A support chat widget on your website that answers from your docs, with AnythingLLM
Put AnythingLLM's chat bubble on your site, answering only from your docs: query mode, a domain allowlist, daily caps, styling, chat logs and costs.
All apps
AnythingLLM
Chat with your documents, and put that chat on your website.
Deploy AnythingLLM
7 days free, then from $5 a month.
AnythingLLM is an open-source workspace for chatting with your own documents, websites and data through the LLM of your choice. On ranx it runs on your own subdomain with its chat widget, developer API and vector database included, and you sign in with your ranx.cloud account.
What you get
- Workspaces that chat over your PDFs, docs and web pages
- Embeddable chat widget for your website, limited to the domains you allow
- Developer API with an OpenAI-compatible endpoint
- Documents, vectors and settings kept on your instance's own disk
- Use your own LLM key: OpenAI, Anthropic, OpenRouter and many more
- Sign in with your ranx.cloud account
Per-instance encryption key, on every plan. Its disk and backups are encrypted with a key unique to your instance, and deleting the instance destroys the key.
On Pro and Power
- Daily backups (7 days)A snapshot of the instance's disk every day, the last 7 kept, restorable from the dashboard. Stored in the same Google Cloud region as the instance.
Live
7 days free, then from $5 a month. Your instance runs on Google Cloud in the US with its own subdomain; add your own LLM key in its dashboard.
Deploy AnythingLLMSource codeGuides
All AnythingLLM guidesReal use cases for AnythingLLM, set up end to end.
Accurate answers from your own PDFs in an AnythingLLM workspace
Set up an AnythingLLM workspace for contracts, manuals or papers: embedder choice, chunk size, similarity threshold, reranking, pinning and costs.
Keep an AnythingLLM workspace in sync with your docs site and GitHub repo
Import a docs site with the Bulk Link Scraper and a repo with the GitHub connector, then let AnythingLLM's document watching re-sync them every week.
Research a question on the web with AnythingLLM's agent and keep what it finds
Use AnythingLLM's @agent to search the web, read the pages, and write a cited answer, then save the best sources into a workspace or export a report.
Send easy questions to a cheap model with AnythingLLM's Model Router
Pick a model per AnythingLLM workspace, then add a Model Router that answers on Haiku by default and switches to Sonnet only for messages that need it.