apache / apache/hamilton

[good first issue - advanced][Example] Create a dataflow modeling information extraction using an LLM

Open
#241 9 comments 0 reactions 0 assignees View on GitHub
documentation good first issue onboarding
Dominant language
Jupyter Notebook
Stars
2.6k
Forks
213
PR merge metrics
No merged PRs in 30d

Description

Write an example dataflow that uses Hamilton to model an information extraction task using an LLM.

For example:
1. given an output schema
2. given input text
3. make a prompt that is sent to an LLM API (pick one)
4. then write a function to validate the output

For inspiration you can look at [Langchain's implementation](https://github.com/langchain-ai/langchain/blob/490ad93b3cf7d24b30f8993f860b654ff107e638/libs/langchain/langchain/chains/openai_functions/extraction.py#L46).

The code for this example should end up under the /examples/LLM_Workflows directory.

Contributor guide

Open the contributing guide

Research direction

Start by reviewing the existing examples in /examples/LLM_Workflows and the linked LangChain extraction implementation. Build an example that defines an output schema and input text, sends a generated prompt to one LLM API, and validates the response. Done means the complete dataflow example is placed under /examples/LLM_Workflows.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
data-engineering, machine-learning
Issue type
Feature
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
38/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.