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