> ## Documentation Index > Fetch the complete documentation index at: https://docs.interactly.ai/llms.txt > Use this file to discover all available pages before exploring further. # Update Assistant > Update Assistant Details by ID ## OpenAPI ````yaml https://api-prod.interactly.ai/api-docs/common/api.json patch /assistants/v1/assistants/{id} openapi: 3.1.0 info: title: Interactly API description: API for building interactly.ai services version: 1.1.0 contact: name: Interactly url: https://interactly.ai email: developers@interactly.ai servers: - url: https://api-prod.interactly.ai description: API Server security: [] paths: /assistants/v1/assistants/{id}: patch: tags: - Assistants summary: Update Assistant description: Update Assistant Details by ID operationId: updateAssistant parameters: - name: id in: path description: Assistant ID required: true schema: type: string example: 5f7b1b1b1b1b1b1b1b1b1b1b requestBody: content: application/json: schema: $ref: '#/components/schemas/UpdateAssistantDTO' required: true responses: '200': description: Successful response content: application/json: schema: $ref: '#/components/schemas/Assistant' security: - bearer: [] components: schemas: UpdateAssistantDTO: type: object allOf: - $ref: '#/components/schemas/AssistantCommon' required: - name Assistant: type: object properties: _id: type: string description: This is the unique identifier of the assistant. example: 5f7b1b1b1b1b1b1b1b1b1b1b teamId: type: string description: >- This is the unique identifier of the team that the assistant belongs to. example: 1f7b1b1b1b1b1b1b1b1b1b1b createdAt: $ref: '#/components/schemas/CreatedAt' updatedAt: $ref: '#/components/schemas/UpdatedAt' allOf: - $ref: '#/components/schemas/AssistantCommon' AssistantCommon: type: object properties: name: type: string description: This is the name of the assistant. example: My Assistant welcomeMessage: type: string description: This is the welcome message of the assistant. default: hi example: Hello! How can I help you? welcomeMessageMode: type: string description: >- This is the mode of the welcome message. It can be one of the following: 'assistant-speaks-first', 'assistant-waits-for-user', 'automatic'. example: assistant-speaks-first default: automatic welcomeMessageInterruptionsEnabled: type: boolean description: >- This is a boolean that controls whether the interruptions are enabled during the welcome message. If set to false, the user can not interrupt the welcome message. example: false default: false assistantProvider: type: string description: This is the provider of the assistant. enum: - openai - azure - gemini - deepseek - bedrock - custom-llm default: azure example: openai assistantModel: type: string description: >- The type of model used for the assistant depends on the provider. For openai - Available Options: `gpt-4`, `gpt-4o`, `gpt-4o-mini`, `gpt-3.5-turbo`. For azure - Available Options: `gpt-4`, `gpt-4o`, `gpt-4o-mini`. For gemini - Available Options: `gemini-1.5-flash-latest`,`gemini-1.5-pro-latest`,`gemini-1.5-flash`. For deepseek - Available Options: `V3`. For bedrock - Available Options: `anthropic.claude-3-5-sonnet`, `anthropic.claude-3-5-haiku`, `meta.llama3-1-8b-instruct`. example: gpt-4o-mini default: gpt-4o-mini discriminator: propertyName: assistantProvider mapping: openai: $ref: '#/components/schemas/OpenAIModels' azure: $ref: '#/components/schemas/AzureModels' gemini: $ref: '#/components/schemas/GeminiModels' deepseek: $ref: '#/components/schemas/DeepseekModels' bedrock: $ref: '#/components/schemas/BedrockModels' custom-llm: $ref: '#/components/schemas/CustomLLMModels' assistantLLMUrl: type: string description: >- Provider your LLM Base URL here when `assistantProvider=custom-llm`. Ex: `https://your-server.com/custom-llm`. Please note that, we will append `/chat/completions` to your base URL before calling LLM endpoints. The LLM URL should be accessible from the Interactly server. If you are using a local server, you can use ngrok to expose your local server to the internet. assistantSystemPrompt: type: string description: This system prompt guides the assistant's operations. example: You are AI assistant to help patients with their health care needs. assistantTemperature: type: number description: This is the temperature of the assistant. default: 0 example: 0 assistantMaxTokens: type: integer description: >- This is the maximum number of tokens that the assistant can generate. default: 256 example: 256 assistantResponseSplitter: type: string description: Use this Delimiter to split the AI responses into separate lines. example: ',' config: $ref: '#/components/schemas/AssistantConfig' hints: type: array description: >- Provide keyword hints to help the assistant better recognize and transcribe important words or phrases. items: type: string backgroundSound: description: >- This is the background sound in the call. Default is 'disable'. You can also provide a custom sound by providing a URL to an audio file. URL should be publicly accessible and should starts with https:// only. Note: Currently custom sound is not supported in `twilio` phone vendor. maxLength: 1000 oneOf: - $ref: '#/components/schemas/BackgroundSoundNative' title: Interactly Supported Sounds - $ref: '#/components/schemas/BackgroundSoundCustom' title: Custom Sound URL backgroundSoundVolume: type: number description: >- This is the volume of the background sound. It is a number between 1 and 100. default: 50 example: 50 ttsCacheEnabled: type: boolean description: This is the enabled flag of the tts cache. example: false ttsAudioCacheScope: type: string description: >- This is the storage scope of the tts audio cache. It can be one of the following: 'assistant', 'team', 'global'. 