Hopiu/llm
1
0
Fork 0
mirror of https://github.com/Hopiu/llm.git synced 2026-03-17 05:00:25 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Release 0.17

Browse source 
Refs #587, #590, #591
This commit is contained in:
Simon Willison 2024-10-28 19:34:25 -07:00
parent 39d61d433a
commit a44ba49c21
2 changed files with 18 additions and 7 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

23
docs/changelog.md
View file

@ -1,23 +1,25 @@
# Changelog
(v0_17a0)=
## 0.17a0 (2024-10-28)
(v0_17)=
## 0.17 (2024-10-29)
Alpha support for **attachments**, allowing multi-modal models to accept images, audio, video and other formats. [#578](https://github.com/simonw/llm/issues/578)
Support for **attachments**, allowing multi-modal models to accept images, audio, video and other formats. [#578](https://github.com/simonw/llm/issues/578)
The default OpenAI `gpt-4o` and `gpt-4o-mini` models can both now be prompted with JPEG, GIF, PNG and WEBP images.
Attachments {ref}`in the CLI <usage-attachments>` can be URLs:
```bash
llm "describe this image" \
llm -m gpt-4o "describe this image" \
-a https://static.simonwillison.net/static/2024/pelicans.jpg
```
Or file paths:
```bash
llm "extract text" -a image1.jpg -a image2.jpg
llm -m gpt-4o-mini "extract text" -a image1.jpg -a image2.jpg
```
Or binary data, which may need to use `--attachment-type` to specify the MIME type:
```bash
cat image | llm "extract text" --attachment-type - image/jpeg
cat image | llm -m gpt-4o-mini "extract text" --attachment-type - image/jpeg
```
Attachments are also available {ref}`in the Python API <python-api-attachments>`:
@ -34,6 +36,15 @@ response = model.prompt(
```
Plugins that provide alternative models can support attachments, see {ref}`advanced-model-plugins-attachments` for details.
The latest **[llm-claude-3](https://github.com/simonw/llm-claude-3)** plugin now supports attachments for Anthropic's Claude 3 and 3.5 models. The **[llm-gemini](https://github.com/simonw/llm-gemini)** plugin supports attachments for Google's Gemini 1.5 models.
Also in this release: OpenAI models now record their `"usage"` data in the database even when the response was streamed. These records can be viewed using `llm logs --json`. [#591](https://github.com/simonw/llm/issues/591)
(v0_17a0)=
## 0.17a0 (2024-10-28)
Alpha support for **attachments**. [#578](https://github.com/simonw/llm/issues/578)
(v0_16)=
## 0.16 (2024-09-12)

2
setup.py
View file

@ -1,7 +1,7 @@
from setuptools import setup, find_packages
import os
VERSION = "0.17a0"
VERSION = "0.17"
def get_long_description():