// Add thinking indicator
        var thinkingId = addThinkingIndicator();

        // Use SSE for streaming
        streamChat(message, thinkingId);
    }

    /**
     * Stream chat using Server-Sent Events
     */
    function streamChat(message, thinkingId) {
        var url = config.streamUrl + '?message=' + encodeURIComponent(message);
        if (state.sessionId) {

     * @param request the chat request containing messages and parameters
     * @param callback the callback to receive streaming chunks
     * @throws LlmException if an error occurs during the request
     */
    void streamChat(LlmChatRequest request, LlmStreamCallback callback);

    /**
     * Returns the name of this LLM client.
     *
     * @return the client name (e.g., "ollama", "openai", "gemini")
     */
    String getName();

     *
     * @param request the chat request
     * @param callback the callback to receive streaming chunks
     * @throws LlmException if LLM is not available or an error occurs
     */
    public void streamChat(final LlmChatRequest request, final LlmStreamCallback callback) {
        final long startTime = System.currentTimeMillis();
        final String llmType = getLlmType();
        if (logger.isDebugEnabled()) {

 *
 * Provides shared infrastructure (HTTP client, availability checking) and
 * default implementations of RAG workflow methods with injectable prompt templates.
 * Subclasses implement provider-specific chat/streamChat and checkAvailabilityNow.
 */
public abstract class AbstractLlmClient implements LlmClient {

    private static final Logger logger = LogManager.getLogger(AbstractLlmClient.class);

                throw new LlmException("Test: no response configured");
            }
            return new LlmChatResponse(chatResponseContent);
        }

        @Override
        public void streamChat(final LlmChatRequest request, final LlmStreamCallback callback) {
            if (streamChatCapture != null) {
                streamChatCapture.capture(request, callback);
            } else {

from pydantic import BaseModel

app = FastAPI()


class Prompt(BaseModel):
    text: str


@app.post("/chat/stream", response_class=EventSourceResponse)
async def stream_chat(prompt: Prompt) -> AsyncIterable[ServerSentEvent]:
    words = prompt.text.split()
    for word in words:
        yield ServerSentEvent(data=word, event="token")