huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-04-22 23:42:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix library

Browse Source
This commit is contained in:
philschmid 2023-08-18 09:16:26 +02:00
parent 69c3d79a1c
commit eccb8a0099
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docs/source/basic_tutorials/stream.md
View File

@ -1,6 +1,6 @@
# Stream responses in Javascript and Python # Stream responses in Javascript and Python
Requesting and generating text with LLMs can be a time-consuming and iterative process. A great way to improve the user experience is streaming tokens to the user as they are generated. Below are two examples of how to stream tokens using Python and JavaScript. For Python, we are going to use the **[client from Text Generation Inference](https://github.com/huggingface/text-generation-inference/tree/main/clients/python)**, and for JavaScript, the **[HuggingFace.js library](https://huggingface.co/docs/huggingface.js/main/en/index)** Requesting and generating text with LLMs can be a time-consuming and iterative process. A great way to improve the user experience is streaming tokens to the user as they are generated. Below are two examples of how to stream tokens using Python and JavaScript. For Python, we are going to use the **[huggingface_hub library](https://huggingface.co/docs/huggingface_hub/index), and for JavaScript, the [HuggingFace.js library](https://huggingface.co/docs/huggingface.js/main/en/index)
## Streaming requests with Python ## Streaming requests with Python