dearwolf/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-05-31 07:54:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 34

Minor fixes (#285)

Browse source
This commit is contained in:
Ettore Di Giacinto 2023-05-17 21:01:46 +02:00 • committed by GitHub
parent 7e4616646f
commit 3f739575d8
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
3 changed files with 70 additions and 59 deletions
Download patch file Download diff file Expand all files Collapse all files

8
README.md
View file

@ -696,6 +696,8 @@ curl http://localhost:8080/v1/models
### Embeddings
OpenAI docs: https://platform.openai.com/docs/api-reference/embeddings
<details>
The embedding endpoint is experimental and enabled only if the model is configured with `embeddings: true` in its `yaml` file, for example:
@ -742,6 +744,8 @@ curl http://localhost:8080/v1/audio/transcriptions -H "Content-Type: multipart/f
### Image generation
OpenAI docs: https://platform.openai.com/docs/api-reference/images/create
LocalAI supports generating images with Stable diffusion, running on CPU.
| mode=0 | mode=1 (winograd/sgemm) |
@ -773,6 +777,8 @@ curl http://localhost:8080/v1/images/generations -H "Content-Type: application/j
}'
```
Note: image generator supports images up to 512x512. You can use other tools however to upscale the image, for instance: https://github.com/upscayl/upscayl.
#### Setup
Note: In order to use the `images/generation` endpoint, you need to build LocalAI with `GO_TAGS=stablediffusion`.
@ -847,7 +853,7 @@ Yes! If the client uses OpenAI and supports setting a different base URL to send
<details>
Not currently, as ggml doesn't support GPUs yet: https://github.com/ggerganov/llama.cpp/discussions/915.
There is partial GPU support, see build instructions above.
</details>