© 2025-2026 PySpect
| Dependency | Optional | Group |
|---|---|---|
| beautifulsoup4 | false | |
| charset-normalizer | false | |
| emoji | false | |
| filelock | false |
| Package | Optional | Group |
|---|---|---|
| acryl-datahub | true | confluence |
| agno | true | markdown |
| airbyte-cdk | true | file-based |
| crewai-tools | true | xml |
| pueblo | true | nlp |
| unstructured-ingest | true | doc |
| filetype | false |
| html5lib | false |
| installer | false |
| langdetect | false |
| lxml | false |
| nh3 | false |
| numba | false |
| numpy | false |
| psutil | false |
| python-iso639 | false |
| python-magic | false |
| python-oxmsg | false |
| rapidfuzz | false |
| regex | false |
| requests | false |
| spacy | false |
| tqdm | false |
| typing-extensions | false |
| unstructured-client | false |
| wrapt | false |
| google-cloud-vision | true | all-docs |
| markdown | true | all-docs |
| msoffcrypto-tool | true | all-docs |
| networkx | true | all-docs |
| openai-whisper | true | all-docs |
| openpyxl | true | all-docs |
| paddlepaddle | true | paddleocr |
| pandas | true | all-docs |
| pdf2image | true | all-docs |
| pdfminer-six | true | all-docs |
| pi-heif | true | all-docs |
| pikepdf | true | all-docs |
| pypandoc-binary | true | all-docs |
| pypdf | true | all-docs |
| python-docx | true | all-docs |
| python-pptx | true | all-docs |
| sentencepiece | true | huggingface |
| tiktoken | true | chunking-tokens |
| torch | true | huggingface |
| transformers | true | huggingface |
| unstructured-inference | true | all-docs |
| unstructured-ingest | true | ingest |
| unstructured-paddleocr | true | paddleocr |
| unstructured-pytesseract | true | all-docs |
| xlrd | true | all-docs |