Upload 2 files

app.py

@@ -0,0 +1,165 @@
+
+
+import os
+import openai
+
+os.environ["TOKENIZERS_PARALLELISM"] = "false"
+os.environ["OPENAI_API_KEY"]
+def save_docs(docs):
+
+    import shutil
+    import os
+
+    destination_dir = "/kaggle/working/docs/"
+    os.makedirs(destination_dir, exist_ok=True)
+
+    output_dir="/kaggle/working/docs/"
+
+    for doc in docs:
+      shutil.copy(doc.name, output_dir)
+
+    return "File(s) saved successfully!"
+
+def process_docs():
+
+    from langchain.document_loaders import PyPDFLoader
+    from langchain.document_loaders import DirectoryLoader
+    from langchain.document_loaders import TextLoader
+    from langchain.document_loaders import Docx2txtLoader
+    from langchain.vectorstores import FAISS
+    from langchain.embeddings.openai import OpenAIEmbeddings
+    from langchain.text_splitter import RecursiveCharacterTextSplitter
+
+    loader1 = DirectoryLoader('/kaggle/working/docs/', glob="./*.pdf", loader_cls=PyPDFLoader)
+    document1 = loader1.load()
+
+    loader2 = DirectoryLoader('/kaggle/working/docs/', glob="./*.txt", loader_cls=TextLoader)
+    document2 = loader2.load()
+
+    loader3 = DirectoryLoader('/kaggle/working/docs/', glob="./*.docx", loader_cls=Docx2txtLoader)
+    document3 = loader3.load()
+
+    document1.extend(document2)
+    document1.extend(document3)
+
+    text_splitter = RecursiveCharacterTextSplitter(
+        chunk_size=1000,
+        chunk_overlap=200,
+        length_function=len
+    )
+
+    docs = text_splitter.split_documents(document1)
+    embeddings = OpenAIEmbeddings()
+
+    docs_db = FAISS.from_documents(docs, embeddings)
+    docs_db.save_local("/kaggle/working/docs_db/")
+
+    return "File(s) processed successfully!"
+
+def formatted_response(docs, response):
+
+    formatted_output = response + "\n\nSources"
+
+    for i, doc in enumerate(docs):
+        source_info = doc.metadata.get('source', 'Unknown source')
+        page_info = doc.metadata.get('page', None)
+
+        doc_name = source_info.split('/')[-1].strip()
+
+        if page_info is not None:
+            formatted_output += f"\n{doc_name}\tpage no {page_info}"
+        else:
+            formatted_output += f"\n{doc_name}"
+
+    return formatted_output
+
+def search_docs(question):
+
+    from langchain.embeddings.openai import OpenAIEmbeddings
+    from langchain.vectorstores import FAISS
+    from langchain.chains.question_answering import load_qa_chain
+    from langchain.callbacks import get_openai_callback
+    from langchain.chat_models import ChatOpenAI
+
+    embeddings = OpenAIEmbeddings()
+    docs_db = FAISS.load_local("/kaggle/working/docs_db/", embeddings)
+    docs = docs_db.similarity_search(question)
+
+    llm = ChatOpenAI(model_name='gpt-3.5-turbo')
+    chain = load_qa_chain(llm, chain_type="stuff")
+
+    with get_openai_callback() as cb:
+        response = chain.run(input_documents=docs, question=question)
+        print(cb)
+
+    return formatted_response(docs, response)
+
+def delete_docs():
+
+    import shutil
+
+    path1 = "/kaggle/working/docs/"
+    path2 = "/kaggle/working/docs_db/"
+
+    try:
+        shutil.rmtree(path1)
+        shutil.rmtree(path2)
+        return "Deleted Successfully"
+
+    except:
+        return "Already Deleted"
+
+import gradio as gr
+
+css = """
+.col{
+    max-width: 50%;
+    margin: 0 auto;
+    display: flex;
+    flex-direction: column;
+    justify-content: center;
+    align-items: center;
+}
+"""
+
+with gr.Blocks(css=css) as demo:
+    gr.Markdown("## <center>Lawyer GPT</center>")
+
+    with gr.Tab("Your AI Legal Assistant"):
+      with gr.Column(elem_classes="col"):
+
+        with gr.Tab("Upload and Process Documents"):
+          with gr.Column():
+
+            docs_upload_input = gr.Files(label="Upload File(s)")
+            docs_upload_button = gr.Button("Upload")
+            docs_upload_output = gr.Textbox(label="Output")
+
+            docs_process_button = gr.Button("Process")
+            docs_process_output = gr.Textbox(label="Output")
+
+            gr.ClearButton([docs_upload_input, docs_upload_output, docs_process_output])
+
+        with gr.Tab("Query Documents"):
+          with gr.Column():
+
+            docs_search_input = gr.Textbox(label="Enter Question")
+            docs_search_button = gr.Button("Search")
+            docs_search_output = gr.Textbox(label="Output")
+
+            docs_delete_button = gr.Button("Delete")
+            docs_delete_output = gr.Textbox(label="Output")
+
+            gr.ClearButton([docs_search_input, docs_search_output, docs_delete_output])
+
+    #########################################################################################################
+    docs_upload_button.click(save_docs, inputs=docs_upload_input, outputs=docs_upload_output)
+    docs_process_button.click(process_docs, inputs=None, outputs=docs_process_output)
+
+    docs_search_button.click(search_docs, inputs=docs_search_input, outputs=docs_search_output)
+
+    docs_delete_button.click(delete_docs, inputs=None, outputs=docs_delete_output)
+    #########################################################################################################
+
+demo.queue()
+demo.launch(debug=True, share=True)