'global' is deprecated and will be removed in future. enum: - assistant - team - global maxConsecutiveTtsFailures: type: integer description: >- Maximum number of consecutive TTS turn failures before the call is ended automatically. default: 2 example: 2 minimum: 0 recordingEnabled: type: boolean description: Controls whether call recording is enabled for this assistant. default: true example: true recordAfterTransfer: type: boolean description: >- When enabled, call recording continues after the call is forwarded or warm-transferred to another party. default: false example: false postCallTranscriptsEnabled: type: boolean description: >- When enabled, a post-call transcript file is generated and stored alongside the call recording after the call ends. default: false example: false assistantBackchannelingEnabled: type: boolean description: This is the backchanneling enabled of the assistant. example: false dtmfInputEnabled: type: boolean description: >- This is a boolean that controls whether the DTMF input is enabled for the assistant. example: false maxCallDuration: type: integer description: This is the max call duration(in minutes) of the assistant. example: 900 minimum: 1 maximum: 120 idleTimeout: type: integer description: >- How long should the assistant wait in silence before confirming the user's presence and playing an idle message? default: 30 example: 20 minimum: 5 maximum: 600 maxIdleMessagesInSequence: type: integer description: Maximum number of times to repeat the idle message in sequence example: 3 minimum: 1 maximum: 5 startSpeakingOptions: type: object description: Configuration for when the assistant should start talking. properties: waitSeconds: type: number description: Number of seconds to wait before starting to process speech default: 0 smartEndpointing: type: string description: >- Controls the endpointing strategy for detecting when a user has finished speaking enum: - Interactly - 'Off' - LiveKit default: Interactly onPunctuationSeconds: type: number description: >- The minimum number of seconds to wait after transcription ending with punctuation before sending a request to the model. This is only used if `smartEndpointing` is set to `Off`. default: 0 onNoPunctuationSeconds: type: number description: >- The minimum number of seconds to wait after transcription ending without punctuation before sending a request to the model. This is only used if `smartEndpointing` is set to `Off`. default: 0 onNumberSeconds: type: number description: >- The minimum number of seconds to wait after transcription ending with a number before sending a request to the model. This is only used if `smartEndpointing` is set to `Off`. default: 0 LiveKitBaseValue: type: number description: >- In the expression where X is the probability that the user is still speaking: `LiveKitBaseValue + (LiveKitScaleValue * X)` This is the base timeout value in milliseconds. This is only used if `smartEndpointing` is set to `LiveKit`. default: 100 LiveKitScaleValue: type: number description: >- In the expression where X is the probability that the user is still speaking: `LiveKitBaseValue + (LiveKitScaleValue * X)` This is the scaling factor for LiveKit endpointing that adjusts based on speech probability. This is only used if `smartEndpointing` is set to `LiveKit`. default: 1000 stopSpeakingOptions: type: object description: >- Configuration for detecting when when assistant should stop talking on customer interruption. properties: numberOfWords: type: number description: >- This is the number of words that the customer has to say before the assistant will stop talking. default: 3 voiceSeconds: type: number description: >- This is the seconds customer has to speak before the assistant stops talking. This uses the VAD (Voice Activity Detection) spike to determine if the customer has started speaking. default: 0 userInterruptionAckPlan: type: object description: >- This is the plan to respond to early interruptions by user with polite filler phrases. properties: enabled: type: boolean description: This is the enabled flag of the user interruption ack plan. count: type: number description: >- This is the number of times the user will interrupt the assistant before responding with a polite filler phrase. default: 2 words: type: number description: >- This is the number of words that the user will interrupt the assistant default: 4 