원문에서 더 깊이 읽기
GEO·AI 검색·마케팅 관련 자료를 주제별로 찾아보세요.
Google · Gemini API 문서 · AI 검색 · 발행일 미상
Gemini 4 Argon is now available. Try it out . Home Gemini API Docs Send feedback Function calling with the Gemini API Function calling lets you connect models to external tools and APIs. Instead of generating text responses, the model determines when to call specific functions and provides the necessary parameters to execute real-world actions. This allows the model to act as a bridge between natural language and real-world actions and data. Function calling has 3 primary use cases: Take Actions: Interact with external systems using APIs, such as scheduling appointments, creating invoices, sen
Google · Gemini API 문서 · AI 검색 · 발행일 미상
Gemini 4 Argon is now available. Try it out . Home Gemini API Docs Send feedback Structured outputs You can configure Gemini models to generate responses that adhere to a provided JSON Schema. This ensures predictable, type-safe results and simplifies extracting structured data from unstructured text. Using structured outputs is ideal for: Data extraction: Pull specific information like names and dates from text. Structured classification: Classify text into predefined categories. Agentic workflows: Generate structured inputs for tools or APIs. In addition to supporting JSON Schema in the REST
Google · Gemini API 문서 · AI 검색 · 발행일 미상
Gemini 4 Argon is now available. Try it out . Home Gemini API Docs Send feedback Thought signatures Send feedback
Google · Gemini API 문서 · AI 검색 · 발행일 미상
Gemini 4 Argon is now available. Try it out . Home Gemini API Docs Send feedback Gemini thinking Gemini models use a "thinking process" that significantly improves their reasoning and multi-step planning abilities, making them highly effective for complex tasks such as coding, advanced mathematics, and data analysis. When you use a thinking model, Gemini reasons internally before responding. The Interactions API surfaces this reasoning via thought steps, dedicated steps that appear chronologically alongside function calls, user inputs or model outputs in the steps array. Every thought step con
Google · Gemini API 문서 · AI 검색 · 발행일 미상
Gemini 4 Argon is now available. Try it out . Home Gemini API Docs Send feedback Audio understanding Gemini can analyze audio input and generate text responses. Python from google import genai import base64 client = genai . Client () uploaded_file = client . files . upload ( file = "path/to/sample.mp3" ) interaction = client . interactions . create ( model = "gemini-3.8-flash" , input = [ { "type" : "text" , "text" : "Describe this audio clip" }, { "type" : "audio" , "uri" : uploaded_file . uri , "mime_type" : uploaded_file . mime_type } ] ) print ( interaction . output_text ) JavaScript impor
Google · Gemini API 문서 · AI 검색 · 발행일 미상
Gemini 4 Argon is now available. Try it out . Home Gemini API Docs Send feedback Document understanding Gemini models can process documents in PDF format, using native vision to understand entire document contexts. This goes beyond just text extraction, allowing Gemini to: Analyze and interpret content, including text, images, diagrams, charts, and tables, even in long documents up to 1000 pages. Extract information into structured output formats. Summarize and answer questions based on both the visual and textual elements in a document. Transcribe document content (e.g. to HTML), preserving l
Google · Gemini API 문서 · AI 검색 · 발행일 미상
Gemini 4 Argon is now available. Try it out . Home Gemini API Docs Send feedback Video understanding To learn about video generation, see the Gemini Omni Flash guide. Gemini models can process videos, enabling many frontier developer use cases that would have historically required domain specific models. Some of Gemini's vision capabilities include the ability to: describe, segment, and extract information from videos, answer questions about video content, and refer to specific timestamps within a video. You can provide videos as input to Gemini in the following ways: Input method Max size Rec
Google · Gemini API 문서 · AI 검색 · 발행일 미상
Gemini 4 Argon is now available. Try it out . Home Gemini API Docs Send feedback Video generation in the Gemini API Use Gemini Omni Flash as your model for video generation and conversational video editing in the Gemini API. It provides superior video coherence, multi-input reasoning (supporting text, images, audio, and video inputs simultaneously), character consistency, factual accuracy, and multi-turn conversational editing (e.g., element replacement or perspective changes). The Veo 3.1 Preview in the Gemini API has been shut down. Gemini Omni Flash Gemini Omni Flash is a fast, multimodal m
Anthropic · Claude 공식 문서 · AI 마케팅 · 발행일 미상
