[OpenAI API] OpenAI Token
·
🗣️ Natural Language Processing
https://github.com/seohyunjun/openAI_API_token GitHub - seohyunjun/openAI_API_token: openAI API token information openAI API token information. Contribute to seohyunjun/openAI_API_token development by creating an account on GitHub. github.com
[LangChain] No using OpenAI API RetrievalQA
·
🗣️ Natural Language Processing
LangChain No using OpenAI API (1) QA를 위한 Document 불러오기 # Load and process the text files # loader = TextLoader("./data/texts") loader = DirectoryLoader('./pdf/', glob="./*.pdf", loader_cls=PyPDFLoader) documents = loader.load() # Document 분절 text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200) texts = text_splitter.split_documents(documents) (2) Embedding # HuggingF..
[Mac] Transformer model downloaded path
·
🗣️ Natural Language Processing
https://discuss.huggingface.co/t/where-is-the-model-path-on-macos/21376 macOS의 모델 경로는 어디에 있습니까?AutoModelxxx를 사용하여 모델을 다운로드했지만 모델이 저장된 경로를 찾을 수 없습니다. 어디에 있습니까, os 코드로 어떻게 찾을 수 있습니까? discuss.huggingface.co Transformer 다운로드 모델 경로 ~/.cache/huggingface/hub/ ~/.cache/huggingface/hub/ 안쓰는 모델 제거 rm -rf [model]
[LangChain] Retrieval PDF
·
🗣️ Natural Language Processing
Retrieval PDF PDF 문서 embedding - vectorize db와 비교 - similar score - retreival document (1) Pagkage Import from langchain.vectorstores import Chroma from langchain.text_splitter import RecursiveCharacterTextSplitter from langchain.llms import OpenAI from langchain.chains import RetrievalQA from langchain.document_loaders import TextLoader from langchain.document_loaders import PyPDFLoader from la..
[LangChain] Building Custom Tool
·
🗣️ Natural Language Processing
Default import os os.environ['OPENAI_API_KEY'] = 'sk-...' Building Custom Tools 1) Package Import from langchain import OpenAI from langchain.chat_models import ChatOpenAI from langchain.chains.conversation.memory import ConversationBufferWindowMemory # callback cost from langchain.callbacks import get_openai_callback 2) llm model 설정 turbo_llm = ChatOpenAI( temperature = 0, model_name = 'gpt-3.5..
[OpenAI-GPT] LangChain 효율적인 Token 관리
·
🛠️ Tools/🤖 ChatGPT
LLM + Chain Tool Welcome to LangChain — 🦜🔗 LangChain 0.0.175 python.langchain.com 최근 LangChain을 통한 GPT 서드파티 툴이 쏟아지고 있다. LLM 모델을 활용해 자동으로 Tool을 사용하게 만들어 주고 있다. 그 결과 실제로 원하는 사이트 만들기 - Auto-GPT https://youtu.be/gWy-pJ2ofEM?si=f3pADRKEIZMsdhB2 Q&A 지식 기반 검색 Bot 만들기 https://youtu.be/cFCGUjc33aU?si=s7m0nw4MjKzaoQII 다양한 서비스가 LLM 모델을 통해 개발되고 있다. 그러나 우리가 사용 가능한 리소스로는 Meta에서 발표한 LLAMA 모델이나 Open소스로 공개한 data..
Could not initialize webview: Error: Could not register service worker: InvalidStateError: Failed to register a ServiceWorker: The document is in an invalid state..}
·
🐍 Python
https://github.com/microsoft/vscode/issues/128649 Error loading webview: Error: Could not register service workers: InvalidStateError: Failed to register a ServiceWorker: The doc Does this issue occur when all extensions are disabled?: Yes/No VS Code Version: 1.58.0 2d23c42 x64 OS Version: mac os 10.15.7 Steps to Reproduce: install extension Draw.io Integration open xx.drawio github.com VSCODE S..
[leetcode-36] Valid Sudoku
·
🐢 One step
LeetCode-36 Valid Sudoku : A Sudoku board (partially filled) could be valid but is not necessarily solvable. note : Only the filled cells need to be validated according to the mentioned rules.Answer :::python class Solution: def isValidSudoku(self, board: List[List[str]]) -> bool: def valid_row(i, j, row): if row==1: item = board[i] else: item = [board[n][j] for n in range(0,9)] p = [] box = [bo..
다했다
'분류 전체보기' 카테고리의 글 목록 (22 Page)