RAG, knowledge graphs and document parsing
Pre-processingFiles are converted into documents.
Multi-file ConverterChunkingDocuments are split into chunks.
Auto SplitterVectorizationChunks are embedded into vectors.
Cohere Document EmbedderStorageVectors are written to the store.
pgvector Writer
In short
Knowledge bases turn files, websites and connected apps into grounded context agents can retrieve. Ingestion runs through configurable lanes, pre-processing, chunking, vectorization and storage, across 8 vector stores and 8 embedding providers. Turn on a knowledge graph alongside the vector store for GraphRAG, and every retrieval respects the permissions and filters you set at ingestion.
What Knowledge does
- Three ways to fill it
- Upload files directly, crawl a website with depth and path filters, or sync Google Drive, Notion, Dropbox, SharePoint, Box or Confluence on an automatic schedule.
- An editable ingestion pipeline
- Pre-processing, chunking, vectorization and storage are real workflow nodes you can inspect, swap and extend in the same editor.
- Document parsing built in
- A multi-file converter routes PDFs, DOCX, PPTX, images and text to the right converter automatically, with AWS Textract, Google Document AI or an LLM for scans and unusual layouts.
- Permission-aware retrieval
- Filter search by the metadata you attach at ingestion, so a retriever only returns chunks a given user or department is allowed to see.
- Knowledge graphs
- Turn on GraphRAG to extract entities and relationships alongside the vector store, so an agent can follow connections, not just match text.
- Bring your own stack
- Use Dynamiq managed storage or point a knowledge base at your own store, across 8 vector stores and 8 embedding providers, or, from the SDK, search Bedrock Knowledge Bases and Vertex AI RAG Engine directly.
Parsing and extraction
Every file first goes through a multi-file converter that routes it by type: PDF, DOCX, PPTX, CSV and text converters each handle their own format, an LLM image converter reads scans and photos, and an unstructured-file converter catches anything else. The same LLM-based OCR pipeline is available directly through the AI Gateway's document endpoints: parse a PDF or image to clean Markdown, or extract structured JSON that matches a schema you define, such as an invoice's line items and totals.
- Swap in a dedicated converter, such as one just for CSV exports, without touching the rest of the pipeline
- A document splitter cuts by character, word, sentence, page, passage or title, with size and overlap you tune
- Structure-aware splitters (recursive, Markdown header and semantic) keep a section together where fixed-size chunks would split it
Output Template (JSON Schema)
{
"appraised_value": "number",
"property_type": "string",
"flood_zone": "string",
"appraisal_date": "date"
}appraisal-20417.pdf
- appraised_value
- 412000
- property_type
- Single family
- flood_zone
- Zone X
- appraisal_date
- 2026-08-14
Retrieval that respects permissions
Every chunk carries the metadata you attached when it was ingested, department, source, access tier, whatever your documents need, and a retriever's Filters restrict search to chunks matching conditions built from that metadata. The same retriever can run per request rather than per workflow: your integration passes a caller's tenant or department as a parameter at invoke time, and the platform merges it into the retriever's filter before the model ever sees it, so one deployed agent can serve many users without leaking across a boundary.
- Queries embed with the same model used at ingestion; there is no separate query embedder to keep in sync
- A similarity threshold drops weak matches; hybrid search blends vector similarity with keyword matching
- Every retriever call is traced with its query and the chunks it returned, so a wrong answer is easy to audit
- With permission syncing on, Google Drive and Confluence sources apply each person's own access at retrieval
What changed in our servicing policy this quarter?
Two changes apply from July 1. Escrow shortage notices now go out 30 days earlier1, and forbearance requests longer than 90 days need a second reviewer2.
- 1Servicing Policy v7.2SharePoint, updated June 28
- 2Credit committee minutesConfluence, restricted, you have access
Knowledge graphs for multi-step questions
A knowledge base stores chunks and finds them by similarity; a knowledge graph stores the same documents as facts, such as a person working at an organization, and finds them by connection. Turn on Build knowledge graph when you create a knowledge base, choose an extraction model and a graph database, and define the entity types, relationship types and allowed triples the model may extract. Every document you add from then on populates the vector store and the graph together, and an agent with that knowledge base attached can follow relationships an ordinary vector search would miss.
- The extraction schema is an ontology: anything outside it is discarded, not written
- Edit the ontology later from the knowledge base's Ontology tab; changes apply to future extractions only
- The Knowledge Graph Writer resolves duplicate entities across ingestion runs instead of creating copies
Who at lenders based in Lisbon signed the servicing agreement?Answered by walking two relationships, not by similarity
Vector stores
- Pinecone
- Weaviate
- Qdrant
- Milvus
- Chroma
- Elasticsearch
- OpenSearch
- pgvector
Embedding providers
- OpenAI
- Cohere
- AWS Bedrock
- Mistral
- Gemini
- Hugging Face
- IBM watsonx
- Vertex AI
Where teams use it
- Research and knowledge assistantsAnswer questions across your documents and systems, grounded in retrieval that respects who can see what, with citations back to the source.
- Document review and underwritingRead loan files, underwriting submissions and contracts, check them against your rules, and flag exceptions for a reviewer instead of a rubber stamp.
- Insurance claims processingTake first notice of loss by phone or chat, read the documents, check coverage and prepare the claim, with an adjuster deciding every payment.
Works with
- Agent BuilderDesign an agent on a visual canvas or in the open-source Python SDK. Both compile to the same engine, so what you build ships either way.
- IntegrationsConnect a workflow to 2,100+ app integrations, or point it at your own databases, warehouses and MCP servers.
- Models and AI GatewayUse 29 model providers from the SDK, call the most-used models behind one endpoint and one credential, or host and fine-tune open models yourself.
Questions and answers
How many vector stores and embedding providers does Dynamiq support?
8 vector stores and 8 embedding providers are available for a knowledge base, or you can use Dynamiq's managed storage and skip the choice entirely.
Does retrieval respect who is allowed to see what?
Retrieval filters on the metadata attached at ingestion, so you can restrict a search to a department, a tenant or any other boundary your documents carry. Per-request filters can also be injected at invoke time, outside what the model itself can see or change.
What is a knowledge graph and when do I need one?
A knowledge graph extracts entities and relationships from your documents alongside the normal vector store, so an agent can answer questions that depend on connections between things, not just similar wording. Turn it on when you create a knowledge base and define which entity and relationship types matter to your documents.
Can I change the embedding provider later?
You can, but queries are always embedded with the same model used at ingestion, so switching providers makes existing vectors unsearchable until you reprocess the affected items.
Do I have to use Dynamiq's managed vector storage?
No. A knowledge base uses Dynamiq managed storage by default, backed by Weaviate, but you can point it at your own vector store connection instead and keep the same managed ingestion pipeline.
See an agent on your own workflow.
Bring a process and its documents. Our engineers will show you how Dynamiq runs it, in your environment or ours.