phrases: type: array description: >- This is the list of phrases that the assistant will use to respond to the user's early interruptions. items: type: string example: - Please hold on while I check your account. - one moment please - let me just check that for you assistantToolIds: type: array items: type: string description: This is the list of tool IDs of the assistant. example: [] assistantPredefinedTools: type: object description: >- Enable or disable specific tools that the assistant can use to improve its functionality. properties: knowledgeBase: type: boolean description: This will allow the assistant to end the call from its side. default: false endCall: type: boolean description: This will allow the assistant to end the call from its side. default: false appointment: type: boolean description: >- This will allow the assistant to manage appointments, including scheduling, rescheduling, and cancellations. default: false volumeControl: type: boolean description: This will allow the assistant to adjust the call volume. default: false waitList: type: boolean description: This will allow the assistant to access the wait list. default: false callForward: type: boolean description: >- This will allow the assistant to forward calls to the desired recipient or queue. default: false sendSms: type: boolean description: >- This will allow the assistant to send SMS messages during the call. default: false assistantType: type: string description: >- This is the type of the assistant. It can be one of the following: 'single_prompt', 'workflow_based'. enum: - single_prompt - workflow_based default: single_prompt assistantKnowledgeBaseIds: type: array items: type: string description: >- This is the list of knowledge base IDs of the assistant. Provide only when `assistantPredefinedTools.knowledgeBase` is enabled example: [] endCallMessage: type: string description: >- This is the message that the assistant will say if it ends the call. Provide only when `assistantPredefinedTools.endCall` is enabled example: Goodbye! endCallToolDescription: type: string description: >- This is the description of the tool that the assistant will use to end the call. Provide only when `assistantPredefinedTools.endCall` is enabled example: >- Trigger the end call only when the user is done with the conversation. endCallPhrases: type: array description: >- List of phrases that the assistant will listen to end the call. Provide only when `assistantPredefinedTools.endCall` is enabled items: type: string example: - goodbye - bye callForwardData: type: array items: type: object properties: phoneNumber: type: string description: Phone number used to forward the call. example: '+1234567890' extension: type: string description: >- This is the extension of the assistant. Leave it empty if there is no extension. example: '' name: type: string description: This is a friendly name for the call forward. example: call-forward-name onFailedMessage: type: string description: >- This is the message that the assistant will say if the call forward fails. example: The call forward failed. Please try again later. required: false description: This is the call-forwarding data of the assistant. example: phoneNumber: '+1234567890' extension: '' name: call-forward-name warmTransferEnabled: type: boolean description: >- Enables warm transfer when forwarding calls. The receiving agent is connected before the caller is transferred, allowing a briefing before handoff. Requires `assistantPredefinedTools.callForward` to be enabled. default: false example: false warmTransferConversational: type: boolean description: >- When enabled with `warmTransferEnabled`, the assistant converses with the receiving agent before completing the transfer. When disabled, a pre-generated briefing message is played to the agent instead. default: false example: false holdMusicUrl: type: string description: >- URL of the hold music played to the caller while a conversational warm transfer is in progress. Must be a publicly accessible HTTPS URL. default: '' example: https://www.soundjay.com/ambient/sounds/people-in-lounge-1.mp3 warmTransferTimeout: type: integer description: >- Maximum time in seconds to wait for the receiving agent to answer during a warm transfer before the transfer is considered failed. default: 300 example: 300 minimum: 1 maximum: 3600 assistantAnalysis: $ref: '#/components/schemas/AssistantAnalysis' assistantOverrides: $ref: '#/components/schemas/AssistantOverrides' assistantServer: $ref: '#/components/schemas/AssistantServer' assistantOutcome: type: array items: type: object properties: type: type: string description: This is the type of the outcome. field: type: string description: This is the field of the outcome. smsConfiguration: type: object description: Control how the assistant composes outbound SMS. properties: enabled: type: boolean description: This is the enabled flag of the sms configuration. sameAsAssistant: type: boolean description: >- Use the same prompt as the assistant, or provide a custom SMS prompt. smsPrompt: type: string