Startseite / Funktionen / Wissen und Memory

Wissensdatenbanken, Memory und RAG auf osFoundry

Automatisch extrahierte Entitäten, Wissensgraphen, eigene Retrieval-Pipelines und gerankte RAG — alles in osStudio konfigurierbar.

osFoundry ist eine wissensorientierte Plattform rund um KI: Jede Notiz, jedes Dokument und jede hochgeladene Datei wird automatisch gechunkt, eingebettet und indexiert. Ein Workspace-Wissensgraph extrahiert Entitäten und Beziehungen über alles, woran Sie gearbeitet haben. Eigene Retrieval-Pipelines (mit Reranking, MMR-Diversität und mehrstufigen Stufen) sind pro Chat-Pfad in osStudio konfigurierbar — keine Quellcode-Änderungen nötig.

Kurzantwort

Auto-Chunking-Pipeline indexiert Notizen, KBs und Dateien bei der Erstellung.
Wissensgraph extrahiert Entitäten + Beziehungen kontinuierlich, abfragbar über den Graph-Screen.
Eigene RAG-Pipelines — definieren Sie Stufen (Retrieve, Filter, Rerank, MMR) pro Path-Konfiguration.
Voyage-Einbettungen + Reranking über einen verwalteten Proxy (kein separater API-Schlüssel).

Was es ist

A knowledge base is only useful if the right passage surfaces at the right moment. osFoundry treats that as a pipeline problem: every note, document, and uploaded file is chunked, embedded, and indexed as it is created, so retrieval is ready the moment content exists — there is no separate “ingest” step to remember and no vector database to operate.

Retrieval is hybrid and configurable. Under the hood a query runs through embedding search and BM25 keyword search, then optional reranking and MMR diversity stages; each Path in osStudio can define its own stages, models, and thresholds. This matters because stuffing whole documents into a prompt hits context-window limits and degrades answer quality — retrieving only the relevant chunks keeps the context focused.

Two layers accumulate on top. The workspace knowledge graph extracts entities and relationships from every chunk continuously, queryable from the Graph screen. And when long conversations compact, memory extraction distills them into durable facts — so decisions made in chat three months ago remain findable, not buried in scrollback.

Wichtige Funktionen

Notizen mit reichem Markdown, Versionshistorie und Three-Way-Merge.
Wissensdatenbanken — versioniert, mehrautorenfähig, exportierbar.
Workspace-Wissensgraph mit Entitätsextraktion auf jedem Chunk.
Memory-Extraktion bei Chat-Kompaktierung — lange Gespräche zu Fakten destilliert.
Konfigurierbare Retrieval-Pipelines (Voyage embed → tantivy BM25 → Reranker → MMR).
Workspace-weite Suche über Notizen, KBs, Chats und Code.

So geht’s in osFoundry

Add sources — Write notes, create knowledge bases, or upload files. Chunking, embedding, and indexing happen automatically on creation.
Ask with grounding — Chat normally — the retrieval pipeline attached to your Path pulls the relevant chunks into context and the model answers against them.
Tune retrieval when needed — In osStudio, adjust the pipeline per Path: swap embedding models, add a reranker, tighten thresholds, or add MMR diversity — no source-code changes.

Anwendungsfälle

Support teams: Load product docs and past tickets into knowledge bases; agents answer new tickets grounded in the actual documentation.
Researchers and writers: Digest long reports without pasting them into chat — retrieval brings in the relevant sections, avoiding context-window overflow.
Teams with long-running projects: Decisions distilled from compacted chats plus the knowledge graph answer “when did we decide this and why” in seconds.

Häufig gestellte Fragen

Does osFoundry use my data to train its models?

No. We don’t train on your data. Embeddings stay in your workspace; retrieval queries are scoped to your workspace; nothing crosses tenant boundaries.

What embedding model does osFoundry use?

Managed Voyage AI by default (no separate API key). You can swap to a local embedding model or BYOK to OpenAI/Cohere via the embedding pipeline config in osStudio.

Can I customise the RAG pipeline per chat?

Yes. Each "Path" in osStudio has its own retrieval pipeline — different stages, models, thresholds, rerankers per use case.

Is the knowledge graph generated automatically?

Yes — entities and relationships are extracted from every note, KB doc, and chat. Browse and edit it in the Graph screen.

Do I need to run a vector database?

No. Chunking, embedding, BM25 indexing, and reranking are built into the platform — there is no separate database to deploy or operate.

How is this different from pasting a document into the chat?

Pasting consumes the context window and degrades on long inputs. Retrieval selects only the chunks relevant to the question, which keeps context focused and works no matter how large the corpus grows.