> ## Documentation Index > Fetch the complete documentation index at: https://docs.zappway.ai/llms.txt > Use this file to discover all available pages before exploring further. # AI Employee - Query ### Streaming ##### When streaming is enabled, the endpoint will emit events "answer" (answer of the model) and "endpoint\_response" (full response of the endpoint) ```js theme={null} import { EventStreamContentType, fetchEventSource, } from '@microsoft/fetch-event-source'; let buffer = ''; let bufferEndpointResponse = ''; const ctrl = new AbortController(); await fetchEventSource(queryAgentURL, { method: 'POST', headers: { 'Content-Type': 'application/json', }, signal: ctrl.signal, body: JSON.stringify({ streaming: true, query, conversationId, visitorId, }), async onopen(response) { if (response.status === 402) { throw new ApiError(ApiErrorType.USAGE_LIMIT); } }, onmessage: (event) => { if (event.data === '[DONE]') { // End of stream ctrl.abort(); try { const { sources, conversationId, visitorId } = JSON.parse( bufferEndpointResponse ) as ChatResponse; } catch {} } else if (event.data?.startsWith('[ERROR]')) { // ... } else if (event.event === "endpoint_response") { bufferEndpointResponse += event.data; } else if (event.event === "answer") { buffer += event.data; // ... } }, }); ``` ## OpenAPI ````yaml POST /agents/{id}/query openapi: 3.0.2 info: title: ZappWay - API OpenAPI specifications description: '' termsOfService: http://zappway.ai/terms contact: email: support@zappway.ai license: name: Apache 2.0 url: http://www.apache.org/licenses/LICENSE-2.0.html version: 1.0.0 servers: - url: https://app.zappway.ai/api security: - bearerAuth: [] tags: - name: agents - name: datastores - name: datasources paths: /agents/{id}/query: post: tags: - agents summary: This let you query your AI Employee for a specific query. parameters: - in: path name: id schema: type: string description: ID of the AI Employee required: true requestBody: content: application/json: schema: type: object properties: query: type: string description: This is the query you want to ask your AI Employee. conversationId: type: string description: >- ID of the conversation (If not provided a new conversation is created) visitorId: type: string description: >- ID of the participant that's sending the query (If not provided a new ID is created) temperature: type: number description: Temperature of the model (min 0.0, max 1.0) streaming: type: boolean description: Enable streaming modelName: description: Override agent model enum: - claude_3_5_haiku - claude_3_5_sonnet - claude_4_5_haiku - claude_4_5_sonnet - claude_sonnet_4_6 - claude_4_sonnet - claude_opus_4_5 - claude_opus_4_6 - claude_opus_4_7 - deepseek_r1_0528 - deepseek_v4_flash - deepseek_v4_pro - deepseek_v3_0324 - dolphin_mixtral_8x7b - gemini_3_1_flash_image_preview - gemini_3_1_flash_lite_preview - gemini_3_1_pro_preview - gemini_3_5_flash - gemini_3_flash_preview - gemini_3_pro_image_preview - gemini_3_pro_preview - gemini_flash_2_0 - gemini_flash_2_5 - gemini_pro_2_5 - gpt_4o_2024_11_20 - gpt_4o_mini_2024_07_18 - gpt_5 - gpt_5_1 - gpt_5_1_chat - gpt_5_2 - gpt_5_2_chat - gpt_5_2_chat_latest - gpt_5_3_chat_latest - gpt_5_3_codex - gpt_5_4 - gpt_5_4_mini - gpt_5_4_nano - gpt_5_5_2026_04_23 - gpt_5_mini - gpt_5_nano - glm_5_1 - minimax_m2_7 - mimo_v2_omni - mimo_v2_pro - mimo_v2_5_pro - grok_4 - grok_4_3 - grok_build_0_1 - grok_4_20 - grok_4_20_multi_agent - lfm_2_24b_a2b - llama_4_maverick - llama_4_scout - mistral_large_2512 - mixtral_8x22b - mixtral_8x7b - nova_2_lite_v1 - nova_premier_v1 - sonar_pro maxTokens: type: number description: >- The maximum number of tokens to generate in the chat completion. presencePenalty: type: number description: >- Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics. frequencyPenalty: type: number description: >- Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. topP: type: number description: >- An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both. filters: type: object properties: custom_ids: type: array description: Filter by Custom IDs items: type: string datasource_ids: type: array description: Filter by Datasource IDs items: type: string systemPrompt: description: AI Employee System Prompt type: string userPrompt: description: AI Employee User Prompt type: string promptType: deprecated: true description: >- (DEPRECATED in favor of systemPrompt and userPrompt) Set the prompt type for this query enum: - raw - customer_support promptTemplate: deprecated: true type: string description: >- (DEPRECATED in favor of systemPrompt and userPrompt) Set the prompt template for this query required: - query responses: '200': description: Success content: application/json: schema: properties: answer: type: string description: The answer of the AI Employee. conversationId: type: string description: ID of the conversation visitorId: type: string description: ID of the participant that's sending the query sources: type: array items: type: object description: Datasource chunks that were used to generate the answer '400': description: Invalid body '403': description: Unauthorized components: securitySchemes: bearerAuth: type: http scheme: bearer ````