mirror of
https://github.com/VectifyAI/PageIndex.git
synced 2026-07-24 21:41:04 +02:00
chore: name the extra after its dependency; keep README install section minimal
This commit is contained in:
parent
472d871ac3
commit
74c8f7b271
4 changed files with 3 additions and 5 deletions
|
|
@ -153,8 +153,6 @@ A unified `PageIndexClient` powers both local self-hosted and cloud-managed mode
|
|||
pip install pageindex
|
||||
```
|
||||
|
||||
Local-mode image extraction uses PyMuPDF (AGPL-licensed) and is an optional extra: `pip install "pageindex[images]"`. Without it, local indexing is text-only.
|
||||
|
||||
### Quick start
|
||||
|
||||
```python
|
||||
|
|
|
|||
|
|
@ -816,7 +816,7 @@ def get_page_tokens(pdf_path, model=None, pdf_parser="PyPDF2"):
|
|||
page_list.append((page_text, token_length))
|
||||
return page_list
|
||||
elif pdf_parser == "PyMuPDF":
|
||||
import pymupdf # optional dependency: pip install pageindex[images]
|
||||
import pymupdf # optional dependency: pip install pageindex[pymupdf]
|
||||
if isinstance(pdf_path, BytesIO):
|
||||
pdf_stream = pdf_path
|
||||
doc = pymupdf.open(stream=pdf_stream, filetype="pdf")
|
||||
|
|
|
|||
|
|
@ -56,7 +56,7 @@ class PdfParser:
|
|||
if not _warned_no_pymupdf:
|
||||
logging.getLogger(__name__).warning(
|
||||
"PyMuPDF is not installed; skipping image extraction. "
|
||||
'Install with: pip install "pageindex[images]"')
|
||||
'Install with: pip install "pageindex[pymupdf]"')
|
||||
_warned_no_pymupdf = True
|
||||
return {}
|
||||
|
||||
|
|
|
|||
|
|
@ -35,7 +35,7 @@ typing-extensions = ">=4.9.0"
|
|||
pydantic = ">=2.5.0,<3.0.0"
|
||||
|
||||
[tool.poetry.extras]
|
||||
images = ["pymupdf"]
|
||||
pymupdf = ["pymupdf"]
|
||||
|
||||
[tool.poetry.group.dev.dependencies]
|
||||
pytest = ">=7.0"
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue