Add batch document inquiry function

crazy_functions/rag_fns/llama_index_worker.py

@@ -1,17 +1,13 @@
-import llama_index
-import os
 import atexit
 from loguru import logger
 from typing import List
+
 from llama_index.core import Document
-from llama_index.core.schema import TextNode
-from request_llms.embed_models.openai_embed import OpenAiEmbeddingModel
-from shared_utils.connect_void_terminal import get_chat_default_kwargs
-from llama_index.core import VectorStoreIndex, SimpleDirectoryReader
-from crazy_functions.rag_fns.vector_store_index import GptacVectorStoreIndex
 from llama_index.core.ingestion import run_transformations
-from llama_index.core import PromptTemplate
-from llama_index.core.response_synthesizers import TreeSummarize
+from llama_index.core.schema import TextNode
+
+from crazy_functions.rag_fns.vector_store_index import GptacVectorStoreIndex
+from request_llms.embed_models.openai_embed import OpenAiEmbeddingModel
 
 DEFAULT_QUERY_GENERATION_PROMPT = """\
 Now, you have context information as below:
@@ -63,7 +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):
@@ -75,7 +71,7 @@ class LlamaIndexRagWorker(SaveLoad):
         if auto_load_checkpoint:
             self.vs_index = self.load_from_checkpoint(checkpoint_dir)
         else:
-            self.vs_index = self.create_new_vs(checkpoint_dir)
+            self.vs_index = self.create_new_vs()
         atexit.register(lambda: self.save_to_checkpoint(checkpoint_dir))
 
     def assign_embedding_model(self):
@@ -91,40 +87,52 @@ class LlamaIndexRagWorker(SaveLoad):
         logger.info('oo --------inspect_vector_store end--------')
         return vector_store_preview
 
-    def add_documents_to_vector_store(self, document_list):
-        documents = [Document(text=t) for t in document_list]
+    def add_documents_to_vector_store(self, document_list: List[Document]):
+        """
+        Adds a list of Document objects to the vector store after processing.
+        """
+        documents = document_list
         documents_nodes = run_transformations(
-                        documents,  # type: ignore
-                        self.vs_index._transformations,
-                        show_progress=True
-                    )
+            documents,  # type: ignore
+            self.vs_index._transformations,
+            show_progress=True
+        )
         self.vs_index.insert_nodes(documents_nodes)
-        if self.debug_mode: self.inspect_vector_store()
+        if self.debug_mode:
+            self.inspect_vector_store()
 
-    def add_text_to_vector_store(self, text):
+    def add_text_to_vector_store(self, text: str):
         node = TextNode(text=text)
         documents_nodes = run_transformations(
-                        [node],
-                        self.vs_index._transformations,
-                        show_progress=True
-                    )
+            [node],
+            self.vs_index._transformations,
+            show_progress=True
+        )
         self.vs_index.insert_nodes(documents_nodes)
-        if self.debug_mode: self.inspect_vector_store()
+        if self.debug_mode:
+            self.inspect_vector_store()
 
     def remember_qa(self, question, answer):
         formatted_str = QUESTION_ANSWER_RECORD.format(question=question, answer=answer)
         self.add_text_to_vector_store(formatted_str)
 
     def retrieve_from_store_with_query(self, query):
-        if self.debug_mode: self.inspect_vector_store()
+        if self.debug_mode:
+            self.inspect_vector_store()
         retriever = self.vs_index.as_retriever()
         return retriever.retrieve(query)
 
     def build_prompt(self, query, nodes):
         context_str = self.generate_node_array_preview(nodes)
         return DEFAULT_QUERY_GENERATION_PROMPT.format(context_str=context_str, query_str=query)
-        
+
     def generate_node_array_preview(self, nodes):
         buf = "\n".join(([f"(No.{i+1} | score {n.score:.3f}): {n.text}" for i, n in enumerate(nodes)]))
         if self.debug_mode: logger.info(buf)
         return buf
+
+    def purge_vector_store(self):
+        """
+        Purges the current vector store and creates a new one.
+        """
+        self.purge()

crazy_functions/rag_fns/rag_file_support.py

@@ -0,0 +1,45 @@
+import os
+from llama_index.core import SimpleDirectoryReader
+
+supports_format = ['.csv', '.docx','.doc', '.epub', '.ipynb',  '.mbox', '.md', '.pdf',  '.txt', '.ppt',
+                   '.pptm', '.pptx','.py', '.xls', '.xlsx', '.html', '.json', '.xml', '.yaml', '.yml' ,'.m']
+
+def read_docx_doc(file_path):
+    if file_path.split(".")[-1] == "docx":
+        from docx import Document
+        doc = Document(file_path)
+        file_content = "\n".join([para.text for para in doc.paragraphs])
+    else:
+        try:
+            import win32com.client
+            word = win32com.client.Dispatch("Word.Application")
+            word.visible = False
+            # 打开文件
+            doc = word.Documents.Open(os.getcwd() + '/' + file_path)
+            # file_content = doc.Content.Text
+            doc = word.ActiveDocument
+            file_content = doc.Range().Text
+            doc.Close()
+            word.Quit()
+        except:
+            raise RuntimeError('请先将.doc文档转换为.docx文档。')
+    return file_content
+
+# 修改后的 extract_text 函数，结合 SimpleDirectoryReader 和自定义解析逻辑
+import os
+
+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 ['.docx', '.doc']:
+        return read_docx_doc(file_path)
+    try:
+        reader = SimpleDirectoryReader(input_files=[file_path])
+        documents = reader.load_data()
+        if len(documents) > 0:
+            return documents[0].text
+    except Exception as e:
+        pass
+
+    return None