alihan/ell-llm-prompting
1
0
Fork 0
mirror of https://github.com/MadcowD/ell.git synced 2024-09-22 16:14:36 +03:00
Code Issues Packages Projects Releases Wiki Activity

version 2

Browse Source
This commit is contained in:
William Guss
2024-09-10 12:20:05 -07:00
parent 838b472148
commit 29d4110018
1 changed files with 7 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
README.md
View File

@@ -1,7 +1,7 @@
<picture>
<source media="(prefers-color-scheme: dark)" srcset="docs/src/_static/ell-wide-dark.png">
<source media="(prefers-color-scheme: light)" srcset="docs/src/_static/ell-wide-light.png">
<img alt="ell logo that inverts based on color scheme" src="docs/src/_static/ell-wide.png">
<source media="(prefers-color-scheme: dark)" srcset="https://docs.ell.so/_static/ell-wide-dark.png">
<source media="(prefers-color-scheme: light)" srcset="https://docs.ell.so/_static/ell-wide-light.png">
<img alt="ell logo that inverts based on color scheme" src="https://docs.ell.so/_static/ell-wide.png">
</picture>
--------------------------------------------------------------------------------
@@ -31,14 +31,14 @@ def hello(world : str):
hello("sama")
```
![alt text](docs/src/_static/gif1.webp)
![alt text](https://docs.ell.so/_static/gif1.webp)
### 2. Prompts are actually parameters of a machine learning model.
The process of prompt engineering involves many iterations, similar to the optimization processes in machine learning. Because LMPs are just functions, `ell` provides rich tooling for this process.
![ell demonstration](docs/src/_static/versions_small.webp)
![ell demonstration](https://docs.ell.so/_static/versions_small.webp)
`ell` provides **automatic versioning and serialization of prompts** through static and dynamic analysis and `gpt-4o-mini` **autogenerated commit messages** directly to a *local store*. This process is similar to `checkpointing` in a machine learning training loop, but it doesn't require any special IDE or editor - it's all done with regular Python code.
@@ -47,7 +47,7 @@ The process of prompt engineering involves many iterations, similar to the optim
Prompt engineering goes from a dark art to a science with the right tools. **Ell Studio is a local, open source tool for prompt version control, monitoring, visualization**. With Ell Studio you can empiricize your prompt optimization process over time and catch regressions before it's too late.
![ell demonstration](docs/src/_static/ell_studio_better.webp)
![ell demonstration](https://docs.ell.so/_static/ell_studio_better.webp)
```bash
ell-studio --storage ./logdir
```
@@ -72,7 +72,7 @@ def describe_activity(image: Image.Image):
# Capture an image from the webcam
describe_activity(capture_webcam_image()) # "they are holding a book"
```
![ell demonstration](docs/src/_static/multimodal_compressed.webp)
![ell demonstration](https://docs.ell.so/_static/multimodal_compressed.webp)
`ell` supports rich type coercion for multimodal inputs and outputs. You can use PIL images, audio, and other multimodal inputs inline in `Message` objects returned by LMPs.