DeepsetFileUploader

Upload the indexed documents to a deepset workspace as text files.

Basic Information

Type: deepset_cloud_custom_nodes.augmenters.deepset_file_uploader.DeepsetFileUploader
Components it can connect with:
- Components accepting a list of Document objects as input and output.

Inputs

Required Inputs

Name	Type	Description
`documents`	LIst of `Document` objects	The list of documents to turn into text files and save in a workspace.

Optional Inputs

Name	Type	Default	Description
`raise_on_failure`	Boolean	`False`	Returns an error message if it fails to upload the documents.

Outputs

Name	Type	Description
`documents`	List of `Document` objects	The documents produced by the indexing pipeline.

Overview

DeepsetFileUploader is used in indexes. You can use it with a web crawling component to upload the crawled documents to a specified workspace. It can also upload any other document the index creates. You can specify the workspace where you want to save the created files in the workspace parameter.

Usage Example

This is an example of an index where FileUploader receives documents from DeepsetFirecrawlWebScraper, uploads them to deepset AI Platform, and sends them to DocumentWriter to write into a document store:

Here's the full YAML configuration you can paste into the YAML editor:

components:
  FileClassifier:
    type: haystack.components.routers.file_type_router.FileTypeRouter
    init_parameters:
      mime_types:
      - text/csv
      - application/vnd.openxmlformats-officedocument.spreadsheetml.sheet
  OutputAdapter:
    type: haystack.components.converters.output_adapter.OutputAdapter
    init_parameters:
      template: |-
        {% set str_list = [] %}
        {% for document in documents %}
          {% set _ = str_list.append(document.content) %}
        {% endfor %}
        {{ str_list }}
      output_type: typing.List[str]
  DocumentWriter:
    type: haystack.components.writers.document_writer.DocumentWriter
    init_parameters:
      document_store:
        type: haystack_integrations.document_stores.opensearch.document_store.OpenSearchDocumentStore
        init_parameters:
          embedding_dim: 768
          similarity: cosine
      policy: NONE
  DeepsetCSVRowsToDocumentsConverter:
    type: deepset_cloud_custom_nodes.converters.csv_rows_to_documents.DeepsetCSVRowsToDocumentsConverter
    init_parameters:
      content_column: urls
      encoding: utf-8
  DeepsetFirecrawlWebScraper:
    type: deepset_cloud_custom_nodes.crawler.firecrawl.DeepsetFirecrawlWebScraper
    init_parameters: {}
  XLSXToDocument:
    type: deepset_cloud_custom_nodes.converters.xlsx.XLSXToDocument
    init_parameters:
      document_per: sheet
      content_column: content
      sheet_name:
  DocumentJoiner:
    type: haystack.components.joiners.document_joiner.DocumentJoiner
    init_parameters:
      join_mode: concatenate
      weights:
      top_k:
      sort_by_score: true
  DeepsetFileUploader:
    type: deepset_cloud_custom_nodes.augmenters.deepset_file_uploader.DeepsetFileUploader
    init_parameters:
      workspace:
      api_key:
        type: env_var
        env_vars:
        - DEEPSET_CLOUD_API_KEY
        strict: false
      write_mode: OVERWRITE
      base_url: https://api.cloud.deepset.ai/api/v1

connections:
- sender: OutputAdapter.output
  receiver: DeepsetFirecrawlWebScraper.urls
- sender: FileClassifier.application/vnd.openxmlformats-officedocument.spreadsheetml.sheet
  receiver: XLSXToDocument.sources
- sender: DocumentJoiner.documents
  receiver: OutputAdapter.documents
- sender: XLSXToDocument.documents
  receiver: DocumentJoiner.documents
- sender: DeepsetCSVRowsToDocumentsConverter.documents
  receiver: DocumentJoiner.documents
- sender: FileClassifier.text/csv
  receiver: DeepsetCSVRowsToDocumentsConverter.sources
- sender: DeepsetFirecrawlWebScraper.documents
  receiver: DeepsetFileUploader.documents
- sender: DeepsetFileUploader.documents
  receiver: DocumentWriter.documents

max_runs_per_component: 100

metadata: {}

inputs:
  files:
  - FileClassifier.sources

Parameters

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Possible Values	Description
`workspace`	String		The name of the deepset workspace where you want to save the resulting TXT files. Required.
`api_key`	Secret	`Secret.from_env_var("DEEPSET_CLOUD_API_KEY")`	deepset API key. By default, it's read from the `DEEPSET_CLOUD_API_KEY` environment variable. Required.
`write_mode`	Literal	`KEEP` `OVERWRITE` (default) `FAIL`	Specifies what to do if a file with the same name already exists in the workspace. Possible values: - `KEEP`: Keeps both files. - `OVERWRITE`: Overwrites the existing file with the uploaded one. - `FAIL`: Fails to upload. Required.
`base_url`	String	Default: `https://api.cloud.deepset.ai/api/v1`	The URL for deepset deployment. Required.

Run Method Parameters

These are the parameters you can configure for the component's run() method. This means you can pass these parameters at query time through the API, in Playground, or when running a job. For details, see Modify Pipeline Parameters at Query Time.

Run() method parameters take precedence over initialization parameters.

Parameter	Type	Possible Values	Description
`documents`	List of `document` objects		The documents to upload. Required.
`raise_on_failure`	Boolean	`True` `False` Default: `False`	Raises an error if the component fails to upload the documents. Required.

Updated 5 months ago