paraphrase
Paraphrase Text
Generate alternative phrasings of input text. Choose from different styles like casual, formal, short, long, or general. Optionally paraphrase only a subsection of the text using start and end indices.
paraphrase
Generate alternative phrasings of input text. Choose from different styles like casual, formal, short, long, or general. Optionally paraphrase only a subsection of the text using start and end indices.
text_completion
Generate text completions using AI21's Jurassic-2 models. Provide a prompt and receive one or more continuations. Supports configurable temperature, penalties, and stop sequences.
segment_text
Break long text into paragraphs segmented by distinct topics. Each segment represents a coherent topical unit. Can also process content from a URL.
get_file
Retrieve metadata for a specific file in your AI21 document library by its ID.
maestro_run
Create and execute a Maestro AI agent run. Maestro is an AI orchestration system that can search, reason, validate, and adapt in real time. Supports model selection (AI21 or third-party), compute budget control, requirements validation, and tool integration including file search and web search.
text_improvements
Analyze text and suggest improvements for fluency, vocabulary, and clarity. Select one or more improvement types to apply.
summarize
Generate a grounded summary of text or a web page URL. The summary stays faithful to the original content. Optionally focus the summary on a specific topic or keyword.
contextual_answer
Answer a question based on a provided context document. Returns an answer only if it can be found in the context, preventing hallucination. Returns null if the answer is not in the context.
grammar_check
Detect and suggest corrections for grammatical errors in text. Identifies issues including grammar, spelling, punctuation, missing words, wrong words, and word repetition.
list_files
List files in your AI21 document library. Optionally filter by labels. Returns file metadata including name, type, size, status, and labels.
delete_file
Permanently delete a file from your AI21 document library.
update_file
Update metadata of a file in your AI21 document library. You can modify labels and the public URL.
conversational_rag
Ask questions over your uploaded documents using conversational RAG. Supports multi-turn conversations, document filtering by labels or file IDs, and configurable retrieval strategies. The system determines whether to answer from model knowledge or retrieved documents.
chat_completion
Generate a chat completion using AI21's Jamba models. Supports multi-turn conversations with system, user, assistant, and tool messages. Optionally enable JSON mode, pass documents for context, or define tools for function calling.
summarize_by_segment
Break text or a web page into logical segments and summarize each one individually. Useful for long documents where you need per-section summaries rather than one overall summary.
Access AI21 Labs' Jamba and Jurassic-2 large language models for chat completions, text generation, and specialized language processing tasks. Generate conversational responses with long-context support (256K tokens), orchestrate AI agents via Maestro for RAG and enterprise automation, and upload/manage documents for conversational retrieval-augmented generation. Task-specific APIs enable text summarization, paraphrasing, text segmentation, grammatical error correction, text improvement suggestions, and contextual question answering. Supports streaming, function calling, JSON mode, and configurable generation parameters.
Common questions about connecting Studio by Ai 21 Labs to AI agents with Metorial.