Biel.ai
Book a demo
RAG API for technical documentation

RAG API for technical documentation

Give users answers from your docs, right inside your product. Biel’s API finds the right information and links to the original pages.

Build with BielRead the API docs
OpenAPI 3.0Streaming responsesSource metadata
curlnodepython
# Ask any question of your indexed docs
curl https://app.biel.ai/api/v2/projects/acme-docs/chats/ \
  -H "Authorization: Api-Key $BIEL_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "message": "How do I rotate API keys?"
  }'

# Illustrative response excerpt
{
  "ai_message": {
    "message": "Follow the key rotation guide and check dependent applications before revoking the old key.",
    "sources": [
      {
        "title": "Key rotation",
        "url": "https://docs.acme.dev/keys/rotation"
      }
    ]
  },
  "chat_uuid": "EXAMPLE_CHAT_UUID"
}

Used by documentation and developer-experience teams

ScyllaDB
Katalon
Tezos
Talon.one
GrepTime
CrazyGames
SecuroSys
ScyllaDB
Katalon
Tezos
Talon.one
GrepTime
CrazyGames
SecuroSys
The build vs. buy moment

What you would need to operate yourself

A documentation assistant needs ingestion, retrieval, model orchestration, source handling, authentication, monitoring, and ongoing updates.

Build it yourself

Build and maintain the pipeline

  • iIngest documentation, code blocks, and OpenAPI specifications.
  • iiOperate retrieval infrastructure and refresh the index after content changes.
  • iiiEvaluate prompts and models against representative documentation questions.
  • ivReturn source metadata and render citations in your application.
  • vAdd authentication, usage limits, monitoring, and cost controls.
  • viMaintain the pipeline as models, sources, and product requirements change.
The work continues as your sources, models, and product requirements change.
Use the Biel RAG API

Use Biel’s managed API

  • iConnect a supported documentation source and let Biel maintain the index.
  • iiUse REST endpoints documented with an OpenAPI specification.
  • iiiChoose streaming or buffered chat responses.
  • ivReceive source metadata with generated answers and retrieval results.
  • vAuthenticate requests and monitor usage through the Biel platform.
  • viAdopt model and retrieval updates without rebuilding the ingestion pipeline.
Read the API documentation and check the plan requirements before integrating.
Endpoints

Endpoints for the documentation workflow

The API covers ingestion, sync, retrieval, conversational chat, feedback, and analytics. Use any HTTP client or generate one from the OpenAPI specification.

POST/api/v2/projects/<slug>/chats/

Generate an answer

Send a question and get a grounded, source-linked answer. Streaming or buffered. Multi-turn aware: pass a chat_uuid to continue an existing conversation with full context.

GET/api/v2/projects/<slug>/search/

Retrieve documentation for your own model

Send a query and receive ranked results with source information. Use them with your own model when you want to control how the answer is generated.

POST/api/v2/projects/<slug>/sources/

Manage what’s indexed

Add a docs URL, a GitHub repo, an OpenAPI spec, a sitemap. Exclude paths, and trigger a recrawl any time through the sync endpoint to wire ingestion into CI/CD.

GET/api/v2/projects/<slug>/analytics/chat/

Read conversation analytics

Read aggregate chat activity over a date range. Separate endpoints report search, MCP, and insights activity; use the conversation endpoints when you need individual messages.

POST/api/v2/projects/<slug>/messages/<uuid>/feedback/

Record feedback

Record feedback on a response and review it in your dashboard. Use it to investigate which answers need improvement.

GETopenapi.json

Generate clients automatically

Use the OpenAPI specification to generate a typed client for your application.

What’s included

What Biel manages for you

i.

Streaming or buffered responses

Stream chat responses with server-sent events or request a buffered response for jobs that do not need incremental output.

ii.

API-key authentication

Authenticate API requests with project credentials that can be rotated from the dashboard.

iii.

Included interactions by plan

Published plans include monthly interactions. Pay for extra usage beyond that allowance and set an optional spending limit in your dashboard.

iv.

Sources in the response

Chat and retrieval responses include source information that your interface can display for verification.

v.

Index refresh controls

Refresh documentation from the dashboard, a schedule, or supported automation hooks.

vi.

Separate projects

Keep documentation sources and API usage organized in separate Biel projects under one account.

Use cases

What teams build with the API

Custom in-product chat

An assistant inside your app

Build the chat experience that fits your product. The widget is a starting point; the API lets you control everything: layout, conversation flow, and how source links appear.

Internal copilots

For sales, success, and support

Power internal tools with grounded answers from your knowledge base. Connect approved runbooks and product guides, then build an interface for the people who should have access.

Pipelines and automations

Wire docs into your workflows

For example, your application could draft a support reply from connected documentation or retrieve relevant guides for an in-product help panel. Your team builds and reviews the workflow.

“It consistently delivers accurate results, and we’ve had no issues depending on it as part of our documentation experience.”

Lars Wilhelmer · Documentation Engineer at Talon.One

Questions about the API

Which plan includes API access?

Business includes API access from $400/month. Enterprise offers custom limits and terms. Compare plans and included usage.

Which AI models do you support?

Selected OpenAI and Anthropic models, depending on your plan. Compare included models.

Can I bring my own LLM?

Yes, on Enterprise. You can also retrieve documentation through the search API and pass it to your own model. See the API requirements.

Is the API the right entry point for my team?

Use the API when you are building your own interface or workflow. For a finished experience, start with AI chat, AI search, or the hosted MCP server.

What about latency?

Latency depends on the selected model, question, and retrieved context. Streaming lets your interface display the response as it is generated.

Is our content used to train AI models?

No. We do not use your indexed content or user conversations to train AI models. See the Security Overview.

Build with your docs through the API

Try Biel with your docsRead the API docs
14-day free trial · No credit card required
Try me ↓