Update a Chat Agent via API

Update a Chatbot via API (PUT)

This article explains how to update an existing Chat Agent (chatbot) in your Flora AI account using a PUT request.

Overview

You can modify a chatbot’s configuration—such as its name, model, behavior, rate limits, and UI options—by sending a PUT request to the chatbot API endpoint.

Use this when you want to:

• Change the chatbot’s name or display name

• Switch to a different LLM model or set a backup model

• Adjust temperature or knowledge base behavior

• Enable/disable features like streaming, audio, image upload

• Configure rate limiting and cooldown messages

• Pin the chatbot in your list

API Endpoint

Use the following URL, replacing your_chatbot_uuid with the actual UUID of the chatbot you want to update:

https://app.floraai.me/en/chatbot/api/v1/chatbot/your_chatbot_uuid/

This endpoint accepts PUT requests to update the chatbot.

Authentication & Headers

Include these headers in your request:

Content-Type: application/jsonAuthorization: Token <Your-API-Token>

• Content-Type: application/json – Required to send JSON data.

• Authorization: Token <Your-API-Token> – Replace <Your-API-Token> with your actual API token.

You may also include:

Accept: application/json

to explicitly request a JSON response.

Request Body Parameters

Send the chatbot configuration as JSON in the request body.

Required Fields

• name (String, Required)
  Internal name of the chatbot.

• base_system_message (String, Required)
  The core system prompt that defines the chatbot’s behavior and role.

Optional Fields

• display_name (String, Optional)
  Name shown to end users in the chat widget.

• chatgpt_model_key (Choice, Optional)
  Primary LLM model key. Example choices include:

• GPT-3.5

• GPT-4

• GPT-4-Turbo

• GPT_4_TURBO_2024_04_09

• GPT_4_O_2024_05_13

• GPT-4o-2024-11-20

• GPT-4O-mini

• GPT-4O-2024-08-06

• GPT-4.1-2025-04-14

• GPT-4.1-mini-2025-04-14

• GPT-4.1-nano-2025-04-14

• GPT-5-2025-08-07

• GPT-5-mini-2025-08-07

• GPT-5-nano-2025-08-07

• GPT-5.2-2025-12-11

• CLAUDE-3-OPUS-20240229

• CLAUDE-3-7-sonnet-20250219

• CLAUDE-3-5-haiku-20241022

• CLAUDE-SONNET-4-6

• CLAUDE-HAIKU-4-5-20251001

• GROK-2-1212

• GROK-3

• GROK-3-mini

• GROK-4-0709

• GROK-4-1-fast-reasoning

• GROK-4-1-fast-non-reasoning

• backup_llm_model_key (Choice, Optional)
  Backup LLM model key used if the primary model is unavailable. Same choices as chatgpt_model_key.

• temperature (Decimal, Optional)
  Controls randomness of responses.

• Lower values (e.g., 0.1) → more deterministic

• Higher values (e.g., 1.0+) → more creative/unpredictable

• support_email (Email, Optional)
  Overrides the default agency support email for this chatbot.

• knowledge_base_results_base_system_prompt (String, Optional)
  System prompt used specifically when responding with knowledge base results.

• conversation_starter_message (String, Optional)
  Starter messages shown at the beginning of the conversation.

• Separate multiple starters with new lines (\n).

• initial_message (String, Optional)
  Initial message(s) shown to the user when the chat opens.

• Separate multiple messages with new lines (\n).

• show_data_sources (Boolean, Optional)

• true: Show data sources in the chat widget.

• false: Hide data sources.

• persistent_conversation_starter_message (Boolean, Optional)

• true: Keep conversation starters visible throughout the conversation.

• false: Show only at the beginning.

• debug_mode (Boolean, Optional)

• true: Show matched data/sources from Redisearch for each query (for debugging).

• false: Hide debug information.

• audio_io_enabled (Boolean, Optional)

• true: Enable audio input/output for the chatbot.

• false: Disable audio features.

