​
ingest_text

Ingest a text document into DataBridge.

def ingest_text(
    content: str,
    filename: Optional[str] = None,
    metadata: Optional[Dict[str, Any]] = None,
    rules: Optional[List[RuleOrDict]] = None,
    use_colpali: bool = True,
) -> Document

​
Parameters

  • content (str): Text content to ingest
  • filename (str, optional): Optional filename for the document
  • metadata (Dict[str, Any], optional): Optional metadata dictionary
  • rules (List[RuleOrDict], optional): Optional list of rules to apply during ingestion. Can be:
    • MetadataExtractionRule: Extract metadata using a schema
    • NaturalLanguageRule: Transform content using natural language
  • use_colpali (bool, optional): Whether to use ColPali-style embedding model to ingest the text (slower, but significantly better retrieval accuracy for text and images). Defaults to True.

​
Returns

  • Document: Metadata of the ingested document

​
Example

from databridge.sync import DataBridge
from databridge.rules import MetadataExtractionRule, NaturalLanguageRule
from pydantic import BaseModel

class DocumentInfo(BaseModel):
    title: str
    author: str
    date: str

db = DataBridge()

doc = db.ingest_text(
    "Machine learning is fascinating...",
    metadata={"category": "tech"},
    rules=[
        # Extract metadata using schema
        MetadataExtractionRule(schema=DocumentInfo),
        # Transform content
        NaturalLanguageRule(prompt="Shorten the content, use keywords")
    ]
)
closeingest_file