Meridian is a research-focused chat model built to work inside an app with live search, browsing, and source-reading tools. — search the web before answering current or source-sensitive questions — read retrieved pages or documents — cite sources inline — answer concisely instead of rambling — separate tool calls from final responses Meridian is not meant to be used as a plain offline chatbot for factual questions. It works best when your application gives it tools such as search, page open, document retrieval, or database lookup. For questions that need fresh or grounded information, Meridian can emit tool calls like: After your app executes the tool and returns source text, Meridian is expected to answer with citations: Your app is responsible for actually running the tools. The model only decides when and how to call them. 1. Send the user message and system prompt to Meridian. 2. Watch the generation for … blocks. 3. Parse the JSON inside each call. 4. Execute the matching tool in your app. 5. Feed the tool result back to the model as source text. 6. Ask the model for the final . — research assistant workflows — live search and browsing agents — citation-style answers -…
Модальности:
Генерация текста
Области применения:
Диалог / чат Вызов функций (Tool use)
Задача: Генерация текста
Автор: Pharos-ai
Теги: gemma4_unified, image-text-to-text, research-assistant, tool-use, citations, conversational, endpoints_compatible
Лайков: 4 | Загрузок: 20
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
