■ RecursiveJsonSplitter 클래스의 create_documents 메소드를 사용해 JSON 딕셔너리에서 문서 리스트를 구하는 방법을 보여준다.
▶ main.py
|
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 |
import requests from langchain_text_splitters import RecursiveJsonSplitter response = requests.get("https://api.smith.langchain.com/openapi.json") jsonDictionary = response.json() recursiveJsonSplitter = RecursiveJsonSplitter(max_chunk_size = 300) documentList = recursiveJsonSplitter.create_documents(texts = [jsonDictionary]) for document in documentList[:3]: print(document) print() """ page_content='{"openapi": "3.1.0", "info": {"title": "LangSmith", "version": "0.1.0"}, "paths": {"/api/v1/sessions/{session_id}": {"get": {"tags": ["tracer-sessions"], "summary": "Read Tracer Session", "description": "Get a specific session."}}}}' page_content='{"paths": {"/api/v1/sessions/{session_id}": {"get": {"operationId": "read_tracer_session_api_v1_sessions__session_id__get", "security": [{"API Key": []}, {"Tenant ID": []}, {"Bearer Auth": []}]}}}}' page_content='{"paths": {"/api/v1/sessions/{session_id}": {"get": {"parameters": [{"name": "session_id", "in": "path", "required": true, "schema": {"type": "string", "format": "uuid", "title": "Session Id"}}, {"name": "include_stats", "in": "query", "required": false, "schema": {"type": "boolean", "default": false, "title": "Include Stats"}}, {"name": "accept", "in": "header", "required": false, "schema": {"anyOf": [{"type": "string"}, {"type": "null"}], "title": "Accept"}}]}}}}' """ |
▶ requirements.txt
|
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 |
annotated-types==0.7.0 certifi==2024.6.2 charset-normalizer==3.3.2 idna==3.7 jsonpatch==1.33 jsonpointer==3.0.0 langchain-core==0.2.10 langchain-text-splitters==0.2.2 langsmith==0.1.82 orjson==3.10.5 packaging==24.1 pydantic==2.7.4 pydantic_core==2.18.4 PyYAML==6.0.1 requests==2.32.3 tenacity==8.4.2 typing_extensions==4.12.2 urllib3==2.2.2 |
※ pip install langchain-text-splitters 명령을 실행했다.