosting↗️
👉demo👈

A no-strings-attached framework for your LLM that allows applying Chain-of-Thought-alike prompt schema towards a massive textual collections using custom third-party providers ↗️.

Main Features

• ✅ No-strings: you're free to LLM dependencies and flexible venv customization.
• ✅ Support schemas descriptions for Chain-of-Thought concept.
• ✅ Provides iterator over infinite amount of input contexts

Installation

From PyPI:

pip install --no-deps bulk-chain

or latest version from here:

pip install git+https://github.com/nicolay-r/bulk-chain@master

Chain-of-Thought Schema

To declare Chain-of-Though (CoT) schema we use JSON format. The field schema is a list of CoT instructions for the Large Language Model. Each item of the list represent a dictionary with prompt and out keys that corresponds to the input prompt and output variable name respectively. All the variable names should be mentioned in {}.

Example:

[
  {"prompt": "Given customer message: {text}, detect the customer's intent?", "out": "intent" },
  {"prompt": "Given customer message: {text}, extract relevant entities?", "out": "entities"},
  {"prompt": "Given intent: {intent} and entities: {entities}, generate a concise response or action recommendation for support agent.", "out": "action"}
]

Usage

🤖 Prepare

1. schema
   • Example for Sentiment Analysis
2. LLM model from the Third-party providers hosting↗️.
3. Data (iter of dictionaries)

🚀 Launch

API: For more details see the related Wiki page

from bulk_chain.core.utils import dynamic_init
from bulk_chain.api import iter_content

content_it = iter_content(
    # 1. Your schema.              
    schema=[
      {"prompt": "Given customer message: {text}, detect the customer's intent?", "out": "intent" },
      {"prompt": "Given customer message: {text}, extract relevant entities?", "out": "entities"},
      {"prompt": "Given intent: {intent} and entities: {entities}, generate a concise response or action recommendation for support agent.", "out": "action"}
    ],
    # 2. Your third-party model implementation.
    llm=dynamic_init(class_filepath="replicate_104.py")(api_token="<API-KEY>"),
    # 3. Customize your inference and result providing modes: 
    infer_mode="batch_async", 
    return_mode="batch",
    # 4. Your iterator of dictionaries
    input_dicts_it=YOUR_DATA_IT,
)
    
for content in content_it:
    # Handle your LLM responses here ...

Embed your LLM

All you have to do is to implement BaseLM class, that includes:

• __init__ -- for setting up batching mode support and (optional) model name;
• ask(prompt) -- infer your model with the given prompt.

See examples with models at nlp-thirdgate 🌌.