Standalone Knowledge Manager
Agentic RAG in Agent
When RAG is configured in an agent, the SDK automatically creates asearchKnowledge tool that the LLM can decide when to use. This is more efficient than always searching, as the LLM only searches when necessary.
Multiple Vector Stores
Managing Documents
Add text documents:Async Ingestion for Large Files
Available since SDK
1.3.2 (platform July 2026). For small files addFile still works — async ingestion is the recommended path for anything big.addFile processes the file synchronously — fine for a manual or an FAQ, but a 50k-row catalog would hold the HTTP request open for minutes. ingestFile uploads the file, returns in seconds with a job id, and the platform embeds everything in the background with batched embeddings and checkpoint resume (if a worker restarts mid-job, ingestion continues from where it stopped instead of starting over).
CSV: one document per row
CSV files are ingested one document per row — ideal for product catalogs and structured data. Each row becomes a searchableColumn: value document. You can control which columns are embedded and which go to metadata:
Data hygiene
Optional cleanup applied server-side before embedding — useful when the source data carries HTML, URLs, or placeholder values that hurt search quality:Job status
getIngestionJob(jobId) (and the onProgress callback) return:
waitForCompletion throws if the job fails or the timeout (default 30 min) elapses — on timeout the job keeps running server-side and you can keep polling.
Metadata Filters
Filter search results by document metadata using thefilters option. Each key maps to a metadata field.
Simple equality filter:
value and operator for non-equality comparisons:
= (default), !=, >, >=, <, <=, @> (contains), <@ (contained by).
Filters also work in agent RAG config:
RAG Interceptor & Rerank
Interceptor - Filter & Transform Results:reciprocal-rank-fusion- Standard RRF algorithmscore-boost- Boost results containing keywordsmetadata-weight- Weight by metadata field valuecustom- Custom scoring function
Next Steps
Agents
Learn about agents
Use Cases
See RAG examples