Kader Miyanyedi <******@****.***> 1768941243 +0300

Motov Yurii <******@****.***> 1773831336 +0100

#### LLM Prompt per Language

Each language has a directory: [https://github.com/fastapi/fastapi/tree/master/docs](https://github.com/fastapi/fastapi/tree/master/docs), in it you can see a file `llm-prompt.md` with the prompt specific for that language.

For example, for Spanish, the prompt is at: [`docs/es/llm-prompt.md`](https://github.com/fastapi/fastapi/blob/master/docs/es/llm-prompt.md).

	<component name="markdownRenderer" class="org.codelibs.fess.helper.MarkdownRenderer">
		<postConstruct name="init"/>
	</component>

	<!-- LLM client manager -->
	<component name="llmClientManager" class="org.codelibs.fess.llm.LlmClientManager">
	</component>

	<!-- LLM client components are provided by fess-llm-* plugins via fess_llm++.xml -->

    /**
     * Gets the configured LLM type.
     *
     * @return the LLM type from configuration
     */
    protected abstract String getLlmType();

    /**
     * Gets the configuration prefix for this provider.
     * Used to look up per-prompt-type parameters from FessConfig.
     *
     * @return the config prefix (e.g. "rag.llm.openai")
     */

 * It manages registered LLM clients and provides access to the configured
 * LLM provider based on the current configuration.
 */
public class LlmClientManager {

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

    /** The list of registered LLM clients. */
    protected final List<LlmClient> clientList = new CopyOnWriteArrayList<>();

    /**

 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.llm;

import java.util.List;
import java.util.Map;

/**
 * Interface for LLM (Large Language Model) clients.
 * Implementations provide integration with different LLM providers
 * such as Ollama, OpenAI, and Google Gemini.
 *
 * In addition to low-level chat operations, this interface defines

        if lang == "en":
            continue
        lang_prompt_path = Path(f"docs/{lang}/llm-prompt.md")
        if lang_prompt_path.exists():
            translatable_langs.append(lang)
    return translatable_langs


@app.command()
def list_llm_translatable() -> list[str]:
    translatable_langs = get_llm_translatable()
    print("LLM translatable languages:", translatable_langs)
    return translatable_langs

 */
package org.codelibs.fess.llm;

/**
 * Callback interface for receiving streaming chat responses from LLM.
 */
@FunctionalInterface
public interface LlmStreamCallback {

    /**
     * Called for each chunk of the streaming response.
     *
     * @param chunk the text chunk from the LLM response
     * @param done true if this is the final chunk
     */

The body should be annotated with `Any`, because the request and the response would be... well... **anything**. 🤷

The idea is that you would receive the payload and send it **directly** to an LLM provider, using a `prompt` to tell the LLM what to do, and return the response **as is**. No questions asked.

You don't even need to write the body of the function. The `@app.vibe()` decorator does everything for you based on AI vibes: