mmarch/text-generation-webui
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

[extensions/openai] various fixes (#2533)

Browse source
This commit is contained in:
matatonic 2023-06-06 00:43:04 -04:00 • committed by GitHub
parent 97f3fa843f
commit 4a17a5db67
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 109 additions and 91 deletions
Download patch file Download diff file Expand all files Collapse all files

8
extensions/openai/README.md
View file

@ -20,6 +20,12 @@ Example:
SD_WEBUI_URL=http://127.0.0.1:7861
```
Make sure you enable it in server launch parameters. Just make sure they include:
```
--extensions openai
```
### Embeddings (alpha)
Embeddings requires ```sentence-transformers``` installed, but chat and completions will function without it loaded. The embeddings endpoint is currently using the HuggingFace model: ```sentence-transformers/all-mpnet-base-v2``` for embeddings. This produces 768 dimensional embeddings (the same as the text-davinci-002 embeddings), which is different from OpenAI's current default ```text-embedding-ada-002``` model which produces 1536 dimensional embeddings. The model is small-ish and fast-ish. This model and embedding size may change in the future.
@ -42,7 +48,7 @@ Almost everything you use it with will require you to set a dummy OpenAI API key
With the [official python openai client](https://github.com/openai/openai-python), you can set the OPENAI_API_BASE environment variable before you import the openai module, like so:
```
OPENAI_API_KEY=dummy
OPENAI_API_KEY=sk-dummy
OPENAI_API_BASE=http://127.0.0.1:5001/v1
```