description: This is the sms prompt for handling sms responses. persistHistory: type: object description: Remember users and keep conversation history for follow-ups. properties: enabled: type: boolean description: This is the enabled flag of the persist history. call: type: boolean description: >- Store metadata and transcripts of calls in persisted data for future personalization and context. sms: type: boolean description: >- Keep outbound and inbound SMS content so follow-ups can reference earlier messages. retentionPeriod: type: number description: >- This is, how long(in number of days) to retain persisted data. Set to 0 to keep nothing. example: 7 CreatedAt: type: string format: date-time description: This is the ISO 8601 date-time string of when the record was created. example: '2020-10-05T00:00:00.000Z' UpdatedAt: type: string format: date-time description: >- This is the ISO 8601 date-time string of when the record was last updated. example: '2020-10-05T00:00:00.000Z' OpenAIModels: type: string description: List of OpenAI models that can be used for the assistant. enum: - gpt-4 - gpt-4o - gpt-4o-mini - gpt-3.5-turbo example: gpt-4 AzureModels: type: string description: List of Azure models that can be used for the assistant. enum: - gpt-4 - gpt-4o - gpt-4o-mini example: gpt-4 GeminiModels: type: string description: List of Gemini models that can be used for the assistant. enum: - gemini-1.5-flash-latest - gemini-1.5-pro-latest - gemini-1.5-flash example: gemini-1.5-flash-latest DeepseekModels: type: string description: List of Deepseek models that can be used for the assistant. enum: - V3 example: V3 BedrockModels: type: string description: List of Bedrock models that can be used for the assistant. enum: - anthropic.claude-3-5-sonnet - anthropic.claude-3-5-haiku - meta.llama3-1-8b-instruct example: anthropic.claude-3-5-sonnet CustomLLMModels: type: string description: List of Custom LLM models that can be used for the assistant. AssistantConfig: type: object description: >- This is the stt and tts configuration of the assistant. You can add one stt and multiple tts configurations. check [here](/vendors) for the list of supported vendors and models. properties: speech: type: object properties: stt: description: >- This section allows you to configure the transcription settings for the assistant. oneOf: - $ref: '#/components/schemas/MicrosoftSTT' title: Microsoft STT - $ref: '#/components/schemas/DeepgramSTT' title: Deepgram STT sttFallback: description: >- This is the fallback speech to text configuration of the assistant. When the main stt configuration fails, the fallback stt configuration will be used. You can enable or disable the fallback stt configuration with `enabled` field. allOf: - type: object description: >- This flag can enable or disable the fallback stt configuration. properties: enabled: type: boolean default: true - oneOf: - $ref: '#/components/schemas/MicrosoftSTT' title: Microsoft STT - $ref: '#/components/schemas/DeepgramSTT' title: Deepgram STT ttsData: description: >- This is the text to speech configuration of the assistant. You can add multiple tts configurations. type: array items: allOf: - type: object properties: enabled: description: >- If you want to use multiple voices for multiple languages, you can add multiple tts configurations and set the `enabled` flag to true for only one of the desired tts configuration that will be used as main tts configuration. If the language of assistant is not present in the tts configuration, the `default` tts configuration will be used. type: boolean default: true example: true - oneOf: - $ref: '#/components/schemas/ElevenLabsTTS' title: Eleven Labs TTS - $ref: '#/components/schemas/DeepgramTTS' title: Deepgram TTS - $ref: '#/components/schemas/MicrosoftTTS' title: Microsoft TTS - $ref: '#/components/schemas/CartesiaTTS' title: Cartesia TTS BackgroundSoundNative: type: string enum: - enable - disable example: enable BackgroundSoundCustom: type: string format: uri example: https://www.soundjay.com/ambient/sounds/people-in-lounge-1.mp3 AssistantAnalysis: type: object properties: summary: description: >- This is the plan for generating the summary of the call. This outputs to `call.analysis.summary`. allOf: - $ref: '#/components/schemas/AssistantAnalysisSummary' successEvaluation: description: >- This is the plan for generating the success evaluation of the call. This outputs to `call.analysis.successEvaluation`. allOf: - $ref: '#/components/schemas/AssistantAnalysisSuccessEvaluation' structuredData: description: >- This is the plan for generating the structured data from the call. This outputs to `call.analysis.structuredData`. allOf: - $ref: '#/components/schemas/AssistantAnalysisStructuredData' AssistantOverrides: type: object description: This is where you can override the default behavior of the assistant. properties: welcomeMessage: type: string description: >- This is the message that the assistant will say when the call starts. example: Hello, how can I help you today? welcomeMessageMode: type: string