Search results
HuggingChat is a web application that lets you chat with various AI models created by the Hugging Face community. You can write emails, code snakes, search web, and more with these models, but be aware of their limitations and biases.
- Chat UI
- No Setup Deploy
- Setup
- Launch
- Web Search
- Text Embedding Models
- Extra parameters
- Deploying to a HF Space
- Building
- Config changes for HuggingChat
- GeneratedCaptionsTabForHeroSec
A chat interface using open source models, eg OpenAssistant or Llama. It is a SvelteKit app and it powers the HuggingChat app on hf.co/chat.
1.No Setup Deploy
2.Setup
3.Launch
4.Web Search
5.Text Embedding Models
If you don't want to configure, setup, and launch your own Chat UI yourself, you can use this option as a fast deploy alternative.
You can deploy your own customized Chat UI instance with any supported LLM of your choice on Hugging Face Spaces. To do so, use the chat-ui template available here.
Set HF_TOKEN in Space secrets to deploy a model with gated access or a model in a private repository. It's also compatible with Inference for PROs curated list of powerful models with higher rate limits. Make sure to create your personal token first in your User Access Tokens settings.
Read the full tutorial here.
The default config for Chat UI is stored in the .env file. You will need to override some values to get Chat UI to run locally. This is done in .env.local.
Start by creating a .env.local file in the root of the repository. The bare minimum config you need to get Chat UI to run locally is the following:
After you're done with the .env.local file you can run Chat UI locally with:
Chat UI features a powerful Web Search feature. It works by:
1.Generating an appropriate search query from the user prompt.
2.Performing web search and extracting content from webpages.
3.Creating embeddings from texts using a text embedding model.
4.From these embeddings, find the ones that are closest to the user query using a vector similarity search. Specifically, we use inner product distance.
5.Get the corresponding texts to those closest embeddings and perform Retrieval-Augmented Generation (i.e. expand user prompt by adding those texts so that an LLM can use this information).
By default (for backward compatibility), when TEXT_EMBEDDING_MODELS environment variable is not defined, transformers.js embedding models will be used for embedding tasks, specifically, Xenova/gte-small model.
You can customize the embedding model by setting TEXT_EMBEDDING_MODELS in your .env.local file. For example:
The required fields are name, chunkCharLength and endpoints. Supported text embedding backends are: transformers.js and TEI. transformers.js models run locally as part of chat-ui, whereas TEI models run in a different environment & accessed through an API endpoint.
When more than one embedding models are supplied in .env.local file, the first will be used by default, and the others will only be used on LLM's which configured embeddingModel to the name of the model.
OpenID connect
The login feature is disabled by default and users are attributed a unique ID based on their browser. But if you want to use OpenID to authenticate your users, you can add the following to your .env.local file: These variables will enable the openID sign-in modal for users.
Theming
You can use a few environment variables to customize the look and feel of chat-ui. These are by default: •PUBLIC_APP_NAME The name used as a title throughout the app. •PUBLIC_APP_ASSETS Is used to find logos & favicons in static/$PUBLIC_APP_ASSETS, current options are chatui and huggingchat. •PUBLIC_APP_COLOR Can be any of the tailwind colors. •PUBLIC_APP_DATA_SHARING Can be set to 1 to add a toggle in the user settings that lets your users opt-in to data sharing with models creator. •PUBLIC_APP_DISCLAIMER If set to 1, we show a disclaimer about generated outputs on login.
Web Search config
You can enable the web search through an API by adding YDC_API_KEY (docs.you.com) or SERPER_API_KEY (serper.dev) or SERPAPI_KEY (serpapi.com) or SERPSTACK_API_KEY (serpstack.com) to your .env.local. You can also simply enable the local google websearch by setting USE_LOCAL_WEBSEARCH=true in your .env.local or specify a SearXNG instance by adding the query URL to SEARXNG_QUERY_URL.
Create a DOTENV_LOCAL secret to your HF space with the content of your .env.local, and they will be picked up automatically when you run.
To create a production version of your app:
You can preview the production build with npm run preview.
The config file for HuggingChat is stored in the .env.template file at the root of the repository. It is the single source of truth that is used to generate the actual .env.local file using our CI/CD pipeline. See updateProdEnv for more details.
Tip
If you want to make changes to model config for HuggingChat, you should do so against .env.template.
We currently use the following secrets for deploying HuggingChat in addition to the .env.template above:
•MONGODB_URL
•HF_TOKEN
Chat UI is a SvelteKit app that uses open source models to power the HuggingChat app on hf.co/chat. Learn how to deploy, configure, and customize Chat UI with web search, text embedding, and extra parameters features.
Apr 27, 2023 · HuggingChat is a generative AI tool that can create text, code, and answer questions like ChatGPT, but it's more prone to hallucinations and errors. Learn how to access, use, and help train this open-source project from Hugging Face.
May 9, 2019 · Learn how to use OpenAI GPT and GPT-2 models to create a state-of-the-art dialog agent with a persona. Follow the tutorial and code to fine-tune the pretrained language models and train them for less than $20.
Apr 9, 2024 · A language model with 12 billion parameters for interpreting instructions in seven languages. It was trained on public and synthetic datasets, and optimized for chat-like applications.
Apr 25, 2023 · HuggingChat is a text-generating AI model developed by Open Assistant, a project organized by LAION, a German nonprofit. It can handle many tasks like ChatGPT, but it may also produce inaccurate or offensive answers depending on the prompts.
People also ask
What can huggingchat do?
Is huggingchat a good alternative to chatgpt?
Is hugging face a Chabot?
Is huggingchat a chatbot?
