- Overview
- Act! 365
- ActiveCampaign
- Adobe Acrobat Sign
- Adobe PDF Services
- Amazon Bedrock
- Amazon Connect
- Amazon Polly
- Amazon SES
- Amazon Transcribe
- Anthropic Claude
- Asana
- AWeber
- Azure AI Document Intelligence
- Azure Maps
- BambooHR
- Box
- Release notes
- About the Box activity package
- Project compatibility
- Add Shared Link to File
- Add Shared Link to Folder
- Search for Content
- Cancel Sign Request
- List Sign Requests
- Create Sign Request
- Resend Sign Request
- Copy File
- Delete File
- Download File
- Get File Info
- Get Folder Items
- Upload File
- Copy Folder
- Create Folder
- Delete Folder
- Delete Record
- Get Record
- Insert Record
- Replace Record
- List All Records
- Brevo
- Calendly
- Campaign Monitor
- Cisco Webex Teams
- Citrix ShareFile
- Clearbit
- Confluence Cloud
- Constant Contact
- Coupa
- Customer.io
- Datadog
- Deputy
- Discord - Preview
- DocuSign
- Drip
- Dropbox
- Dropbox Business
- Egnyte
- Epic FHIR R4 - Preview
- Eventbrite
- Exchangerates
- Expensify
- Facebook
- Freshbooks
- Freshdesk
- Freshservice
- GetResponse
- GitHub
- Google Maps
- Google Speech-to-Text
- Google Text-to-Speech
- Google Vertex
- Google Vision - Preview
- GoToWebinar
- Release Notes
- About the GoToWebinar activity package
- Project Compatibility
- Delete Webinar
- Get Webinar
- Get Webinar Meeting Times
- Get Webinar Registrant
- Get Webinar Start URL
- List Account Webinars
- List All In Session Webinars
- List All Webinar Attendees
- List All Webinar Registrants
- List All Webinars
- Quick Create Webinar
- Quick Update Webinar
- Search Recording Assets
- Delete Record
- Get Record
- Insert Record
- List All Records
- List Records
- API References
- Greenhouse
- Hootsuite
- HTTP Webhook
- Hubspot CRM
- HubSpot Marketing
- iContact
- Insightly CRM
- Intercom
- Jira
- Release notes
- About the Jira activity package
- Project compatibility
- Create Issue
- Add Issue Attachment
- Download Issue Attachment
- Get Instance Details
- Add Comment
- Get Comments
- Get Issue
- Search Issues by JQL
- Update Issue
- Update Issue Assignee
- Find User by Email Address or Display Name
- Update Issue Status
- Delete Record
- Get Record
- Insert Record
- List All Records
- Replace Record
- Upsert Record
- Invoke Operation
- Delete Issue
- Event Trigger
- Keap
- Klaviyo
- LinkedIn
- Mailchimp
- Mailjet
- MailerLite
- Mailgun
- Marketo
- Microsoft Azure OpenAI
- Microsoft Dynamics CRM
- Microsoft Sentiment
- Microsoft Teams
- Release Notes
- About the Microsoft Teams activity package
- Project compatibility
- Create Channel
- Invite Member to Channel
- List All Channels
- Send Individual Chat Message
- Reply to Channel Message
- Create Online Teams Meeting
- Send Channel Message
- Send Group Chat Message
- Get Channel by Name
- Get Individual Chat
- Get Team by Name
- Invite User to Team
- List All Channel Messages
- List All Chat Messages
- List All Team Members
- Get Online Teams Meeting
- List All Recordings
- List All Transcripts
- Download Meeting Transcript/Recording
- List All Records
- Insert Record
- Update Record
- Get Record
- Delete Record
- Technical references
- Microsoft Translator
- Microsoft Vision
- Miro
- Okta
- OpenAI
- Oracle Eloqua
- Oracle NetSuite
- Release Notes
- About the Oracle NetSuite activity package
- Project Compatibility
- Delete Record
- Get Record
- Insert Record
- List All Records
- Update Record
- Create Basic Company Customer
- Create Basic Company Vendor
- Create Basic Contact
- Create Basic Individual Customer
- Create Basic Individual Vendor
- Create Basic Support Case
- Update Basic Company Customer
- Update Basic Company Vendor
- Update Basic Contact
- Update Basic Individual Customer
- Update Basic Individual Vendor
- Update Basic Support Case
- Customer Created
- Customer Updated
- Record Created
- Record Updated
- Support Case Raised
- Support Case Updated
- Vendor Created
- Vendor Updated
- PagerDuty
- Paypal
- PDFMonkey
- Pinecone
- Pipedrive
- QuickBooks Online
- Quip
- Salesforce
- Release Notes
- About the Salesforce activity package
- Project Compatibility
- Create Account
- Update Account
- Create Contact
- Update Contact
- Create Lead
- Update Lead
- Create Opportunity
- Upload File
- Download File
- Search Records
- Get Opportunity
- Get Lead
