bc8f648a91
The default sampler on some models don't return enough candidates which leads to a false sense of randomness. Tracing back the code it looks that with the temperature sampler there might not be enough candidates to pick from, and since the seed and "randomness" take effect while picking a good candidate this yields to the same results over and over. Fixes https://github.com/mudler/LocalAI/issues/1723 by updating the examples and documentation to use mirostat instead. |
||
---|---|---|
.. | ||
autoGPT | ||
bruno/LocalAI Test Requests | ||
chainlit | ||
chatbot-ui | ||
chatbot-ui-manual | ||
configurations | ||
continue | ||
discord-bot | ||
e2e-fine-tuning | ||
flowise | ||
functions | ||
insomnia | ||
k8sgpt | ||
kubernetes | ||
langchain | ||
langchain-chroma | ||
langchain-huggingface | ||
langchain-python | ||
llamaindex | ||
localai-webui | ||
models | ||
privateGPT | ||
query_data | ||
rwkv | ||
slack-bot | ||
slack-qa-bot | ||
streamlit-bot | ||
telegram-bot | ||
README.md |
Examples
ChatGPT OSS alternative | Image generation |
---|---|
Telegram bot | Flowise |
---|---|
Here is a list of projects that can easily be integrated with the LocalAI backend.
Projects
AutoGPT
by @mudler
This example shows how to use AutoGPT with LocalAI.
Chatbot-UI
by @mkellerman
This integration shows how to use LocalAI with mckaywrigley/chatbot-ui.
There is also a separate example to show how to manually setup a model: example
K8sGPT
by @mudler
This example show how to use LocalAI inside Kubernetes with k8sgpt.
Fine-tuning a model and convert it to gguf to use it with LocalAI
by @mudler
This example is an e2e example on how to fine-tune a model with axolotl and convert it to gguf to use it with LocalAI.
Flowise
by @mudler
This example shows how to use FlowiseAI/Flowise with LocalAI.
Discord bot
by @mudler
Run a discord bot which lets you talk directly with a model
Check it out here, or for a live demo you can talk with our bot in #random-bot in our discord server.
Langchain
A ready to use example to show e2e how to integrate LocalAI with langchain
Langchain Python
by @mudler
A ready to use example to show e2e how to integrate LocalAI with langchain
LocalAI functions
by @mudler
A ready to use example to show how to use OpenAI functions with LocalAI
LocalAI WebUI
by @dhruvgera
A light, community-maintained web interface for LocalAI
How to run rwkv models
by @mudler
A full example on how to run RWKV models with LocalAI
PrivateGPT
by @mudler
A full example on how to run PrivateGPT with LocalAI
Slack bot
by @mudler
Run a slack bot which lets you talk directly with a model
Slack bot (Question answering)
by @mudler
Run a slack bot, ideally for teams, which lets you ask questions on a documentation website, or a github repository.
Question answering on documents with llama-index
by @mudler
Shows how to integrate with Llama-Index to enable question answering on a set of documents.
Question answering on documents with langchain and chroma
by @mudler
Shows how to integrate with Langchain
and Chroma
to enable question answering on a set of documents.
Telegram bot
_by @mudler
Use LocalAI to power a Telegram bot assistant, with Image generation and audio support!
Template for Runpod.io
by @fHachenberg
Allows to run any LocalAI-compatible model as a backend on the servers of https://runpod.io
Continue
by @gruberdev
Demonstrates how to integrate an open-source copilot alternative that enhances code analysis, completion, and improvements. This approach seamlessly integrates with any LocalAI model, offering a more user-friendly experience.
Streamlit bot
by @majoshi1
A chat bot made using Streamlit
& LocalAI.
Want to contribute?
Create an issue, and put Example: <description>
in the title! We will post your examples here.