Overview
Connect DocsBot with Flows360
DocsBot AI allows you to build AI-powered chatbots that pull answers from your existing documentation and content. This integration enables workflows to ask DocsBot questions and update its training sources dynamically.
Use the DocsBot connector to include its declared actions and events in Flows360 workflows without duplicating the integration logic inside each consuming system. This pinned connector version currently exposes 6 actions and no declared triggers.
Available actions
- Ask Question
- Create Source
- Upload Source File
- Create Bot
- Find Bot
- Custom API Call
Available triggers
- No triggers are declared in this pinned package.
The capability list above is generated from the exact reviewed connector package so the public description stays aligned with the version Flows360 operates.
Technical guide
Technical reference
Package identity
- Connector: DocsBot
- Package:
@activepieces/piece-docsbot@0.2.0 - Exact artifact digest:
sha256:74a6a612558b583ac8449e077431bcb0d2b74476c060917f043e1d75cb027560 - Runtime: Activepieces-compatible deterministic worker
- Source: the exact reviewed Activepieces source
Authentication
SECRET TEXT. Connection values are tenant-specific and remain in the consuming Studio instance; CDK stores definitions and field metadata, not customer credential values.
Action contracts
- Ask Question (
askQuestion), Ask a question to a specific bot in a specific team. Classification: read. - Create Source (
createSource), Create a new source for a bot. Classification: read. - Upload Source File (
uploadSourceFile), Upload a file to be used as a source. Classification: read. - Create Bot (
createBot), Creates a new bot. Classification: read. - Find Bot (
findBot), Finds bot by name. Classification: read. - Custom API Call (
custom_api_call), Make a custom API call to a specific endpoint Classification: read.
Trigger contracts
- No trigger delivery contracts are declared.
Verification
Deterministic execution evidence is recorded for the pinned artifact, including 1 exercised action entrypoint and 0 exercised trigger entrypoints.
Capability summary
Authentication
Authentication method: custom
Authentication profiles
connection · custom
- API Key Required · protected credential
Supported objects
| Object | Read | Write | Notes |
|---|---|---|---|
| Ask Question | Yes | No | Ask a question to a specific bot in a specific team. |
| Create Source | Yes | No | Create a new source for a bot. |
| Upload Source File | Yes | No | Upload a file to be used as a source. |
| Create Bot | Yes | No | Creates a new bot. |
| Find Bot | Yes | No | Finds bot by name. |
| Custom API Call | Yes | No | Make a custom API call to a specific endpoint |
Supported actions
Ask Question · Read
Ask a question to a specific bot in a specific team.
ask_question · Risk: low · Retry: safe
Inputs
teamId· string · Required, The team to use.botId· string · Required, The bot to use.question· string · Required, The question to ask the bot. 2 to 500 characters. Max increased to 8K tokens (roughtly 32k chars) when authenticated.metadata· object · Optional, A user identification object with arbitrary metadata about the user. Will be saved to the question and conversation. Keys referrer, email, and name are shown in question history logs. Optional, defaults to null.context_items· number · Optional, Number of sources to lookup for the bot to answer from. Optional, default is 5. Research mode uses 16 (more expensive token usage).human_escalation· boolean · Optional, Whether to enable human escalation for this question. Optional, default is false.followup_rating· boolean · Optional, Whether to ask the user for a follow-up rating after the question is answered. Optional, default is false.document_retriever· boolean · Optional, Whether to use the document retriever for this question. Optional, default is false.full_source· boolean · Optional, Whether to return the full source content in the response. Optional, default is false.autocut· number · Optional, Autocut results to num groups. Optional, defaults to false.testing· boolean · Optional, Whether the request is for testing purposes. Optional, defaults to false.image_urls· array · Optional, List of image URLs to include with the question as context. Optional, defaults to null.model· string · Optional, Override the model used for this request. Requires an OpenAI API key to be set on your team. Optional, defaults to the model configured for the bot.default_language· string · Optional, The default language to use if the language of the conversation is unclear. Use locale codes like 'en' or 'en-US'. Optional, defaults to the bot's configured language.reasoning_effort· string · Optional, Reasoning depth for the response. Requires authentication to override default.
