KDB.AI - Unstructured

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

Batch process all your records to store structured outputs in KDB.AI.

The requirements are as follows.

A KDB.AI Cloud or server instance. Sign Up for KDB.AI Cloud: Starter Edition. Set up KDB.AI Server.
The instance’s endpoint URL. Get the KDB.AI Cloud endpoint URL. Get the KDB.AI Server endpoint URL.
An API key. Create the API key.

The name of the target table to access. Create the table.

KDB.AI requires the target table to have a defined schema before Unstructured can write to the table. The recommended table schema for Unstructured contains the fields id, element_id, document, metadata, and embeddings, as follows. This example code demonstrates the use of the KDB.AI Client for Python to create a table with this recommended schema, along with creating a vector index that contains 3072 dimensions:

Python
import kdbai_client as kdbai
import os

session = kdbai.Session(
    endpoint=os.getenv("KDBAI_ENDPOINT"),
    api_key=os.getenv("KDBAI_API_KEY")
)

db = session.database("default")

schema = [
    {
        "name": "id",
        "type": "str"
    },
    {
        "name": "element_id",
        "type": "str"
    },
    {
        "name": "document",
        "type": "str"
    },
    {
        "name": "metadata", 
        "type": "general"
    },
    {
        "name": "embeddings",
        "type": "float32s"
    }
]

indexes = [ 
    {
        "name": "vectorIndex",
        "type": "flat", 
        "params": {
            "dims": 3072,
            "metric": "L2"
        },
        "column": "embeddings"
    }
]

table = db.create_table(
    table=os.getenv("KDBAI_TABLE"),
    schema=schema,
    indexes=indexes
)

print(f"The table named '{table.name}' now exists.")

The KDB.AI connector dependencies:

CLI, Python
pip install "unstructured-ingest[kdbai]"

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

The following environment variables:

KDBAI_ENDPOINT - The KDB.AI instance’s endpoint URL, represented by --endpoint (CLI) or endpoint (Python).
KDBAI_API_KEY - The KDB.AI API key, represented by --api-key (CLI) or api_key (Python).
KDBAI_TABLE - The name of the target table, represented by --table-name (CLI) or table_name (Python).

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.

#!/usr/bin/env bash

# Chunking and embedding are optional.

unstructured-ingest \
  local \
    --input-path $LOCAL_FILE_INPUT_DIR \
    --chunking-strategy by_title \
    --embedding-provider huggingface \
    --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}" \
  kdbai \
    --endpoint $KDBAI_API_KEY \
    --api-key $KDBAI_API_KEY \
    --table-name $KDBAI_TABLE

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 sales@unstructured.io.

Ingestion