> ## Documentation Index > Fetch the complete documentation index at: https://docs.vellaro.io/llms.txt > Use this file to discover all available pages before exploring further. # Post Message > Send a message and stream the assistant response via SSE. Event stream shape: event: text data: {"text": "..."} (a piece of the answer as it is written, ids already removed: append them) event: text_reset data: {"text": "..."} (only with features ["text_reset"]: show THIS as the answer so far, then append the next pieces — alphabet guard) event: tool_start data: {"tool": {"name": "search_products", "input": {...}}} event: tool_result data: {"tool": {"name": "...", "output": {...}}} event: refusal data: {"text": "...", "meta": {"label": "off_topic"}} event: complete data: {"message_id": "...", "meta": {"products": [...], "turn_locale": "sq"}} event: error data: {"text": , "meta": {"code": , "message": , "contact": {"email", "phone"}}} `products`: the card add_to_cart prepared (with its `proposal`), then the products the answer names, in its order (none after a refusal); `turn_locale`: the language of the turn (BE-34). Error codes: `chat_disabled`, `budget_exhausted`, `unavailable` (provider misconfigured or any unexpected failure, also in the middle of an answer — the cause is logged, never sent). `error` is always the last event: no `complete` follows, and a half answer is not saved. Too many messages (CHAT-11, `rate_limit.check_message`): 429 before any model call, with `{code: "rate_limited", message, contact}` and `Retry-After`. ## OpenAPI ````yaml https://api.vellaro.io/openapi/storefront.json post /api/v1/chat/conversations/{conv_id}/message openapi: 3.1.0 info: title: Vellaro Storefront API description: >- The API of storefronts and mobile apps. The store comes from the publishable key in the `X-Vellaro-Key` header (or from the store's domain); the customer's endpoints also take the customer's token as `Authorization: Bearer `. version: 0.1.0 servers: - url: https://api.vellaro.io description: Produzione security: [] tags: - name: Authentication description: >- Customer sign-up and login, tokens, password reset, email verification, Google and Apple login, two-factor authentication. - name: Catalog description: Products, categories and brands, with filters, sorting and pagination. - name: Search description: Full-text product search and suggestions as you type. - name: Cart description: >- The cart of a guest (`X-Cart-Token`) or of the logged-in customer, and the extra warranty offered on a product page. - name: Checkout & orders description: >- Checkout, the customer's orders and reorder, «Order on WhatsApp» (cart codes, clicks). - name: Payments description: >- The store's payment methods, paying an order again, and the confirmation steps of PayPal, PokPay and Iute. - name: Account description: >- The logged-in customer: profile, addresses, wishlist, digital downloads, subscriptions, affiliate account. - name: Reviews & questions description: Product reviews and product questions. - name: AI chat description: 'The store''s AI shopping assistant: conversations, messages, feedback.' - name: Content description: CMS pages, menus, banners, flipbooks and information pages. - name: Marketing & contact description: >- Newsletter sign-up and email links, the contact form, campaign click tracking. - name: Store description: >- The store for the storefront: brand, public settings, languages, translations, currencies, physical stores, theme. - name: Devices description: Push-notification devices of the mobile app. paths: /api/v1/chat/conversations/{conv_id}/message: post: tags: - AI chat summary: Post Message description: >- Send a message and stream the assistant response via SSE. Event stream shape: event: text data: {"text": "..."} (a piece of the answer as it is written, ids already removed: append them) event: text_reset data: {"text": "..."} (only with features ["text_reset"]: show THIS as the answer so far, then append the next pieces — alphabet guard) event: tool_start data: {"tool": {"name": "search_products", "input": {...}}} event: tool_result data: {"tool": {"name": "...", "output": {...}}} event: refusal data: {"text": "...", "meta": {"label": "off_topic"}} event: complete data: {"message_id": "...", "meta": {"products": [...], "turn_locale": "sq"}} event: error data: {"text": , "meta": {"code": , "message": , "contact": {"email", "phone"}}} `products`: the card add_to_cart prepared (with its `proposal`), then the products the answer names, in its order (none after a refusal); `turn_locale`: the language of the turn (BE-34). Error codes: `chat_disabled`, `budget_exhausted`, `unavailable` (provider misconfigured or any unexpected failure, also in the middle of an answer — the cause is logged, never sent). `error` is always the last event: no `complete` follows, and a half answer is not saved. Too many messages (CHAT-11, `rate_limit.check_message`): 429 before any model call, with `{code: "rate_limited", message, contact}` and `Retry-After`. operationId: post_message_api_v1_chat_conversations__conv_id__message_post parameters: - name: conv_id in: path required: true schema: type: string format: uuid title: Conv Id requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/MessageIn' responses: '200': description: Successful Response content: application/json: schema: {} '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' security: - HTTPBearer: [] components: schemas: MessageIn: properties: text: type: string maxLength: 4000 minLength: 1 title: Text locale: anyOf: - type: string maxLength: 8 minLength: 2 - type: 'null' title: Locale features: anyOf: - items: type: string maxLength: 32 minLength: 1 type: array maxItems: 8 - type: 'null' title: Features type: object required: - text title: MessageIn HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type input: title: Input ctx: type: object title: Context type: object required: - loc - msg - type title: ValidationError securitySchemes: HTTPBearer: type: http scheme: bearer ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.