---
title: "Stream Custom Course Conversation"
method: GET
path: "/demo-custom-course/{course_id}/conversation/stream"
tags: ["Demo Custom Course"]
---

# Stream Custom Course Conversation

`GET /demo-custom-course/{course_id}/conversation/stream`

Streams GPT's reply for a custom course doc,
using ephemeral conversation_history in memory.
We keep the same SSE approach from your original code,
but no DB or user references.

We add 'lang' so we can pass it to get_prompt_data(...)
to pick the correct language prompts if needed.

## Path parameters

- `course_id` string, required

## Query parameters

- `session_id` string, required — Ephemeral session ID
- `token` string — Unused here, but keep the same signature
- `lang` string — Language code, 'EN' or 'FR'

## Response `200`

Successful Response

- unknown

## Other responses

- `422` — Validation Error

---

[API](https://skmtc.dev/excellence-ai/apis/excellence-learning.md) · [All operations](https://skmtc.dev/excellence-ai/apis/excellence-learning/llms.txt) · [OpenAPI document](https://skmtc.dev/excellence-ai/apis/excellence-learning/revisions/05e048df94c6?raw)