Delete doc_qa_1.py

doc_qa_1.py

@@ -1,62 +0,0 @@
-from langchain.vectorstores import FAISS
-from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain.embeddings import HuggingFaceEmbeddings
-from langchain.text_splitter import CharacterTextSplitter
-from langchain.docstore.document import Document
-from transformers import pipeline
-from langchain.chains.question_answering import load_qa_chain
-import os
-
-# Step 1: Load QA pipeline (don't wrap in HuggingFacePipeline)
-embeddings = HuggingFaceEmbeddings(model_name="intfloat/multilingual-e5-small")
-qa_pipeline = pipeline("question-answering", model="deepset/xlm-roberta-base-squad2")
-multi_directory_path=r'tmp/'
-
-def docs_vector_index():
-    from langchain.document_loaders import DirectoryLoader
-    # Define a directory path
-    directory_path = r"C:\Users\savni\PycharmProjects\DocsSearchEngine\tmp"
-
-    # Create the DirectoryLoader, specifying loaders for each file type
-    loader = DirectoryLoader(
-        directory_path,
-        glob="**/*",  # This pattern loads all files; modify as needed
-
-    )
-    docs = loader.load()
-
-    text_splitter = RecursiveCharacterTextSplitter(
-        chunk_size=1024, chunk_overlap=100, separators=[" ", ",", "\n", "."]
-    )
-    print(docs)
-    docs_chunks = text_splitter.split_documents(docs)
-
-    print(f"docs_chunks length: {len(docs_chunks)}")
-    print('********************docs_chunks',docs_chunks)
-    if len(docs_chunks)>0:
-        db = FAISS.from_documents(docs_chunks, embeddings)
-        return db
-    else:
-        return ''
-
-
-
-def run_custom_qa(question, retrieved_docs):
-    context = " ".join([doc.page_content for doc in retrieved_docs])
-    output = qa_pipeline(question=question, context=context)
-    return output #output["answer"]
-
-# # Step 6: Ask question
-# question = "東京大学はいつ設立されましたか？"
-# relevant_docs = retriever.get_relevant_documents(question)
-# answer = run_custom_qa(question, relevant_docs)
-#
-# print("Answer:", answer)
-
-def doc_qa(query, db):
-    print("*************************custom qa doc_qa",query)
-    retriever = db.as_retriever()
-    relevant_docs = retriever.get_relevant_documents(query)
-    response=run_custom_qa(query, relevant_docs)
-    print('response', response)
-    return response