Home / Features / Knowledge and memory
osFoundry पर knowledge bases, memory, और RAG
Auto-extracted entities, knowledge graphs, custom retrieval pipelines, और reranked RAG — सब osStudio में configurable।
osFoundry AI के around बना एक knowledge platform है: हर note, document, और uploaded file auto-chunked, embedded, और indexed होती है। एक workspace knowledge graph उन सबसे entities और relationships extract करता है जिन पर आपने काम किया है। Custom retrieval pipelines (reranking, MMR diversity, और multi-stage stages के साथ) osStudio में प्रति chat path configurable हैं — कोई source-code changes आवश्यक नहीं।
संक्षिप्त उत्तर
- Auto-chunking pipeline notes, KBs, और files को बनाते ही index करती है।
- Knowledge graph entities + relationships को निरंतर extract करता है, Graph screen के माध्यम से queryable।
- Custom RAG pipelines — प्रति Path config stages (retrieve, filter, rerank, MMR) define करें।
- एक managed proxy के माध्यम से Voyage embeddings + reranking (कोई अलग API key नहीं)।
यह क्या है
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.
मुख्य क्षमताएँ
- Rich Markdown, version history, और three-way merge के साथ Notes।
- Knowledge bases — versioned, multi-author, exportable।
- हर chunk पर entity extraction के साथ Workspace knowledge graph।
- Chat compaction पर Memory extraction — long conversations facts में distilled।
- Configurable retrieval pipelines (Voyage embed → tantivy BM25 → reranker → MMR)।
- Notes, KBs, chats, और code में Workspace-wide search।
osFoundry में कैसे करें
- 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.
उपयोग के मामले
- 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.
सामान्य प्रश्न
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.
संबंधित सुविधाएँ