huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-10 20:04:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

Addressed Omar's comments

Browse Source
This commit is contained in:
Merve Noyan 2023-08-18 14:05:33 +03:00 committed by GitHub
parent 452f8f3c2b
commit 08593dc180
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 17 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
docs/source/basic_tutorials/consuming_tgi.md
View File

@ -77,16 +77,20 @@ To serve both ChatUI and TGI in same environment, simply add your own endpoints
## Gradio ## Gradio
Gradio has a `ChatInterface` class to create neat UIs for chatbots. Let's take a look at how to create a chatbot with streaming mode using TGI and Gradio. Assume you are serving your model on port 8080. Gradio is a Python library that helps you build a web application for your machine learning model with few lines of code. It has a `ChatInterface` class to create neat UIs for chatbots. Let's take a look at how to create a chatbot with streaming mode using TGI and Gradio. Let's install Gradio and Hub Python library first.
```bash
pip install huggingface-hub gradio
```
Assume you are serving your model on port 8080, we will query through [InferenceClient](consuming_tgi#Inference-Client).
```python ```python
import gradio as gr import gradio as gr
from huggingface_hub import InferenceClient from huggingface_hub import InferenceClient
# initialize InferenceClient
client = InferenceClient(model="http://127.0.0.1:8080") client = InferenceClient(model="http://127.0.0.1:8080")
# query client using streaming mode
def inference(message, history): def inference(message, history):
partial_message = "" partial_message = ""
for token in client.text_generation(message, max_new_tokens=20, stream=True): for token in client.text_generation(message, max_new_tokens=20, stream=True):
@ -108,7 +112,16 @@ gr.ChatInterface(
The UI looks like this 👇 The UI looks like this 👇
![Gradio TGI](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/gradio-tgi.png) <div class="flex justify-center">
<img
class="block dark:hidden"
src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/tgi/gradio-tgi.png"
/>
<img
class="hidden dark:block"
src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/tgi/gradio-tgi.png"
/>
</div>
You can disable streaming mode using `return` instead of `yield` in your inference function. You can disable streaming mode using `return` instead of `yield` in your inference function.
You can read more about how to customize a `ChatInterface` [here](https://www.gradio.app/guides/creating-a-chatbot-fast). You can read more about how to customize a `ChatInterface` [here](https://www.gradio.app/guides/creating-a-chatbot-fast).