description: >- This is the mode of the welcome message. It can be one of the following: 'assistant-speaks-first', 'assistant-waits-for-user', 'automatic'. example: assistant-speaks-first default: automatic welcomeMessageInterruptionsEnabled: type: boolean description: >- This is a boolean that controls whether the interruptions are enabled during the welcome message. If set to false, the user can not interrupt the welcome message. example: false default: false recordingEnabled: type: boolean description: >- This is a boolean that controls whether the recording is enabled. If set to false, the model will not record the call. @default true default: true example: true recordAfterTransfer: type: boolean description: >- When enabled, call recording continues after the call is forwarded or warm-transferred to another party. default: false example: false postCallTranscriptsEnabled: type: boolean description: >- When enabled, a post-call transcript file is generated and stored alongside the call recording after the call ends. default: false example: false maxConsecutiveTtsFailures: type: integer description: >- Maximum number of consecutive TTS turn failures before the call is ended automatically. default: 2 example: 2 minimum: 0 warmTransferEnabled: type: boolean description: >- Enables warm transfer when forwarding calls. The receiving agent is connected before the caller is transferred. default: false example: false warmTransferConversational: type: boolean description: >- When enabled with `warmTransferEnabled`, the assistant converses with the receiving agent via WebSocket before completing the transfer. default: false example: false holdMusicUrl: type: string description: >- URL of the hold music played to the caller while a conversational warm transfer is in progress. default: '' example: https://www.soundjay.com/ambient/sounds/people-in-lounge-1.mp3 warmTransferTimeout: type: integer description: >- Maximum time in seconds to wait for the receiving agent to answer during a warm transfer. default: 300 example: 300 minimum: 1 maximum: 3600 recordingPath: type: string description: >- This is the path where the recording will be stored. If not provided, the recording will be stored in the default path. example: /recordings dynamicVariables: type: object description: >- This is the dynamic variables of the conversation. Values in this object will be replaced in the assistant system prompt, welcome message, end call message. If your dynamic variable is `user_name`, you can use it in the system prompt message as `Hello, {{user_name}}`. example: user_name: John Doe AssistantServer: type: object description: >- This is where Interactly will send webhooks. You can find all webhooks available along with their shape in ServerMessage schema. properties: enabled: type: boolean description: >- This is a boolean that controls whether the server is enabled. If set to false, the model will not send webhooks to the server. @default false example: false messages: type: array enum: - status-update - conversation-update - hang - end-of-call-report - error example: - status-update - conversation-update - hang - end-of-call-report - error description: These are the messages that will be sent to your Server URL. items: type: string enum: - status-update - conversation-update - hang - end-of-call-report - error allOf: - $ref: '#/components/schemas/Server' MicrosoftSTT: type: object properties: vendor: type: string description: This is the vendor of the speech to text. example: microsoft default: microsoft enum: - microsoft languages: type: array description: This is the list of languages that the assistant can understand. items: type: string enum: - en-US - en-IN - en-GB - es-US - es-MX - fr-FR - fr-CA - zh-CN - pt-BR - pt-PT - hi-IN example: en-US default: - en-US DeepgramSTT: type: object properties: vendor: type: string description: This is the vendor of the speech to text. example: deepgram default: deepgram enum: - deepgram languages: type: array description: This is the list of languages that the assistant can understand. items: type: string enum: - en-US example: en-US default: - en-US deepgramOptions: type: object description: This is the configuration of the deepgram text to speech. properties: model: type: string description: This is the model of the deepgram speech to text. example: nova-3 enum: - nova-3 - nova-3-medical - nova-2 - nova-2-phonecall - nova-2-meeting - nova-2-conversationalai - nova-2-medical - flux-general-en punctuate: type: boolean description: >- Enable punctuation in the transcription output. This is enabled by default. example: true default: true endpointing: type: number description: >- The number of seconds of silence after which the speech is considered to be ended. This is set to 10 seconds by default. example: 10 default: 10 smart_format: type: boolean description: >- Enable smart formatting in the transcription output. This is enabled by default. example: true default: true no_delay: type: boolean description: >- Enable no delay in the transcription output. This