--- title: "Get agent settings." method: GET path: "/api/v1/projects/{projectId}/settings" tags: ["Agent Settings"] --- # Get agent settings. `GET /api/v1/projects/{projectId}/settings` Retrieve the agent (formerly known as project) settings for a specific agent. This endpoint allows you to fetch the configuration and settings associated with the project. Here is an example to get an agent settings: [API](https://github.com/Poll-The-People/customgpt-cookbook/blob/main/examples/Get_Settings_for_a_particular_project.ipynb) [SDK](https://github.com/Poll-The-People/customgpt-cookbook/blob/main/examples/SDK_Get_settings_for_a_particular_project.ipynb). ## Path parameters - `projectId` integer, required ## Response `200` Agent settings that belong to a certain agent - object - `status` 'error' | 'success' — The status of the response - `data` ProjectSettings - `chatbot_avatar` string — This is the avatar that is shown in the agent response. You can make it a profile picture or your company logo. - `chatbot_background_type` string — Here you can choose whether the agent conversations widget will use background image or background color. - `chatbot_background` string — This is the background image shown in the agent conversations widget. You can change it to a company logo or background image. - `chatbot_background_color` string — This is the background color of the agent conversations widget. You can set it to any valid color hex. - `default_prompt` string — This is the default prompt shown to the user. You can customize this for your company or client. - `example_questions` string[] — These are example questions shown to guide users. You can create customized questions to suit your company or client needs. - `response_source` 'default' | 'own_content' | 'openai_content' — By default, we ask ChatGPT to use only your content in its response (recommended). If you wish ChatGPT to improvise and use its own knowledgebase as well, you can select "My Content + ChatGPT" - `chatbot_msg_lang` string — By default, the agent messages like 'Ask Me Anything' are in English. You can customize this to your preferred language. Please note: This setting does not control what language ChatGPT responds in. That is controlled by the user's question. So a user asking in Portuguese, will most likely get a response from ChatGPT in Portuguese. - `chatbot_color` string — Color of the agent in hex format - `chatbot_toolbar_color` string — Color of the agent toolbar in hex format - `persona_instructions` string, nullable — Customize your agent behavior by adjusting the system parameter to control its personality traits and role. - `citations_answer_source_label_msg` string, nullable — This is the message shown to indicate where the response came from. You can customize this message based on your business or language. - `citations_sources_label_msg` string, nullable — This is the message shown for the Sources label. You can customize this message based on your business or language. - `hang_in_there_msg` string, nullable — This is the message shown when the agent is thinking and waiting to answer. You can customize this message based on your tone, personality or language. - `chatbot_siesta_msg` string, nullable — This is the message shown when the agent has encountered a problem or error. You can customize this message based on your tone, personality or language. - `is_loading_indicator_enabled` boolean, nullable — Show animated loading indicator while waiting for a response from the agent - `enable_citations` 0 | 1 | 2 | 3, nullable — Each agent response shows an option for the user to see the sources/citations from your content from which the response was generated. - `enable_feedbacks` boolean, nullable — Each agent response shows an thumbs up/down for the user to left own feedback. - `citations_view_type` 'user' | 'show' | 'hide', nullable — Control how citations are shown. By default, the user can initiate to see the citations. You can choose to have it "Auto Shown" or "Auto Hide" - `image_citation_display` 'default' | 'first_only', nullable — Controls how images are displayed in citations. Default displays like regular citations, first_only inserts the image below the first paragraph where referenced, all inserts the image below all referenced paragraphs. - `no_answer_message` string, nullable — This is the message shown when the agent cannot answer. You can customize it to a message asking the user to contact customer support or leave their email / phone. - `ending_message` string, nullable — You can instruct ChatGPT to end every response with some text like asking "Please email us for further support" (Not recommended for most use cases) - `try_asking_questions_msg` string, nullable — This is the message shown to the user to encourage them to ask questions. You can customize this message based on your tone, personality or language. - `view_more_msg` string, nullable — This is the message shown to the user to view more starter questions. You can customize this message based on your tone, personality or language. - `view_less_msg` string, nullable — This is the message shown to the user to view less starter questions. You can customize this message based on your tone, personality or language. - `remove_branding` boolean, nullable — Controls what branding is shown at the bottom of the agent. - `private_deployment` boolean, nullable — When Private Agent Deployment is enabled you can add agent’s code snippet to any website, but users will be able to access it only if they login to their CustomGPT.ai account - `enable_recaptcha_for_public_chatbots` boolean, nullable — Should we check messages from guests with Recaptcha when your agent is publicly available (i.e. shared or embedded). - `chatbot_model` 'gpt-4-o' | 'gpt-4-1' | 'gpt-4o-mini' | 'gpt-4-1-mini' | 'claude-3-sonnet' | 'claude-3.5-sonnet' | 'gpt-o4-mini-low' | 'gpt-o4-mini-medium' | 'gpt-o4-mini-high', nullable — This is the model used by the agent. You can choose a different model to suit your needs. - `is_selling_enabled` boolean, nullable — Enable selling of agent for monetization - `license_slug` boolean, nullable — License slug used for monetization - `selling_url` string, nullable — Selling URL used for monetization - `can_share_conversation` boolean, nullable — Whether conversations can be shared - `can_export_conversation` boolean, nullable — Whether conversations can be exported - `hide_sources_from_responses` boolean, nullable — Should the agent mention source names? - `input_field_addendum` string, nullable — You can add URL for your Terms of Service here, and it will be automatically added to your agent's interface. - `user_avatar_enabled` boolean — Enable user avatar - `user_avatar` string, binary — User avatar - `spotlight_avatar_enabled` boolean — Enable spotlight avatar - `spotlight_avatar` string, binary — Spotlight avatar - `spotlight_avatar_shape` 'circle' | 'rectangle' — Spotlight avatar shape - `spotlight_avatar_type` 'default' | 'image' — Spotlight avatar type - `user_avatar_orientation` string — Avatars orientation - `chatbot_title` string, nullable — Chatbot title - `chatbot_title_color` string, nullable — Chatbot title color, HEX color code - `enable_inline_citations_api` boolean, nullable — Should the citations be shown inline in the response? - `conversation_time_window` boolean, nullable — Defines the maximum duration of a conversation. If set to false, users can continue the conversation beyond 24 hours, but the agent will ignore messages older than 24 hours. If set to true, the agent will consider messages older than 24 hours. - `conversation_retention_period` 'custom' | 'year' | 'never' — Period after which we automatically delete all conversations. - `conversation_retention_days` integer — Custom period in days after which we automatically delete all conversations. - `use_context_aware_starter_question` boolean, nullable — Use context-aware starter question - `enable_agent_knowledge_base_awareness` boolean — Enable agent knowledge base awareness - `markdown_enabled` boolean — Enable Markdown support in the agent responses. This allows for rich text formatting in the agent responses, such as bold, italics, lists, and links. ## Other responses - `400` — Bad Argument - `401` — API Token is either missing or invalid - `404` — Agent not found - `500` — Internal Server Error --- [API](https://skmtc.net/poll-the-people/apis/customgpt-ai.md) · [All operations](https://skmtc.net/poll-the-people/apis/customgpt-ai/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/poll-the-people/customgpt-ai/revisions/b80e6dfcf78d/schema)