• categories (ManyToMany, Optional)
  List of category IDs the chatbot belongs to.
  Example: [1, 2, 3].

• is_streaming_enabled (Boolean, Optional)

• true: Enable streaming responses.

• false: Disable streaming.

• top_k (Integer, Optional)
  Number of knowledge base results to fetch as context for the chatbot.

• image_upload_enabled (Boolean, Optional)

• true: Allow users to upload images/documents.

• false: Disable uploads.

• llm_driven_conversation_titles (Boolean, Optional)

• true: Let the AI generate conversation titles based on context.

• false: Disable AI-generated titles.

• rate_limiting_enabled (Boolean, Optional)

• true: Enable message rate limiting.

• false: Disable rate limiting.

• time_period (Choice, Optional; used with rate limiting)
  Time window for enforcing message limits:

• per_hour

• per_day

• per_month

• messages_limit (Integer, Optional; used with rate limiting)
  Maximum number of messages allowed within the selected time_period.

• cooldown_period (Integer, Optional; used with rate limiting)
  Cooldown period in minutes after reaching the message limit before users can send messages again.

• cooldown_message (String, Optional; used with rate limiting)
  Message shown to users when they hit the rate limit.

• is_pinned (Boolean, Optional)

• true: Pin the chatbot to the top of the chatbot list.

• false: Do not pin.

Example Request (Python)

Below is a complete example using Python’s requests library:

import requests# Define the API endpointurl = "https://app.floraai.me/en/chatbot/api/v1/chatbot/your_chatbot_uuid/"# Set up authentication and headersheaders = {    'Authorization': 'Token <YOUR-API-TOKEN>',    'Content-Type': 'application/json',    'Accept': 'application/json'}# Data is passed in the request body as JSONdata = {    "name": "Your message/string here.",    "display_name": "Your message/string here.",    "chatgpt_model_key": "GPT-4",    "backup_llm_model_key": "GPT-3.5",    "temperature": "1.1",    "support_email": "[email protected]",    "base_system_message": "Your message/string here.",    "knowledge_base_results_base_system_prompt": "Your message/string here.",    "conversation_starter_message": "Your message/string here.",    "initial_message": "Your message/string here.",    "show_data_sources": True,    "persistent_conversation_starter_message": True,    "debug_mode": True,    "audio_io_enabled": True,    "categories": [1, 2, 3],    "is_streaming_enabled": True,    "top_k": 10,    "image_upload_enabled": True,    "llm_driven_conversation_titles": True,    "rate_limiting_enabled": True,    "time_period": "per_hour",    "messages_limit": 10,    "cooldown_period": 10,    "cooldown_message": "Your message/string here.",    "is_pinned": True}response = requests.put(url, headers=headers, json=data)# Process the responseif response.status_code in (200, 201, 202):    result = response.json()    print("Response data:", result)else:    try:        error_data = response.json()        error_message = error_data.get('message') or error_data.get('error', 'Unknown error')        print(f"Error: {error_message}")    except ValueError:        print(f"Error: Status code {response.status_code}")

Notes:

• Replace your_chatbot_uuid with the actual chatbot UUID.

• Replace <YOUR-API-TOKEN> with your real API token.

• Adjust the field values to match your desired configuration.

• For categories, send a JSON array (e.g., [1, 2, 3]), not a string.

Example Response

A successful update returns the updated chatbot object. For example:

{  "id": 6,  "name": "AI Meeting Scheduler",  "display_name": "AI Meeting Scheduler",  "chatgpt_model_key": "GPT_4_O_2024_05_13",  "temperature": "0.1",  "support_email": "[email protected]",  "base_system_message": "Bass system Prompt.",  "conversation_starter_message": "",  "initial_message": "Hi! What can I help you with?",  "show_data_sources": false,  "persistent_conversation_starter_message": false,  "debug_mode": false,  "audio_io_enabled": false,  "image_upload_enabled": false}

Key points:

• status_code will typically be 200 for a successful update.

• The response body contains the current configuration of the chatbot after the update.