cognee/cognee/api/v1/update/update.py

100 lines
4.2 KiB
Python

from uuid import UUID
from typing import Union, BinaryIO, List, Optional
from cognee.modules.users.models import User
from cognee.api.v1.delete import delete
from cognee.api.v1.add import add
from cognee.api.v1.cognify import cognify
async def update(
data_id: UUID,
data: Union[BinaryIO, list[BinaryIO], str, list[str]],
dataset_id: UUID,
user: User = None,
node_set: Optional[List[str]] = None,
vector_db_config: dict = None,
graph_db_config: dict = None,
preferred_loaders: List[str] = None,
incremental_loading: bool = True,
):
"""
Update existing data in Cognee.
Supported Input Types:
- **Text strings**: Direct text content (str) - any string not starting with "/" or "file://"
- **File paths**: Local file paths as strings in these formats:
* Absolute paths: "/path/to/document.pdf"
* File URLs: "file:///path/to/document.pdf" or "file://relative/path.txt"
* S3 paths: "s3://bucket-name/path/to/file.pdf"
- **Binary file objects**: File handles/streams (BinaryIO)
- **Lists**: Multiple files or text strings in a single call
Supported File Formats:
- Text files (.txt, .md, .csv)
- PDFs (.pdf)
- Images (.png, .jpg, .jpeg) - extracted via OCR/vision models
- Audio files (.mp3, .wav) - transcribed to text
- Code files (.py, .js, .ts, etc.) - parsed for structure and content
- Office documents (.docx, .pptx)
Workflow:
1. **Data Resolution**: Resolves file paths and validates accessibility
2. **Content Extraction**: Extracts text content from various file formats
3. **Dataset Storage**: Stores processed content in the specified dataset
4. **Metadata Tracking**: Records file metadata, timestamps, and user permissions
5. **Permission Assignment**: Grants user read/write/delete/share permissions on dataset
Args:
data_id: UUID of existing data to update
data: The latest version of the data. Can be:
- Single text string: "Your text content here"
- Absolute file path: "/path/to/document.pdf"
- File URL: "file:///absolute/path/to/document.pdf" or "file://relative/path.txt"
- S3 path: "s3://my-bucket/documents/file.pdf"
- List of mixed types: ["text content", "/path/file.pdf", "file://doc.txt", file_handle]
- Binary file object: open("file.txt", "rb")
dataset_name: Name of the dataset to store data in. Defaults to "main_dataset".
Create separate datasets to organize different knowledge domains.
user: User object for authentication and permissions. Uses default user if None.
Default user: "default_user@example.com" (created automatically on first use).
Users can only access datasets they have permissions for.
node_set: Optional list of node identifiers for graph organization and access control.
Used for grouping related data points in the knowledge graph.
vector_db_config: Optional configuration for vector database (for custom setups).
graph_db_config: Optional configuration for graph database (for custom setups).
dataset_id: Optional specific dataset UUID to use instead of dataset_name.
Returns:
PipelineRunInfo: Information about the ingestion pipeline execution including:
- Pipeline run ID for tracking
- Dataset ID where data was stored
- Processing status and any errors
- Execution timestamps and metadata
"""
await delete(
data_id=data_id,
dataset_id=dataset_id,
user=user,
)
await add(
data=data,
dataset_id=dataset_id,
user=user,
node_set=node_set,
vector_db_config=vector_db_config,
graph_db_config=graph_db_config,
preferred_loaders=preferred_loaders,
incremental_loading=incremental_loading,
)
cognify_run = await cognify(
datasets=[dataset_id],
user=user,
vector_db_config=vector_db_config,
graph_db_config=graph_db_config,
incremental_loading=incremental_loading,
)
return cognify_run