All integrationsAI Agents
Chat Data
Create and train Chat Data chatbots, send messages, and manage conversations, leads, actions and analytics.
- actions
- 24
Actions
Steps a workflow can run in Chat Data.
- Create and train a chatbotCreate a chatbot using one of our medical chat models, your own uploaded data, or a custom model. model is required; a request without a valid model is rejected with a 400.
- Retrain an existing chatbotThe Chatbot Retrain API enables you to retrain an existing chatbot. This API is applicable for chatbots with the custom-data-upload model. It allows you to update the chatbot's knowledge base with new information or remove existing data.
- Get chatbot training statusGet the current training progress of the chatbot.
- Delete a chatbotThis API enables the deletion of a chatbot by specifying its ID. It removes the chatbot along with its associated data from the system, including training data, user monitoring data, conversations, leads information, etc. Exercise caution when using this deletion action, as all deleted sources are unrecoverable.
- Get all chatbotsReturns the chatbots the API key can reach, with related information: every chatbot in the workspace for a workspace key, or only its own chatbot for a chatbot-scoped key.
- Get a chatbotReturns the related information about a single chatbot. The returned chatbot schema is the same as in the /get-chatbots endpoint.
- Update chatbot settingsThis API endpoint allows you to edit your chatbot. Only the fields you send are changed; fields set to null are ignored.
- Add a webhookAdd a webhook endpoint that receives real-time events from the chatbot: chat, live-chat-escalation, lead-submission, user-online or user-offline. Your plan must include webhooks. A chatbot can have up to 5 webhook endpoints; adding an event to an existing url subscribes that endpoint to one more event.
- Delete a webhookDelete the webhook registered with the given URL, together with all of its event subscriptions. The response lists the chatbot's remaining webhooks. If no webhook matches url, nothing is deleted and the response is still 200 with the unchanged list.
- Get confidence scoresThis operation retrieves the confidence scores of the related chunks used to generate answers. You can use it to obtain confidence scores before calling the /chat API endpoint, providing an estimate of the chatbot's ability to deliver high-quality answers based on the context. Chunks are cached based on the messages array, so subsequent calls to the /chat API with the same messages array will incur minimal latency in retrieving related vector embeddings from the database. Therefore, calling this API endpoint before /chat should not significantly impact overall chat performance.
- Query the knowledge baseThis operation fetches segments pertinent to generating responses. Designed for seamless chatbot integration with the GPTs store, this API endpoint allows users to supply relevant document fragments to the GPTs. As with the /get-confidence-score endpoint, results are cached by query for efficiency.
- Send a messageSend messages to a chatbot and receive a response. The API supports both streaming and non-streaming modes, as well as OpenAI-compatible response formats.
- Get conversationsGet conversations from a chatbot, most recently active first. Only conversations with at least one user message are returned. Results are paginated.
- Get a conversationGet detailed information about a specific conversation, including messages, customer details if available, and metadata.
- Delete a conversationDeletes a specific conversation associated with a chatbot. This operation requires both chatbotId and conversationId.
- Attach a lead to a conversationAttach or update a lead for a specific conversation. This endpoint allows you to associate customer information with a conversation.
- Get the conversation portal linkGenerate a shareable portal link for a specific conversation. The conversation portal must be enabled for the chatbot. The link is valid for 30 days.
- List actionsRetrieves all configured actions for the specified chatbot. Returns one page; use its pagination values to continue.
- Get an actionRetrieves a specific action by name or index for the specified chatbot. Send exactly one of name or index.
- Add an actionAdds a new action to the specified chatbot. Top-level fields are checked (see the 400 response); headers, pathParams, queryParams and bodyParams items are stored as sent, without schema checks. An api action is also tested before it is saved: Chat Data sends a request to its url, filling each parameter with its example value, and rejects the action if that request fails.
- Delete an actionDeletes a specific action from the chatbot by either name or index. Send exactly one of name or index.
- Get customersGet the customers (leads) collected by a chatbot, newest first. Results are paginated.
- Get analyticsGet the aggregated statistics of a chatbot.
- Get the current planGet a summary of the workspace's current subscriptions and privileges.
No actions match that.
Automate Chat Data with Lodol.
Connect Chat Data and ask your AI for your first workflow.
Free plan, no credit card