■ Document 클래스를 사용해 수동으로 문서를 작성하는 방법을 보여준다.
▶ main.py
|
1 2 3 4 5 6 7 8 9 10 11 12 13 |
from llama_index.core import Document textList = [ "This is the first document. It contains some sample text.", "This is the second document. It also contains some sample text.", "This is the third document with different content." ] documentList = [Document(text = text) for text in textList] print(documentList) |
▶ 실행 결과
|
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 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 |
[ Document( id_ ='40b4f5f2-c8be-404a-a0e9-18eedf1916f7', embedding = None, metadata = {}, excluded_embed_metadata_keys = [], excluded_llm_metadata_keys = [], relationships = {}, text = 'This is the first document. It contains some sample text.', start_char_idx = None, end_char_idx = None, text_template = '{metadata_str}\n\n{content}', metadata_template = '{key}: {value}', metadata_seperator ='\n' ), Document ( id_ = '28b47184-b448-41ce-a6fe-b3df69286081', embedding = None, metadata = {}, excluded_embed_metadata_keys = [], excluded_llm_metadata_keys = [], relationships = {}, text = 'This is the second document. It also contains some sample text.', start_char_idx = None, end_char_idx = None, text_template = '{metadata_str}\n\n{content}', metadata_template = '{key}: {value}', metadata_seperator = '\n' ), Document ( id_ = 'c60f0ec7-db70-4a7f-8936-7ddeed886c94', embedding = None, metadata = {}, excluded_embed_metadata_keys = [], excluded_llm_metadata_keys = [], relationships = {}, text = 'This is the third document with different content.', start_char_idx = None, end_char_idx = None, text_template = '{metadata_str}\n\n{content}', metadata_template = '{key}: {value}', metadata_seperator = '\n' ) ] |
▶ requirements.txt
|
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 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 |
aiohttp==3.9.5 aiosignal==1.3.1 annotated-types==0.7.0 anyio==4.4.0 async-timeout==4.0.3 attrs==23.2.0 beautifulsoup4==4.12.3 certifi==2024.6.2 charset-normalizer==3.3.2 click==8.1.7 dataclasses-json==0.6.6 Deprecated==1.2.14 dirtyjson==1.0.8 distro==1.9.0 exceptiongroup==1.2.1 frozenlist==1.4.1 fsspec==2024.6.0 greenlet==3.0.3 h11==0.14.0 httpcore==1.0.5 httpx==0.27.0 idna==3.7 joblib==1.4.2 llama-index==0.10.43 llama-index-agent-openai==0.2.7 llama-index-cli==0.1.12 llama-index-core==0.10.43 llama-index-embeddings-openai==0.1.10 llama-index-indices-managed-llama-cloud==0.1.6 llama-index-legacy==0.9.48 llama-index-llms-openai==0.1.22 llama-index-multi-modal-llms-openai==0.1.6 llama-index-program-openai==0.1.6 llama-index-question-gen-openai==0.1.3 llama-index-readers-file==0.1.23 llama-index-readers-llama-parse==0.1.4 llama-parse==0.4.4 llamaindex-py-client==0.1.19 marshmallow==3.21.3 multidict==6.0.5 mypy-extensions==1.0.0 nest-asyncio==1.6.0 networkx==3.3 nltk==3.8.1 numpy==1.26.4 openai==1.33.0 packaging==24.0 pandas==2.2.2 pillow==10.3.0 pydantic==2.7.3 pydantic_core==2.18.4 pypdf==4.2.0 python-dateutil==2.9.0.post0 pytz==2024.1 PyYAML==6.0.1 regex==2024.5.15 requests==2.32.3 six==1.16.0 sniffio==1.3.1 soupsieve==2.5 SQLAlchemy==2.0.30 striprtf==0.0.26 tenacity==8.3.0 tiktoken==0.7.0 tqdm==4.66.4 typing-inspect==0.9.0 typing_extensions==4.12.2 tzdata==2024.1 urllib3==2.2.1 wrapt==1.16.0 yarl==1.9.4 |
※ pip install llama-index 명령을 실행했다.