merge master

.github/workflows/close-issue.yml

@@ -0,0 +1,22 @@
+name: Close inactive issues
+on:
+  schedule:
+    - cron: "30 1 * * *"
+
+jobs:
+  close-issues:
+    runs-on: ubuntu-latest
+    permissions:
+      issues: write
+      pull-requests: write
+    steps:
+      - uses: actions/stale@v5
+        with:
+          days-before-issue-stale: 30
+          days-before-issue-close: 14
+          stale-issue-label: "stale"
+          stale-issue-message: "This issue is stale because it has been open for 30 days with no activity."
+          close-issue-message: "This issue was closed because it has been inactive for 14 days since being marked as stale."
+          days-before-pr-stale: -1
+          days-before-pr-close: -1
+          repo-token: ${{ secrets.GITHUB_TOKEN }}

.gitignore

@@ -4,7 +4,7 @@ logs
 .idea/
 __pycache__/
 /knowledge_base/
-configs/*.py
+/configs/*.py
 .vscode/
 .pytest_cache/
 *.bak

README.md

@@ -488,7 +488,7 @@ $ streamlit run webui.py --server.port 666
 
 ## 项目交流群
 
-<img src="img/qr_code_59.jpg" alt="二维码" width="300" height="300" />
+<img src="img/qr_code_60.jpg" alt="二维码" width="300" height="300" />
 
 🎉 langchain-ChatGLM 项目微信交流群，如果你也对本项目感兴趣，欢迎加入群聊参与讨论交流。
 

document_loaders/mypdfloader.py

@@ -6,7 +6,7 @@ import tqdm
 class RapidOCRPDFLoader(UnstructuredFileLoader):
     def _get_elements(self) -> List:
         def pdf2text(filepath):
-            import fitz
+            import fitz # pyMuPDF里面的fitz包，不要与pip install fitz混淆
             from rapidocr_onnxruntime import RapidOCR
             import numpy as np
             ocr = RapidOCR()

server/knowledge_base/utils.py

@@ -74,8 +74,8 @@ LOADER_DICT = {"UnstructuredHTMLLoader": ['.html'],
                "RapidOCRLoader": ['.png', '.jpg', '.jpeg', '.bmp'],
                "UnstructuredFileLoader": ['.eml', '.msg', '.rst',
                                           '.rtf', '.txt', '.xml',
-                                          '.doc', '.docx', '.epub', '.odt',
-                                          '.ppt', '.pptx', '.tsv'],  # '.xlsx'
+                                          '.docx', '.epub', '.odt',
+                                          '.ppt', '.pptx', '.tsv'],
                }
 SUPPORTED_EXTS = [ext for sublist in LOADER_DICT.values() for ext in sublist]