is enabled by default. example: true default: true numerals: type: boolean description: >- Enable numerals in the transcription output. This is enabled by default. example: true default: true eagerEotThreshold: type: number description: >- The threshold for the end of turn detection. This is set to 0.5 by default. Valid Values 0.3 - 0.9. Used for flux-general-en model. example: 0.5 default: 0.5 eotThreshold: type: number description: >- The threshold for the end of turn detection. This is set to 0.8 by default. Valid Values 0.5 - 0.9. Used for flux-general-en model. example: 0.8 default: 0.8 eotTimeoutMs: type: number description: >- The timeout for the end of turn detection. This is set to 5000 milliseconds by default. Valid Values 100 - 10000 milliseconds. Used for flux-general-en model. example: 5000 default: 5000 ElevenLabsTTS: type: object properties: vendor: type: string example: eleven-labs enum: - eleven-labs language: type: string description: This is the language of the text to speech. example: en-US enum: - en-US - es-US - fr-FR - zh-CN - hi-IN voice: type: string description: >- Provider voice ID. Ex: Voice ID will be `ZeK6O9RfGNGj0cJT2HoJ` for `Shanaya (female)-Customer Care Agent` voice. example: ZeK6O9RfGNGj0cJT2HoJ config: type: object description: This is the configuration of the eleven labs text to speech. properties: modelId: type: string description: This is the model id of the eleven labs text to speech. example: eleven_multilingual_v2 enum: - eleven_multilingual_v2 - eleven_turbo_v2_5 - eleven_flash_v2_5 - eleven_turbo_v2 - eleven_flash_v2 default: eleven_turbo_v2 stability: type: number description: This is the stability of the eleven labs text to speech. example: 0.7 default: 0.7 minimum: 0 maximum: 1 similarityBoost: type: number description: >- Determines how closely the AI should adhere to the original voice when attempting to replicate it. example: 0.85 default: 0.85 minimum: 0 maximum: 1 speakerBoost: type: boolean description: This is the speaker boost of the eleven labs text to speech. example: true default: true styleExaggeration: type: number description: >- Determines the style exaggeration of the voice. This setting attempts to amplify the style of the original speaker. It does consume additional computational resources and might increase latency if set to anything other than 0. example: 0.5 default: 0 minimum: 0 maximum: 1 seed: type: number description: >- If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed. Must be integer between 0 and 4294967295. example: 42 default: null speed: type: number description: >- Adjusts the speed of the voice. A value of 1.0 is the default speed, while values less than 1.0 slow down the speech, and values greater than 1.0 speed it up. example: 1 default: 1 minimum: 0.5 maximum: 2 applyTextNormalization: type: boolean description: >- This is the apply text normalization of the eleven labs text to speech. example: true default: false DeepgramTTS: type: object properties: vendor: type: string example: deepgram enum: - deepgram language: type: string description: This is the language of the text to speech. example: en-US enum: - en-US - en-UK voice: type: string description: >- Provider voice ID. Ex: Voice ID will be `aura-luna-en` for `Luna (US) Female` voice. example: aura-luna-en MicrosoftTTS: type: object properties: vendor: type: string example: microsoft enum: - microsoft language: type: string description: This is the language of the text to speech. example: en-US enum: - en-US - es-ES - fr-FR - hi-In voice: type: string description: >- Provider voice ID. Ex: Voice ID will be `en-US-JennyNeural` for `Jenny (Female)` voice. example: en-US-JennyNeural CartesiaTTS: type: object properties: vendor: type: string example: cartesia enum: - cartesia language: type: string description: This is the language of the text to speech. example: en enum: - en - es - fr - zh - hi voice: type: string description: >- Provider voice ID. Ex: Voice ID will be `79f8b5fb-2cc8-479a-80df-29f7a7cf1a3e` for `Nonfiction Man` voice. example: 79f8b5fb-2cc8-479a-80df-29f7a7cf1a3e AssistantAnalysisSummary: type: object properties: enabled: type: boolean description: >- This is a boolean that controls whether the summary is generated. If set to false, the model will not generate a summary of the call. @default false example: false prompt: type: string description: >- This is the prompt that the model will use to generate the summary of the call. example: Generate a summary of the call. timeoutSeconds: type: number description: >- This is how long the request is tried before giving up. When request times out, `call.analysis.summary` will be empty. Usage: - To guarantee the summary is generated, set this value high. Note, this will delay the end of call report in cases where model is slow to respond. @default 5 seconds minimum: 1 maximum: 60 example: 30 AssistantAnalysisSuccessEvaluation: type: object properties: enabled: type: boolean description: >- This is a boolean that controls whether the success evaluation is generated. If set to