You are here:
Unstructured Data Workflow
Regardless of your use case for unstructured data, there's a general workflow to ingest and process it in Data 360.
Required Editions
| Available in: All Editions supported by Data 360. See Data 360 edition availability. |
| User Permissions Needed | |
|---|---|
| To set up Data 360 | System admin profile OR Data Cloud Architect |
| To ingest unstructured data and create search indexes | One of these permission sets:
|
See Also
Step 1: Set up Data 360 In Your Org
Before you can connect unstructured data, make sure that Data 360 is provisioned and enabled in your org.
Step 2: Ingest Unstructured Data
Depending on your use case, Data 360 has connectors purpose built for ingesting unstructured data from third-party applications or sources. You can also use the Salesforce CRM connector to ingest knowledge article data.
Some connectors, such as those for Amazon S3, Azure, or Google Cloud Storage, require file notification pipelines. Review the documentation for each connector.
Refer to the Unstructured Data Reference for more information.
Step 3: Process Data
Use Document AI in Data 360 to read and import unstructured or semi-structured data from documents like invoices, resumes, lab reports, and purchase orders. Using AI, Data 360 extracts data from those documents into Data Lake Objects (DLO), which represent schemas for the extracted data. From this point, your data is available for search index processing and retrieval from automation flows or AI agent actions.
See Document AI.
Step 4: Create a Search Index
After setting up an unstructured data connection, you create a vector search index or a hybrid search index using either Data 360 defaults or the advanced builder. The search index helps ensure that outputs are finely tuned to your users' intents and contexts.
See Create a Vector Search Index with Advanced Setup or Create a Hybrid Search Index with Advanced Setup.
Step 5: Use Unstructured Data in a Workflow
Using unstructured data in Salesforce improves your AI agent, automation, and analytics workflows, improving customer experiences and operational efficiency. Based on your use case, consider these resources.
- Use Query API to Run Vector Search Queries or to Run Hybrid Search Queries.
- Retrieval Augmented Generation (RAG) in Data 360 is a framework for grounding large language model (LLM) prompts. By augmenting prompts with accurate, current, and pertinent information, RAG improves the relevance and value of LLM responses for users. See Using Retrieval Augmented Generation.
- Bring the power of conversational AI to your business with Agentforce. Build intelligent, trusted, and customizable AI agents and empower your users to get more done with Salesforce. See Agentforce Agents.