--- title: Context windows url: https://platform.claude.com/docs/en/build-with-claude/context-windows description: Understand how the context window works, how extended thinking and tool use count toward it, and how to manage context as conversations grow. --- As conversations grow, you’ll eventually approach context window limits. For long-running conversations and agentic workflows, [server-side compaction](https://platform.claude.com/docs/en/build-with-claude/compaction) is the primary strategy for context management. The “context window” refers to all the text a language model can referenc
Anthropic · Claude 공식 문서 · 콘텐츠 · SEO · 발행일 미상
--- title: Context editing url: https://platform.claude.com/docs/en/build-with-claude/context-editing description: Automatically manage conversation context as it grows with context editing. featureMetadata: status: beta betaHeader: context-management-2025-06-27 zdr: eligibility: eligible note: Excludes [Covered Models](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements). Context edits (tool use clearing and thinking clearing) are applied in real time. supportedModels: - claude-fable-5-1 - claude-mythos-5-1 - claude-fable-5 - cla
Anthropic · Claude 공식 문서 · AI 마케팅 · 발행일 미상
--- title: Computer use tool url: https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool description: Give Claude screenshot, mouse, and keyboard control of a desktop environment with the computer use tool, the computer_toolset_20260801 client toolset. featureMetadata: betaHeader: computer-use-2025-11-24, computer-use-2025-01-24 zdr: eligibility: eligible note: Excludes [Covered Models](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements). Client-side tool where screenshots and files are captured and store
Anthropic · Claude 공식 문서 · 콘텐츠 · SEO · 발행일 미상
--- title: Compaction that keeps recent turns url: https://platform.claude.com/docs/en/build-with-claude/compaction-keep-recent-turns description: Summarize the older turns of a conversation with on-demand compaction and send the most recent turns after the summary, word for word. featureMetadata: status: beta betaHeader: compact-2026-09-04 supportedModels: - claude-fable-5-1 - claude-mythos-5-1 - claude-fable-5 - claude-mythos-5 - claude-mythos-preview - claude-opus-5-5 - claude-opus-5 - claude-sonnet-5-5 - claude-sonnet-5 - claude-haiku-5-5 - claude-opus-4-8 - claude-opus-4-7 - claude-opus-4
Anthropic · Claude 공식 문서 · AI 마케팅 · 발행일 미상
--- title: Compaction overview url: https://platform.claude.com/docs/en/build-with-claude/compaction description: Learn what compaction does, how compaction on demand and compaction at a token threshold differ, and which page covers your task. --- Compaction replaces the older turns of a conversation with a summary that Claude writes on the server, so you need no summarization code of your own. It keeps a long conversation or agent task inside the context window, and it keeps the active context small, because response quality degrades as a conversation grows. If you want to skip this overview,
Anthropic · Claude 공식 문서 · 콘텐츠 · SEO · 발행일 미상
--- title: Compaction on demand url: https://platform.claude.com/docs/en/build-with-claude/compaction-on-demand description: Ask Claude to summarize a conversation when your application chooses, then continue from the summary. featureMetadata: status: beta betaHeader: compact-2026-09-04 supportedModels: - claude-fable-5-1 - claude-mythos-5-1 - claude-fable-5 - claude-mythos-5 - claude-mythos-preview - claude-opus-5-5 - claude-opus-5 - claude-sonnet-5-5 - claude-sonnet-5 - claude-haiku-5-5 - claude-opus-4-8 - claude-opus-4-7 - claude-opus-4-6 - claude-sonnet-4-6 supportedPlatforms: Claude API:
Anthropic · Claude 공식 문서 · 콘텐츠 · SEO · 발행일 미상
--- title: Compaction in the background url: https://platform.claude.com/docs/en/build-with-claude/compaction-background description: Request an on-demand compaction summary while the conversation continues on its full history, then swap the block in when it arrives. featureMetadata: status: beta betaHeader: compact-2026-09-04 supportedModels: - claude-fable-5-1 - claude-mythos-5-1 - claude-fable-5 - claude-mythos-5 - claude-mythos-preview - claude-opus-5-5 - claude-opus-5 - claude-sonnet-5-5 - claude-sonnet-5 - claude-haiku-5-5 - claude-opus-4-8 - claude-opus-4-7 - claude-opus-4-6 - claude-so
Anthropic · Claude 공식 문서 · 콘텐츠 · SEO · 발행일 미상
--- title: Compaction at a token threshold url: https://platform.claude.com/docs/en/build-with-claude/compaction-threshold description: Have the API summarize older context automatically, inside an ordinary request, when the conversation reaches a token threshold you set. featureMetadata: status: beta betaHeader: compact-2026-01-12 zdr: eligibility: eligible note: Excludes [Covered Models](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements). Server-side compaction results are returned and round-tripped statelessly through the API
Anthropic · Claude 공식 문서 · 콘텐츠 · SEO · 발행일 미상
