-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathindex.xml
8 lines (8 loc) · 4.75 KB
/
index.xml
1
2
3
4
5
6
7
8
<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Bavarder</title><link>http://bavarder.codeberg.page/</link><description>Recent content on Bavarder</description><generator>Hugo -- gohugo.io</generator><language>en-us</language><atom:link href="http://bavarder.codeberg.page/index.xml" rel="self" type="application/rss+xml"/><item><title/><link>http://bavarder.codeberg.page/code/baichat/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>http://bavarder.codeberg.page/code/baichat/</guid><description>BAIChat API Python Installation Pypi pip install baichat-py Codeberg pip install --index-url https://codeberg.org/api/packages/Bavarder/pypi/simple/ baichat-py Usage from baichat_py import Completion prompt = &#34;Hello, world!&#34; for token in Completion.create(prompt): print(token, end=&#34;&#34;, flush=True) print(&#34;&#34;)</description></item><item><title/><link>http://bavarder.codeberg.page/code/hgchat/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>http://bavarder.codeberg.page/code/hgchat/</guid><description>Hgchat hgchat was a Python wrapper for Hugging Chat. hgchat is now deprecated but you can use Soulter/hugging-chat-api instead.
Installation As library From Pypi pip install hgchat From Codeberg pip install --index-url https://codeberg.org/api/packages/Bavarder/pypi/simple/ hgchat As an interactive prompt git clone https://codeberg.org/Bavarder/hgchat.git # or https://github.com/Bavarder/hgchat.git cd hgchat Usage As library from hgchat import HGChat hgchat = HGChat() r = hgchat.ask(user_input) for i in r: char = i[&#34;token&#34;][&#34;text&#34;] if char == &#34;&lt;/s&gt;&#34;: print(&#34;\n&#34;, end=&#34;&#34;) else: print(char, end=&#34;&#34;) As an interactive prompt python chat.</description></item><item><title/><link>http://bavarder.codeberg.page/help/huggingchat/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>http://bavarder.codeberg.page/help/huggingchat/</guid><description>HuggingChat Until 0.2.2 Bavarder was using HuggingChat as the default provider but since HuggingChat added authentification, we changed to the model used by Hugging Chat: Open-Assistant SFT-1 12B Model.</description></item><item><title/><link>http://bavarder.codeberg.page/help/huggingface/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>http://bavarder.codeberg.page/help/huggingface/</guid><description>Hugging Face A token is not necessary, it allow you to have a bigger rate limit
Create an account on HuggingFace Follow the documentation for getting an user access token Use the generated token in the API key entry</description></item><item><title/><link>http://bavarder.codeberg.page/help/local/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>http://bavarder.codeberg.page/help/local/</guid><description>Local models You can run model locally with tools like FastChat or LocalAI which provide a OpenAI-API compatible API.
Custom API URL Maybe you are using a custom endpoint which is providing an OpenAI-API compatible API. For using a custom endpoint, you just need to provide the base url in the preferences. For example, if you are using FastChat, you need to put http://localhost:8000/v1 in Preferences &gt; Local Model &gt; API URL.</description></item><item><title/><link>http://bavarder.codeberg.page/help/openai/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>http://bavarder.codeberg.page/help/openai/</guid><description>OpenAI The OpenAI API uses API keys for authentication. Visit your API Keys page to retrieve the API key you&rsquo;ll use in your requests.
Custom API URL Maybe you are using a custom endpoint which is providing an OpenAI-API compatible API. For using a custom endpoint, you just need to provide the base url in the preferences. For example, if you are using FastChat, you need to put http://localhost:8000/v1 in Preferences &gt; OpenAI Custom Model &gt; API URL.</description></item><item><title/><link>http://bavarder.codeberg.page/install/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>http://bavarder.codeberg.page/install/</guid><description>Installation Flatpak Flathub You can either use your GNOME Software and search for &ldquo;Bavarder&rdquo; or you can run
flatpak install io.github.Bavarder.Bavarder From Source Clone the repo and run flatpak-builder
git clone https://codeberg.org/Bavarder/Bavarder.git # or https://github.com/Bavarder/Bavarder.git cd Bavarder flatpak-builder --install --user --force-clean repo/ build-aux/flatpak/io.github.Bavarder.Bavarder.json Archlinux Bavarder is available in the AUR. Just use your favourite aur helper!
yay -S bavarder</description></item></channel></rss>