- Get Contact
- Get Account
- Add File to Record
- Create Bulk Upload Job
- Get Bulk Job Info
- Starts or Aborts Bulk Job
- Download SOQL Bulk Job Results
- Download Unprocessed Records of Bulk Upload
- Create Bulk Download Job Using SOQL
- Search Using String
- Get Object Fields
- Insert Record
- Get Record
- Delete Record
- Update Record
- List All Records
- Salesforce Marketing Cloud
- SAP BAPI - Preview
- SAP Build Process Automation - Preview
- SAP Cloud for Customer
- SAP Concur
- SendGrid
- ServiceNow
- Release Notes
- About the ServiceNow activity package
- Project Compatibility
- Troubleshooting
- Create New Incident
- Create Incident Task
- List All Incidents
- Update Incident
- Add Attachment
- Download Attachment
- Get Incident Task
- Get Attachment
- List All Attachments
- List All Incident Tasks
- Update Incident Task
- When an Event Happens
- Delete Attachment
- Delete Record
- Get Record
- Insert Record
- List All Records
- Update Record
- Incident Created
- Incident Updated
- Incident Task Created
- Incident Task Updated
- Record Created
- Record Updated
- Shopify
- Slack
- Release Notes
- About the Slack activity package
- Project compatibility
- Create Channel
- Invite Users to Channel
- Remove User from Channel
- Send File to Channel
- Send Message to Channel
- Send Message to User
- Send Reply
- Send Button Response
- Create User Group
- Get User
- List All User Groups
- List All Users
- Set Channel Topic
- Join Channel
- Archive Channel
- Create Group Direct Message
- Get Channel Info
- Button Clicked
- Troubleshooting
- SmartRecruiters
- Smartsheet
- Release notes
- About the Smartsheet activity package
- Project compatibility
- Attach URL to Sheet
- Add Column
- Update Column
- Add Row
- Update Row
- Get Sheet
- List All Sheets
- Attach File to Comment
- Search Everything
- Update Sheet
- Create Sheet from Template
- Send Sheet Via Email
- List All Folders
- Download Attachment
- Attach File to Row
- Attach URL to Row
- Attach File to Sheet
- List All Workspaces
- List All Attachments
- Delete Row
- Download Sheet
- Search Sheets
- Insert Record
- Get Record
- List All Records
- Delete Record
- Snowflake
- Stripe
- Sugar Enterprise
- Sugar Professional
- Sugar Sell
- Sugar Serve
- TangoCard
- Todoist
- Trello
- Twilio
- UiPath GenAI Activities
- IBM WatsonX
- WhatsApp Business
- WooCommerce
- Workable
- Workday
- Workday REST - Preview
- X (formerly Twitter)
- Xero
- Release notes
- About the Xero activity package
- Project compatibility
- Create Contact
- List All Contacts
- Add Attachment to Contact
- Get Balance Sheet Report
- Get BAS Report
- Get GST Report
- Get Bank Summary Report
- Get Aged Receivables by Contact Report
- Get Attachments of a Contact
- Get Budget Summary Report
- Get Profit and Loss Report
- Get Trial Balance Report
- Get Executive Summary Report
- Get Aged Payables by Contact Report
- List Reports
- Delete Record
- List All Records
- Get Record
- Insert Record
- Replace Record
- Youtube
- Zendesk
- Zoho Campaigns
- Zoho Desk
- Zoho Mail
- Zoom
- ZoomInfo
Best practices
This section includes information on how to use Context grounding effectively.
To start using Context Grounding, follow these steps first:
- Make sure you use Studio Web or Studio Desktop version 2024.4 or newer.
- In Automation Cloud, in Integration Service, establish a connection to the UiPath GenAI Activities connector.
To use Context Grounding you need a dataset (e.g., a group of documents) readily available. Then, Context Grounding can interact with your data in three phases:
- Establish your data source for Context Grounding.
- Use an automation or upload files directly into an Orchestrator bucket, in a shared Orchestrator folder. The Orchestrator folder must be shared, because Context Grounding is a tenant-scoped.
- You must have Edit permissions for that folder to ensure you can upload or remove documents from the bucket. No additional permissions are required.
- Ingest data from your data source into Context Grounding.
- Use the Index and Ingest (Public Preview) and Delete Index (Public Preview) activities to manage the lifecycle of your data.
- Query and ground prompts with your data.
- Use Content Generation to query over documents and use information to augment or ground prompts.
