a flexible prompt renderer for large language models (LLMs)
Project description
flex[prompt]
Large language models have maximum context window—a maximum number of tokens they can receive and produce. You may have noticed this:
Flex prompt addresses this by fitting your prompt into the model's context window. You provide a flexible prompt template, flex prompt renders it into model input.
Flex prompt does not handle model execution, but integrates well with execution frameworks like LangChain and Haystack.
Check out the intro to flex prompt colab (github link) for usage and examples.
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
flex_prompt-0.0.4.tar.gz
(80.4 kB
view hashes)
Built Distribution
Close
Hashes for flex_prompt-0.0.4-py3-none-any.whl
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | f0a518cda947659af714addb41a489f78b778f6380230137f1e7a37c1697d310 |
|
| MD5 | ed510ae6d3ef8b6e9f566b2d7c8459cf |
|
| BLAKE2b-256 | 3499886ed56e8f2d58d60ca5a0ecaf5a77598d8cc845749aee287a113d908e99 |