false, the model will not generate a success evaluation of the call. @default false example: false prompt: type: string description: >- This is the prompt that the model will use to generate the success evaluation of the call. example: Evaluate the success of the call. rubric: type: string enum: - NumericScale - DescriptiveScale - Checklist - Matrix - PercentageScale - LikertScale - AutomaticRubric - PassFail description: >- This enforces the rubric of the evaluation. The output is stored in `call.analysis.successEvaluation`. Options include: - 'NumericScale': A scale of 1 to 10. - 'DescriptiveScale': A scale of Excellent, Good, Fair, Poor. - 'Checklist': A checklist of criteria and their status. - 'Matrix': A grid that evaluates multiple criteria across different performance levels. - 'PercentageScale': A scale of 0% to 100%. - 'LikertScale': A scale of Strongly Agree, Agree, Neutral, Disagree, Strongly Disagree. - 'AutomaticRubric': Automatically break down evaluation into several criteria, each with its own score. - 'PassFail': A simple 'true' if call passed, 'false' if not. Default is 'PassFail'. timeoutSeconds: type: number description: >- This is how long the request is tried before giving up. When request times out, `call.analysis.summary` will be empty. Usage: - To guarantee the summary is generated, set this value high. Note, this will delay the end of call report in cases where model is slow to respond. @default 5 seconds minimum: 1 maximum: 60 example: 30 AssistantAnalysisStructuredData: type: object properties: enabled: type: boolean description: >- This determines whether structured data is generated and stored in `call.analysis.structuredData`. Defaults to false. Usage: - If you want to extract structured data, set this to true and provide a `schema`. @default false default: false prompt: type: string description: >- This is the prompt that the model will use to generate the structured data of the call. example: Extract structured data from the call. timeoutSeconds: type: number description: >- This is how long the request is tried before giving up. When request times out, `call.analysis.structuredData` will be empty. Usage: - To guarantee the structured data is generated, set this value high. Note, this will delay the end of call report in cases where model is slow to respond. @default 5 seconds minimum: 1 maximum: 60 example: 30 schema: description: >- This is the schema of the structured data. The output is stored in `call.analysis.structuredData`. Complete guide on JSON Schema can be found [here](https://ajv.js.org/json-schema.html#json-data-type). allOf: - $ref: '#/components/schemas/JsonSchema' example: type: object properties: name: type: string description: This is the name of the user. example: John Doe dob: type: string format: date description: This is the date of birth of the user. example: '1990-03-08' Server: type: object properties: timeoutSeconds: type: number description: >- This is the timeout in seconds for the request to your server. Defaults to 20 seconds. @default 20 minimum: 1 maximum: 120 example: 20 url: type: string description: API endpoint to send requests to. example: https://api.example.com/v1/getUserDetails secret: type: string description: >- This is the secret you can set that Interactly will send with every request to your server. Will be sent as a header called x-interactly-secret. example: my-secret headers: type: object description: >- These are the custom headers to include in the request sent to your server. Each key-value pair represents a header name and its value. example: {} required: - url JsonSchema: type: object properties: type: type: string description: >- This is the type of output you'd like. `string`, `number`, `integer`, `boolean` are the primitive types and should be obvious. `array` and `object` are more interesting and quite powerful. They allow you to define nested structures. For `array`, you can define the schema of the items in the array using the `items` property. For `object`, you can define the properties of the object using the `properties` property. enum: - string - number - integer - boolean - array - object items: type: object description: >- This is required if the type is "array". This is the schema of the items in the array. This is of type JsonSchema. However, Swagger doesn't support circular references. properties: type: object description: >- This is required if the type is "object". This specifies the properties of the object. This is a map of string to JsonSchema. However, Swagger doesn't support circular references. description: type: string description: >- This is the description to help the model understand what it needs to output. required: description: |- This is a list of properties that are required. This only makes sense if the type is "object". type: array items: type: string required: - type securitySchemes: bearer: scheme: bearer bearerFormat: Bearer type: http description: >- Retrieve your API Key from [Dashboard API Keys Section](https://dashboard.interactly.ai/api-keys). ````