jalr/tabbyAPI-ollama
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

OAI: Initial vision support in OAI chat completions

Browse source 
* Support image_url inputs containing URLs or base64 strings following OAI vision spec
* Use async lru cache for image embeddings
* Add generic wrapper class for multimodal embeddings
This commit is contained in:
DocShotgun 2024-11-17 21:23:09 -08:00
parent 5fa298e601
commit dd41eec8a4
7 changed files with 115 additions and 26 deletions
Download patch file Download diff file Expand all files Collapse all files

1
pyproject.toml
View file

@ -29,6 +29,7 @@ dependencies = [
"lm-format-enforcer >= 0.9.6",
"aiofiles",
"aiohttp",
"async_lru",
"huggingface_hub",
"psutil",
"httptools>=0.5.0",