Rank documents by relevance with AI
Create text embeddings and rerank documents by relevance to improve semantic search.
MCP / oo CLI + SkillСервисов: 2
Возможности
Connect a query with the most relevant passages in a document collection. Generate text embeddings for similarity workflows or rerank candidate documents around a research question.
Rank documents by relevance
Create text embeddings and rerank documents by relevance to improve semantic search.
Search team knowledge
Retrieve relevant passages from indexed team documents.
Попробовать запросы
Замените значения в скобках и скопируйте задачу в подключённого ИИ-ассистента.
Rank documents by relevance
Create text embeddings and rerank documents by relevance to improve semantic search.
Use OOMOL MCP with AIsa to complete this task: Rank [documents] by relevance to [query] and show the best matching passages.
Search team knowledge
Retrieve relevant passages from indexed team documents.
Use OOMOL MCP with OOMOL RAG to complete this task: Use OOMOL RAG to find passages about [question] in the team knowledge base. Cite the returned sources.
Начните работу с Semantic Search
Подключите ИИ-ассистента
Добавьте OOMOL в MCP-клиент и войдите в свою команду, чтобы использовать подключённые сервисы.
Установите oo CLI и Skill, войдите в OOMOL и используйте /oo в ИИ-ассистенте.
Установить oo CLIВыбрать сервис
AIsaUse OOMOL-provided access or connect your AIsa account.
Create text embeddings and rerank documents by relevance to improve semantic search.
Подключить AIsa →OOMOL RAGSign in to OOMOL; no separate provider credential is required.
Use OOMOL services with your current team.
Подключить OOMOL RAG →Попробуйте первую задачу
Use OOMOL MCP with AIsa to complete this task: Rank [documents] by relevance to [query] and show the best matching passages.
Сервисы для Semantic Search
Выберите сервис для задачи. Указано общее число инструментов каждого сервиса.
Все действия
Create Jina Embeddings
Compute Jina embedding vectors for supplied text without storing a retrieval index. AISA documents 1024-dimensional output for the supported models; billing is token-based.
Usage-based pricing.
aisa.create_jina_embeddingsRerank Jina Documents
Rank supplied documents against a query using a Jina reranker, preserving original indexes for retrieval pipelines. No provider index or stored document collection is created; billing is token-based.
Usage-based pricing.
aisa.rerank_jina_documentsRetrieve
Retrieve the most relevant text chunks from the current OOMOL team's knowledge base.
Эмбеддинг запроса: 100 кредитов / 1 млн токенов; Переранжирование (включено по умолчанию): 100 кредитов / 1 млн токенов
- Эмбеддинг запроса
- 100 кредитов / 1 млн токенов
- Переранжирование (включено по умолчанию)
- 100 кредитов / 1 млн токенов
oomol_rag.retrieveПодходящих инструментов нет.
Частые вопросы
How does document reranking help search?
Reranking orders candidate documents by their relevance to a query, helping surface the most useful passages.