Anthropic으로 함수 호출을 사용하여 Claude의 기능 향상
컬렉션을 사용해 정리하기
내 환경설정을 기준으로 콘텐츠를 저장하고 분류하세요.
Anthropic Claude를 사용하여 함수 호출을 통해 Google Places API와 같은 외부 도구를 쿼리합니다. 이 샘플은 Claude 프롬프트에서 Text Search Places API를 직접 호출하여 사용자의 검색어를 기반으로 장소에 관한 정보를 가져옵니다.
더 살펴보기
이 코드 샘플이 포함된 자세한 문서는 다음을 참조하세요.
코드 샘플
달리 명시되지 않는 한 이 페이지의 콘텐츠에는 Creative Commons Attribution 4.0 라이선스에 따라 라이선스가 부여되며, 코드 샘플에는 Apache 2.0 라이선스에 따라 라이선스가 부여됩니다. 자세한 내용은 Google Developers 사이트 정책을 참조하세요. 자바는 Oracle 및/또는 Oracle 계열사의 등록 상표입니다.
[[["이해하기 쉬움","easyToUnderstand","thumb-up"],["문제가 해결됨","solvedMyProblem","thumb-up"],["기타","otherUp","thumb-up"]],[["이해하기 어려움","hardToUnderstand","thumb-down"],["잘못된 정보 또는 샘플 코드","incorrectInformationOrSampleCode","thumb-down"],["필요한 정보/샘플이 없음","missingTheInformationSamplesINeed","thumb-down"],["번역 문제","translationIssue","thumb-down"],["기타","otherDown","thumb-down"]],[],[],[],null,["# Use function calling with Anthropic to enhance the capabilities of Claude\n\nUse function calling with Anthropic Claude to query external tools, such as the Google Places API. The sample calls the Text Search Places API directly from your Claude prompt to retrieve information about places based on a user's query.\n\nExplore further\n---------------\n\n\nFor detailed documentation that includes this code sample, see the following:\n\n- [Request predictions with Claude models](/vertex-ai/generative-ai/docs/partner-models/claude/use-claude)\n\nCode sample\n-----------\n\n### Python\n\n\nBefore trying this sample, follow the Python setup instructions in the\n[Vertex AI quickstart using\nclient libraries](/vertex-ai/docs/start/client-libraries).\n\n\nFor more information, see the\n[Vertex AI Python API\nreference documentation](/python/docs/reference/aiplatform/latest).\n\n\nTo authenticate to Vertex AI, set up Application Default Credentials.\nFor more information, see\n\n[Set up authentication for a local development environment](/docs/authentication/set-up-adc-local-dev-environment).\n\n # TODO(developer): Vertex AI SDK - uncomment below & run\n # pip3 install --upgrade --user google-cloud-aiplatform\n # gcloud auth application-default login\n # pip3 install -U 'anthropic[vertex]'\n from anthropic import AnthropicVertex\n\n # TODO(developer): Update and un-comment below line\n # PROJECT_ID = \"your-project-id\"\n\n client = AnthropicVertex(project_id=PROJECT_ID, region=\"us-east5\")\n message = client.messages.create(\n model=\"claude-3-5-sonnet-v2@20241022\",\n max_tokens=1024,\n tools=[\n {\n \"name\": \"text_search_places_api\",\n \"description\": \"returns information about a set of places based on a string\",\n \"input_schema\": {\n \"type\": \"object\",\n \"properties\": {\n \"textQuery\": {\n \"type\": \"string\",\n \"description\": \"The text string on which to search\",\n },\n \"priceLevels\": {\n \"type\": \"array\",\n \"description\": \"Price levels to query places, value can be one of [PRICE_LEVEL_INEXPENSIVE, PRICE_LEVEL_MODERATE, PRICE_LEVEL_EXPENSIVE, PRICE_LEVEL_VERY_EXPENSIVE]\",\n },\n \"openNow\": {\n \"type\": \"boolean\",\n \"description\": \"whether those places are open for business.\",\n },\n },\n \"required\": [\"textQuery\"],\n },\n }\n ],\n messages=[\n {\n \"role\": \"user\",\n \"content\": \"What are some affordable and good Italian restaurants open now in San Francisco??\",\n }\n ],\n )\n print(message.model_dump_json(indent=2))\n # Example response:\n # {\n # \"id\": \"msg_vrtx_018pk1ykbbxAYhyWUdP1bJoQ\",\n # \"content\": [\n # {\n # \"text\": \"To answer your question about affordable and good Italian restaurants\n # that are currently open in San Francisco....\n # ...\n\nWhat's next\n-----------\n\n\nTo search and filter code samples for other Google Cloud products, see the\n[Google Cloud sample browser](/docs/samples?product=generativeaionvertexai)."]]