Coming soon
Enterprise Search for AI (RAG)
The Lookeen RAG API and MCP integration are not yet available. The information below describes planned functionality.
Give your own AI applications controlled access to corporate knowledge. Lookeen indexes email, files and Microsoft 365, retrieves relevant passages and supplies agents and language models with sources and metadata.
Turn enterprise search into your retrieval layer
RAG means retrieval-augmented generation: before a language model answers, it receives relevant content from reliable sources. Lookeen handles indexing, retrieval and permission filtering; the model, prompt and agent logic remain your choice.
Connect existing data
File servers, network drives, Exchange, Microsoft 365, SharePoint, OneDrive and PST archives feed one central index that stays up to date.
Supply focused context
The RAG API returns ranked, query-specific text passages rather than a generated answer – compact enough for a language model’s context.
Keep sources traceable
Every result carries a stable document ID plus title, path, URL, type and modification time where those values are available.
Two ways to connect applications and agents
Your own application or an off-the-shelf AI assistant: Lookeen delivers the right sources through an open interface.
HTTP API
POST /v1/rag accepts a query, result limit and optional user, group and filter context. Its synchronous JSON response fits directly into custom RAG pipelines.
Model Context Protocol (MCP)
Through MCP, Lookeen can be exposed as a tool to compatible assistants and agents. An agent searches corporate knowledge when needed, receives sources and incorporates the findings into its own workflow.
Ask about MCP integrationRetrieval without a prescribed answer
The RAG API does not invoke a language model. It only returns search results and selected passages. You remain free to choose the model provider, system prompt, guardrails, citation format and additional tools. For complete conversational research, Lookeen AI is available alongside it.
Built for corporate data
Handing company knowledge to AI systems takes control over where it lives, how much is shared and who gets access.
Inside your infrastructure
Lookeen Server and its index run on your network. Local language models and fully isolated architectures are supported too.
Bounded context
topK limits the response to between 1 and 100 results. The default is ten passages, preventing uncontrolled model-context growth.
Explicit authentication
Access uses a Bearer API key. User and group IDs can scope retrieval to the intended permission context.
Typical uses
Where Lookeen as a retrieval layer makes the difference today.
- Internal assistants: answer questions about projects, customers, policies and earlier communications.
- Agentic workflows: search for evidence before acting and pass cited sources into the next step.
- Business applications: provide relevant email and documents inside CRM, service, legal or compliance processes.
- Your own AI platform: add local enterprise retrieval to existing models and orchestration systems.
Frequently asked questions
Does the RAG API generate an AI answer?
No. It returns ranked passages and document metadata. Your language model or agent performs generation. Keeping the steps separate makes control, evaluation and model changes easier.
Is retrieval semantic or lexical?
The current API explicitly reports its strategy as lexical. It uses Lookeen’s proven full-text retrieval and selects the stored passage that best matches the query from each document.
How can agents discover the API contract?
GET /v1/rag returns machine-readable JSON covering authentication, fields, limits, filter operators and examples. The same contract is available in the HTML reference.
Put your corporate knowledge to work for AI
Talk to us about data sources, permissions, API or MCP integration and deployment in your infrastructure.