Chroma

This page was recently updated. What do you think about it? Let us know!.

Batch process all your records to store structured outputs in a Chroma account.

The requirements are as follows.

• A Chroma server. See Deployment.

  For example, here is a video about how to deploy a Chroma server to AWS:

• The Chroma server’s hostname or IP address, and the server’s port number.

• If you are not connecting to the server through HTTP, the path to the server instance.

• The name of the tenant that you want to access on the server.

• The name of the database that you want to access in the tenant.

• The name of the collection that you want to access in the database.

The Chroma connector dependencies:

CLI, Python

pip install "unstructured-ingest[chroma]"

You might also need to install additional dependencies, depending on your needs. Learn more.

The following environment variables:

• CHROMA_HOST - The , represented by --host (CLI) or host (Python).
• CHROMA_PORT - The , represented by --port (CLI) or port (Python).
• CHROMA_TENANT - The name of the tenant that you want to access on the Chroma server, represented by --tenant (CLI) or tenant (Python).
• CHROMA_DATABASE - The name of the database that you want to access in the tenant, represented by --database (CLI) or database (Python).
• CHROMA_COLLECTION - The name of the collection that you want to access in the database, represented by --collection-name (CLI) or collection_name (Python).

Additional settings include:

• --path (CLI) or path (Python): The location where Chroma is persisted if you are not connecting through HTTP.
• --settings (CLI) or settings (Python): A dictionary of settings to communicate with the Chroma server, for example: '{"persist_directory":"./chroma-persist"}'.
• --headers (CLI) or headers (Python): A dictionary of headers to send to the Chroma server, for example: '{"Authorization":"Basic()"}'.
• --ssl (CLI) or ssl (Python): True to use SSL for the connection.

Now call the Unstructured CLI or Python. The source connector can be any of the ones supported. This example uses the local source connector.

This example sends files to Unstructured for processing by default. To process files locally instead, see the instructions at the end of this page.

CLI

#!/usr/bin/env bash

# Chunking and embedding are optional.

unstructured-ingest \
  local \
    --input-path $LOCAL_FILE_INPUT_DIR \
    --output-dir $LOCAL_FILE_OUTPUT_DIR \
    --chunk-elements \
    --embedding-provider huggingface \
    --num-processes 2 \
    --verbose \
    --work-dir $WORK_DIR \
    --partition-by-api \
    --api-key $UNSTRUCTURED_API_KEY \
    --partition-endpoint $UNSTRUCTURED_API_URL \
    --strategy hi_res \
    --additional-partition-args="{\"split_pdf_page\":\"true\", \"split_pdf_allow_failed\":\"true\", \"split_pdf_concurrency_level\": 15}" \
  chroma \
    --host $CHROMA_HOST \
    --port $CHROMA_PORT \
    --collection-name $CHROMA_COLLECTION \
    --tenant $CHROMA_TENANT \
    --database $CHROMA_DATABASE \
    --settings "{\"persist_directory\":\"./chroma-persist\"}" \
    --headers "{\"Authorization\":\"Basic()\"}" \
    --batch-size 80 \
    --ssl

For the Unstructured Ingest CLI and the Unstructured Ingest Python library, you can use the --partition-by-api option (CLI) or partition_by_api (Python) parameter to specify where files are processed:

• To do local file processing, omit --partition-by-api (CLI) or partition_by_api (Python), or explicitly specify partition_by_api=False (Python).

  Local file processing does not use an Unstructured API key or API URL, so you can also omit the following, if they appear:

  • --api-key $UNSTRUCTURED_API_KEY (CLI) or api_key=os.getenv("UNSTRUCTURED_API_KEY") (Python)
  • --partition-endpoint $UNSTRUCTURED_API_URL (CLI) or partition_endpoint=os.getenv("UNSTRUCTURED_API_URL") (Python)
  • The environment variables UNSTRUCTURED_API_KEY and UNSTRUCTURED_API_URL

• To send files to the Unstructured Partition Endpoint for processing, specify --partition-by-api (CLI) or partition_by_api=True (Python).

  Unstructured also requires an Unstructured API key and API URL, by adding the following:

  • --api-key $UNSTRUCTURED_API_KEY (CLI) or api_key=os.getenv("UNSTRUCTURED_API_KEY") (Python)
  • --partition-endpoint $UNSTRUCTURED_API_URL (CLI) or partition_endpoint=os.getenv("UNSTRUCTURED_API_URL") (Python)
  • The environment variables UNSTRUCTURED_API_KEY and UNSTRUCTURED_API_URL, representing your API key and API URL, respectively.
  You must specify the API URL only if you are not using the default API URL for Unstructured Ingest, for example, if you are using a self-hosted instance of the Unstructured API.

  The default API URL for Unstructured Ingest is https://api.unstructuredapp.io/general/v0/general, which is the API URL for the Unstructured Partition Endpoint.

  If you do not have an API key, get one now.

  If the Unstructured API is self-hosted, the process for generating Unstructured API keys, and the Unstructured API URL that you use, are different. For details, contact Unstructured Sales at [e-mail].