Skip to main content

Update Record

Update Record in Text Collection

To update an existing record, use the update_record method. This method requires the following parameters:

  • collection_id: The identifier of the collection where the record is stored.
  • record_id: The identifier of the record to be updated.
  • content: (Optional) The new textual content of the record.
  • type: (Optional) The type of record. Supported types are text, web, and file.
  • url: (Optional) The URL of the webpage to be scraped.
  • file_id: (Optional) The file ID of the record to be updated.
  • text_splitter: (Optional) A dictionary containing the text splitter configuration.
  • metadata: (Optional) A dictionary containing metadata for the record.

Ensure that the combination of content, type, url, and file_id is valid. Specify the type and set a value for one of content, url, or file_id parameters that match the type.

Example of Updating a Record with New Content:

import taskingai

record = taskingai.retrieval.update_record(
collection_id="YOUR_COLLECTION_ID",
record_id="YOUR_RECORD_ID",
type="text",
content="Machine learning is a subfield of artificial intelligence...",
text_splitter={"type": "token", "chunk_size": 200, "chunk_overlap": 20},
)
note

After updating the content, all the old text chunks associated with the record will be deleted and replaced with the new ones.

Example of Updating Metadata:

import taskingai

record = taskingai.retrieval.update_record(
collection_id="YOUR_COLLECTION_ID",
record_id="YOUR_RECORD_ID",
metadata={"file_name": "machine_learning.pdf", "author": "James Brown"}
)

Update Record in QA Collection

To update an existing record, use the update_record method. The related parameters are as follows:

  • collection_id: The identifier of the collection where the record is stored.
  • record_id: The identifier of the record to be updated.
  • type: The type of record. It is always qa_sheet.
  • file_id: The file ID of the record to be updated.
  • metadata: The metadata of the record.

Example of Updating a Record with New Content:

import taskingai

new_file = taskingai.file.upload_file(file=open("PATH_TO_FILE", "rb"), purpose="qa_record_file")
print(f"Uploaded file ID: {new_file.file_id}")

record = taskingai.retrieval.update_record(
collection_id="YOUR_COLLECTION_ID",
record_id="YOUR_RECORD_ID",
type="qa_sheet",
file_id=new_file.file_id,
)
note

After updating the content, all the old Q&A chunks associated with the record will be deleted and replaced with the new ones.

Example of Updating Metadata:

import taskingai

record = taskingai.retrieval.update_record(
collection_id="YOUR_COLLECTION_ID",
record_id="YOUR_RECORD_ID",
metadata={"file_name": "new_product_qa_sheet.csv"},
)