Comments (2)
It sounds like the PDFOCRLoader is not converting images in a PDF to text as expected. Here are some steps to troubleshoot and potentially resolve the issue:
-
Check Dependencies: Ensure that
fitz
(PyMuPDF) and OpenCV libraries are installed. These are essential for processing PDF files and images. Install them using:pip install pymupdf pip install opencv-python-headless
-
Image Quality: The OCR's accuracy can be affected by the image quality in the PDF. Low-quality images may not be converted accurately.
-
OCR Threshold: The
PDF_OCR_THRESHOLD
setting determines which images are processed based on their size relative to the page. Adjusting these values inconfigs/kb_config.py.example
might help if your images are not being recognized due to their size. -
Rotation Handling: Ensure that image rotation is correctly handled before OCR processing. Incorrect rotation can lead to recognition errors.
-
OCR Engine Setup: Verify that the OCR engine is correctly set up and functioning. Issues with the OCR engine can prevent successful image to text conversion.
If you're encountering specific error messages or if the images within the PDF are of a particular quality or size, providing more details could help in identifying a more specific solution.
Details
Sources
- pdfloader为什么要加图片尺寸检测?
- markdown_docs/document_loaders/mypdfloader.md
- document_loaders/mypdfloader.py
- configs/kb_config.py.example
- document_loaders/myimgloader.py
- document_loaders/ocr.py
About Dosu
This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.
Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.
To continue the conversation, mention @dosu.
from langchain-chatchat.
这个issue似乎应该去ocr提
from langchain-chatchat.
Related Issues (20)
- [BUG]httpcore.RemoteProtocolError: peer closed connection without sending complete message body (incomplete chunked read)
- 配置好vllm配置之后启动startup.py时候遇到一个问题,似乎是缺少一个参数配置,具体报错如下
- 运行后卡柱不动
- 在初始化过程中,显存爆了 HOT 1
- 知识库匹配需要原文回答,而不是润色的内容
- 这个项目中的fastapi 怎么在vscode 调试时 重载代码? uvicorn --reload时报错
- 知识库问答调用add_message_to_db 无法保存response
- UnstructuredMarkdownLoader会丢失Markdown的结构标识
- 怎么使用splite
- [FEATURE] 搜索引擎支持百度api
- 请问怎么看最后传给大模型的历史对话和用户询问,我目前只跟踪到以下部分。
- http://127.0.0.1:7861/knowledge_base/kb_summary_api/summary_file_to_vector_store 进行文件总结 响应7分钟后出现一下报错,是超时了吗,这个逻辑是在哪啊,
- 上传文件不支持json格式的吗,似乎上传后解析不了
- 问答的第二个问题就会卡住中断
- cannot import name 'PDFResourceManag er' from 'pdfminer.converter'这是什么错误[BUG] 简洁阐述问题 / Concise description of the issue HOT 1
- 如何同时接入多个封装好的openai api格式大模型 HOT 2
- 请问怎么计算输出的token数量?这个框架有现成支持的方法吗
- 调用讯飞星火api,没有输出回答 HOT 2
- [BUG] 知识库问答匹配不到/ Concise description of the issue HOT 2
- 是否可以支持用户中断模型输出
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from langchain-chatchat.