RAG interactive prompts added, issues resolved

crazy_functions/rag_fns/llama_index_worker.py

@@ -59,7 +59,7 @@ class SaveLoad():
     def purge(self):
         import shutil
         shutil.rmtree(self.checkpoint_dir, ignore_errors=True)
-        self.vs_index = self.create_new_vs()
+        self.vs_index = self.create_new_vs(self.checkpoint_dir)
 
 
 class LlamaIndexRagWorker(SaveLoad):

crazy_functions/rag_fns/rag_file_support.py

@@ -1,10 +1,8 @@
 import os
+from llama_index.core import SimpleDirectoryReader
 
-import markdown
+# 保留你原有的自定义解析函数
 from PyPDF2 import PdfReader
-from bs4 import BeautifulSoup
-from docx import Document as DocxDocument
-
 
 def extract_text_from_pdf(file_path):
     reader = PdfReader(file_path)
@@ -13,35 +11,24 @@ def extract_text_from_pdf(file_path):
         text += page.extract_text() + "\n"
     return text
 
-def extract_text_from_docx(file_path):
-    doc = DocxDocument(file_path)
-    return "\n".join([para.text for para in doc.paragraphs])
-
-def extract_text_from_txt(file_path):
-    with open(file_path, 'r', encoding='utf-8') as f:
-        return f.read()
-
-def extract_text_from_md(file_path):
-    with open(file_path, 'r', encoding='utf-8') as f:
-        md_content = f.read()
-    return markdown.markdown(md_content)
-
-def extract_text_from_html(file_path):
-    with open(file_path, 'r', encoding='utf-8') as f:
-        soup = BeautifulSoup(f, 'html.parser')
-    return soup.get_text()
-
+# 修改后的 extract_text 函数，结合 SimpleDirectoryReader 和自定义解析逻辑
 def extract_text(file_path):
     _, ext = os.path.splitext(file_path.lower())
+
+    # 使用 SimpleDirectoryReader 处理它支持的文件格式
+    if ext in ['.txt', '.md', '.pdf', '.docx', '.html']:
+        try:
+            reader = SimpleDirectoryReader(input_files=[file_path])
+            documents = reader.load_data()
+            if len(documents) > 0:
+                return documents[0].text
+        except Exception as e:
+            pass
+
+    # 如果 SimpleDirectoryReader 失败，或文件格式不支持，使用自定义解析逻辑
     if ext == '.pdf':
-        return extract_text_from_pdf(file_path)
-    elif ext in ['.docx', '.doc']:
-        return extract_text_from_docx(file_path)
-    elif ext == '.txt':
-        return extract_text_from_txt(file_path)
-    elif ext == '.md':
-        return extract_text_from_md(file_path)
-    elif ext == '.html':
-        return extract_text_from_html(file_path)
-    else:
-        raise ValueError(f"Unsupported file extension: {ext}")
+        try:
+            return extract_text_from_pdf(file_path)
+        except Exception as e:
+            pass
+    return None