Create Source · Read
Create a new source for a bot.
create_source · Risk: low · Retry: safe
Inputs
teamId· string · Required, The team to use.botId· string · Required, The bot to use.type· string · Required, Can be url, document, sitemap, wp, urls, csv, rss, qa, youtube. All but url, sitemap, and youtube require uploading a formatted file.sourceProperties· object · Required, Create Source Properties
Upload Source File · Read
Upload a file to be used as a source.
upload_source_file · Risk: low · Retry: safe
Inputs
teamId· string · Required, The team to use.botId· string · Required, The bot to use.file· object · Required, The file to upload.
Create Bot · Read
Creates a new bot.
create_bot · Risk: low · Retry: safe
Inputs
teamId· string · Required, The team to use.name· string · Required, The bot name. Used publically.description· string · Required, The bot description. Shown by default in embeds and share links.privacy· string · Required, The bot privacy. Can be public or private.language· string · Required, The bot language.model· string · Optional, The OpenAI model.embeddingModel· string · Optional, The embedding model. Currently supports text-embedding-ada-002, text-embedding-3-large, text-embedding-3-small, embed-multilingual-v3.0, and embed-v4.0 (Cohere) depending on your plan.copyFrom· string · Optional, The ID of an existing bot in your team to copy from. If provided, the new bot will be created as a copy of the specified bot, with all sources copied over after creation.
Find Bot · Read
Finds bot by name.
find_bot · Risk: low · Retry: safe
Inputs
teamId· string · Required, The team to use.name· string · Required, The bot name.
Custom API Call · Read
Make a custom API call to a specific endpoint
custom_api_call · Risk: low · Retry: safe
Inputs
url· object · Requiredmethod· string · Requiredheaders· object · Optional, Authorization headers are injected automatically from your connection.queryParams· object · Optional, Appended to the URL as ?key=value.body_type· string · Optionalbody· object · Optionalresponse_is_binary· boolean · Optional, Enable for files like PDFs, images, etc.failsafe· boolean · Optional, On a failed request, output the error instead of failing the step.timeout· number · Optional, Seconds to wait for a response. Empty: up to the flow limit (10 min).followRedirects· boolean · Optional, Follow 3xx redirects instead of returning them as the response.
Setup
Setup
- Add the DocsBot connector to the workflow in the target Flows360 Studio instance.
- Create or select the tenant-specific connection required by the connector. Connection secrets remain in the Studio connection boundary and are not copied into CDK documentation.
- Provide the connection fields declared by the pinned package:
- No provider credential fields are declared by the pinned package.
- Select the required action or trigger and complete its declared input fields. Required and optional inputs are defined by the exact package schema.
- Test the workflow in the appropriate environment before enabling production scheduling or event delivery.
Limitations
Limitations and operational notes
- This content describes
@activepieces/piece-docsbot@0.2.0; provider behaviour can change independently and should be revalidated when the provider or connector version changes. - Only the 6 actions and 0 triggers declared by this pinned package are represented here.
- Tenant credentials and connection values are not stored in the public connector record.
- Provider-side permissions, account entitlements, quotas and rate limits remain subject to the connected provider account and are not inferred when the package does not declare them.
- Deterministic execution evidence is recorded for the pinned artifact, including 1 exercised action entrypoint and 0 exercised trigger entrypoints.
Troubleshooting
Why canu2019t the connector authenticate?
Check the tenant connection in Studio and confirm every required DocsBot connection field is present. Re-authorise OAuth-based connections if the provider token or consent has expired. Do not place credential values in CDK content or logs.
Why is an action or trigger unavailable?
Confirm that the workflow is using @activepieces/piece-docsbot@0.2.0 and compare the requested capability with the declared action and trigger list for this version. A capability that is not declared by the pinned package should not be presented as supported.
What should I check after a provider-side change?
Revalidate authentication, required fields, action/trigger behaviour and provider documentation before publishing refreshed connector content or moving a new package version into production.