--- title: Compaction and preserved thinking url: https://platform.claude.com/docs/en/build-with-claude/compaction-thinking-blocks description: When thinking blocks in turns kept after on-demand compaction stay valid on models with preserved thinking, and how to check. featureMetadata: status: beta betaHeader: compact-2026-09-04 supportedModels: - claude-fable-5-1 - claude-mythos-5-1 - claude-fable-5 - claude-mythos-5 - claude-mythos-preview - claude-opus-5-5 - claude-opus-5 - claude-sonnet-5-5 - claude-sonnet-5 - claude-haiku-5-5 - claude-opus-4-8 - claude-opus-4-7 - claude-opus-4-6 - claude-
Anthropic · Claude 공식 문서 · AI 마케팅 · 발행일 미상
--- title: Code execution tool url: https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool description: Run Python and Bash code in a sandboxed container to analyze data, generate files, and iterate on solutions. featureMetadata: status: stable zdr: eligibility: not-eligible note: Container data retained up to 30 days. supportedModels: - claude-fable-5-1 - claude-mythos-5-1 - claude-fable-5 - claude-mythos-5 - claude-mythos-preview - claude-opus-5-5 - claude-opus-5 - claude-sonnet-5-5 - claude-sonnet-5 - claude-haiku-5-5 - claude-haiku-4-5-20251001 - claude-opus-4-8
Anthropic · Claude Code 문서 · 콘텐츠 · SEO · 발행일 미상
> Fetch the complete documentation index at: https://code.claude.com/docs/llms.txt > Use this file to discover all available pages before exploring further. > Tune what Code Review flags on your pull requests with REVIEW.md and CLAUDE.md: recalibrate severity, skip paths, add checks, and see which copy applies. You can change what [Code Review](https://code.claude.com/docs/en/code-review.md) flags on your repository by committing instructions to it. This is how you cut nit volume, stop comments on generated files, or add a rule your team cares about. Put them in one of two files: * **`CLAUDE.m
Anthropic · Claude Code 문서 · 콘텐츠 · SEO · 발행일 미상
> Fetch the complete documentation index at: https://code.claude.com/docs/llms.txt > Use this file to discover all available pages before exploring further. > Turn on Code Review for your Claude organization: connect GitHub, install the Claude GitHub App, choose repositories, and set when reviews run As an Owner of your Claude organization, you turn on Code Review in [**Admin settings > Claude Code**](https://claude.ai/admin-settings/claude-code#code-review) on claude.ai. Reviews run on Anthropic infrastructure, so you don't add workflow files to your repositories. After setup, you choose how
Anthropic · Claude Code 문서 · AI 마케팅 · 발행일 미상
> Fetch the complete documentation index at: https://code.claude.com/docs/llms.txt > Use this file to discover all available pages before exploring further. > Catch bugs in GitHub pull requests with Code Review: Claude reviews each change, verifies its findings, and comments inline. For Team and Enterprise plans With Code Review, Claude reviews the pull requests in your GitHub repositories. Several agents read each change alongside the surrounding code, looking for issues such as logic errors, security vulnerabilities, or broken edge cases. A verification step checks findings against the code
Anthropic · Claude Code 문서 · 콘텐츠 · SEO · 발행일 미상
> Fetch the complete documentation index at: https://code.claude.com/docs/llms.txt > Use this file to discover all available pages before exploring further. > Connect Claude Code to your self-hosted GitHub Enterprise Server instance for cloud sessions, code review, and plugin marketplaces. > [!NOTE] > > GitHub Enterprise Server support is available for Team and Enterprise plans. GitHub Enterprise Server (GHES) support lets your organization use Claude Code with repositories hosted on your self-managed GitHub instance instead of github.com. Once an Owner connects your GHES instance, developers
Anthropic · Claude Code 문서 · 리서치 · 발행일 미상
> Fetch the complete documentation index at: https://code.claude.com/docs/llms.txt > Use this file to discover all available pages before exploring further. > Run a deep, multi-agent code review in the cloud with /code-review ultra to find and verify bugs before you merge. > [!NOTE] > > Ultrareview is a research preview feature. The feature, pricing, and availability may change based on feedback. The command is `/code-review ultra`. When ultrareview is available to your account, `/ultrareview` is an alias. Ultrareview is a deep code review that runs as a [cloud session](https://code.claude.com
Anthropic · Claude Code 문서 · 리서치 · 발행일 미상
> Fetch the complete documentation index at: https://code.claude.com/docs/llms.txt > Use this file to discover all available pages before exploring further. > Run `/code-review` in a Claude Code session to find bugs in your branch's changes, point the review at a pull request or path, and have Claude apply the fixes. `/code-review` is a command you type at the Claude Code prompt, in the session where you're working. Claude reviews the changes on your branch, looks for correctness bugs, and reports what it found in your conversation. Depending on your model and effort level, the review also cov