The Index and Ingest (Public Preview) activity provides an asynchronous mechanism to ingest documents that are uploaded and stored in Orchestrator buckets.
In the Index and Ingest (Public Preview) activity, under Additional properties, the Data type dropdown field allows you to specify the file type you would like to ingest:
- PDF - to ingest PDF files (default selection).
- CSV - to ingest CSV files.
- JSON - to ingest JSON files.
If you add more files to your Orchestrator bucket, you need to re-run this activity to ensure the index remains up to date.
The File glob pattern field is designed to the file type you set Data type:
- If you have one data type in your Orchestrator Bucket (e.g. all PDFs), you
select PDF from the Data type dropdown list and keep the File glob
pattern default value as
*.
.
- If you have multiple file types in your orchestrator bucket, you need to specify
in both the Data type dropdown and in File glob pattern the data
types you want ingested. The patterns are the same as data type, we specify the
difference to help clarify the ingestion request:
-
*.pdf
for PDFs. -
*.csv
for CSVs. -
*.json
for JSONs.
-
PDF
, and File glob pattern set to
*.
. Next, you upload CSV files to that same Orchestrator
Bucket. You need to run Index and Ingest (Public Preview) again, select the same index,
but set the Data type field to CSV
and File glob
pattern to *.CSV
.
Follow a similar pattern when you remove documents from your data source: when you re-ingest via Index and Ingest (Public Preview), you need to specify the Data Type and File Glob to ensure the ingestion recognizes to remove that document type from the index.
After you create an index, activities and other UiPath products can use it to query documents that are important for your use case.
Ingestion time
Ingestion is an asynchronous process. After you execute the activity, it does not mean the data is queryable immediately. Smaller ingestion payloads are processed faster. Therefore, we recommend you upload documents in batches and run this activity periodically. The duration of this process depends on the amount of data and how many other users submit ingestion requests.
After sending the ingestion request, assuming each document is less than or equal to 1MB, we typically recommend waiting:
- <10 minutes: for 10 documents or less;
- <30 minutes: for 50 documents or less;
- up to 2 hours: for 50 documents or more.
Run the Index and Ingest (Public Preview) activity each time you add or delete data from your data source. This ensures parity with your data source and the embeddings used for search and RAG.
The index name may not appear in the Content Generation activity before the ingestion is completed. If you can’t find the index name in the Content Generation activity:
Common errors and resolution patterns
- You may receive an error ("No Results Found") if the ingestion job has not completed.
- You may receive an error ("No Schema Found") if the ingestion job has failed. In this case, wait a few minutes, retry querying, and retry ingestion.
- You may receive an error ("Datasource Synchronization Already in Progress") which means you have an ingestion job to that index that is currently in progress. Wait a few minutes and retry ingestion.
You can run the Index and Ingest (Public Preview) activity:
- Manually (strongly recommended).
- Event-based: Set up an automation to run the ingestion pipeline every time a new document is added to or removed from a storage bucket. Do this if you regularly add or remove documents from buckets.
- Time-based: Set up an automation to run the ingestion pipeline on a scheduled basis. Do this if you regularly expect a high volume of inflow/outflow of documents. For any trigger creation to work with these activities you should consider previous statements of ingestion being an asynchronous process.
Use the Delete Index (Public Preview) activity if you want to delete the index and embeddings, removing that as a data source that can be queried from other UiPath GenAI Activity experiences. This does not delete the documents or data in the data source (e.g. Orchestrator buckets).
The Content Generation activity features two options for working with documents: File resource and Existing index.
The File resource option allows you to use file variables from previous activities (e.g. a document downloaded from Google Drive) and have Context Grounding perform a just-in-time (JIT) style of RAG. This means it ingests the document into an index, searches across it, augments the prompt, and then deletes the index, so those data are not persistent.
- The File Resource option currently supports only PDF format.
-
Keep these documents smaller (under 50 pages). Integration Service activities have a timeout window in which all of the processing above must take place.
-
If you have a PDF with scanned images, we recommend using the Document Understanding OCR option in the Extract Data activity after you have downloaded a file to extract the text from these images (as Context Grounding does not yet support images). Pass that
extracted_data
output into the prompt with that File Resource pointing at your downloaded file.
The Existing index option allows you to use an index you created with the Index and Ingest (Public Preview) activity. You query across a persistent index into which you've ingested documents from your data source. You can re-use this index as many times as you like until you delete it.
We recommend using the Log Message activity after Content Generation in your workflow sequence, to input the Top Generated Text variable and see the LLM generation response after the workflow executes.
The Content Generation activity also has an output variable called Citations String (Public Preview). Use it as input in a Log Message activity to see the semantic search results used to influence the generation output. This works only for PDF and JSON data types.