insert()
Insert text content into the knowledge base. Vrin chunks the text, extracts facts (entities + relationships), and indexes everything for retrieval.insert() waits for processing to complete. Pass wait=False to get a job ID and poll later.
Parameters
string
required
Text content to insert into the knowledge base.
string
default:"Untitled"
Document title. Used in search results and source attribution.
List[str]
Optional tags for categorization and filtering.
Dict[str, Any]
Optional metadata dict attached to the document.
bool
default:"True"
If
True, poll until processing completes and return the result dict.
If False, return the job ID string immediately.float
default:"2.0"
Seconds between status polls when
wait=True.float
default:"300.0"
Maximum seconds to wait when
wait=True. Raises TimeoutError if exceeded.Synchronous (default)
Asynchronous
get_job_status()
Check the status of an async insertion job.Parameters
string
required
The job ID returned by
insert(wait=False).Returns
pending -> chunking -> extracting -> storing -> completed.
wait_for_job()
Poll a job until completion or timeout. Logs progress as the job moves through stages.Parameters
string
required
The job ID to wait on.
float
default:"2.0"
Seconds between status polls.
float
default:"300.0"
Maximum seconds to wait. Raises
TimeoutError if exceeded.Exceptions
JobFailedError— The job failed during processing.TimeoutError— The job did not complete withinmax_waitseconds. Useget_job_status()to check current state.
get_knowledge_graph()
Get knowledge graph visualization data showing entities and their relationships.Parameters
int
default:"100"
Maximum number of graph elements to return.
What happens during insertion
When you callinsert(), Vrin:
- Chunks the text into overlapping segments optimized for retrieval
- Extracts facts — entities, relationships, and attributes using an LLM
- Stores facts in the knowledge graph (Neptune) with
{model, timestamp, confidence}metadata - Indexes chunks in the vector store (OpenSearch) with BM25 + kNN embeddings
- Returns a summary with fact counts and chunk IDs