Upload 4 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+docs_db/index.faiss filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,132 @@
+import os
+import openai
+
+os.environ["TOKENIZERS_PARALLELISM"] = "false"
+os.environ["OPENAI_API_KEY"]
+global agent
+
+
+def create_agent():
+
+    from langchain.chat_models import ChatOpenAI
+    from langchain.chains.conversation.memory import ConversationSummaryBufferMemory
+    from langchain.chains import ConversationChain
+
+    global agent
+
+    llm = ChatOpenAI(model_name="gpt-3.5-turbo-16k")
+    memory = ConversationSummaryBufferMemory(llm=llm, max_token_limit=1000)
+    agent = ConversationChain(llm=llm, memory=memory, verbose=True)
+
+    return "Successful!"
+
+
+def formatted_response(docs, question, response, state):
+
+    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}"
+
+    state.append((question, formatted_output))
+    return state, state
+
+
+def search_docs(prompt, question, state):
+
+    from langchain.embeddings.openai import OpenAIEmbeddings
+    from langchain.vectorstores import FAISS
+    from langchain.callbacks import get_openai_callback
+
+    global agent
+    agent = agent
+
+    state = state or []
+
+    embeddings = OpenAIEmbeddings()
+    docs_db = FAISS.load_local("/home/user/app/docs_db/", embeddings)
+    docs = docs_db.similarity_search(question)
+
+    prompt += "\n\n"
+    prompt += question
+    prompt += "\n\n"
+    prompt += str(docs)
+
+    with get_openai_callback() as cb:
+        response = agent.predict(input=prompt)
+        print(cb)
+
+    return formatted_response(docs, question, response, state)
+
+
+import gradio as gr
+
+css = """
+.col{
+    max-width: 75%;
+    margin: 0 auto;
+    display: flex;
+    flex-direction: column;
+    justify-content: center;
+    align-items: center;
+}
+"""
+
+with gr.Blocks(css=css) as demo:
+    gr.Markdown("## <center>All in One Document Chatting App</center>")
+
+    with gr.Tab("Chat With Your Documents"):
+        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")
+
+                    create_agent_button = gr.Button("Create Agent")
+                    create_agent_output = gr.Textbox(label="Output")
+
+                    # gr.ClearButton([docs_upload_input, docs_upload_output, docs_process_output, create_agent_output])
+                    gr.ClearButton([create_agent_output])
+            with gr.Tab("Query Documents"):
+                with gr.Column():
+
+                    docs_prompt_input = gr.Textbox(label="Custom Prompt")
+
+                    docs_chatbot = gr.Chatbot(label="Chats")
+                    docs_state = gr.State()
+
+                    docs_search_input = gr.Textbox(label="Question")
+                    docs_search_button = gr.Button("Search")
+
+                    gr.ClearButton([docs_prompt_input, docs_search_input])
+
+    #########################################################################################################
+
+    # 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)
+    create_agent_button.click(create_agent, inputs=None, outputs=create_agent_output)
+
+    docs_search_button.click(
+        search_docs,
+        inputs=[docs_prompt_input, docs_search_input, docs_state],
+        outputs=[docs_chatbot, docs_state],
+    )
+
+    #########################################################################################################
+
+demo.queue()
+demo.launch()

docs_db/index.faiss

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8374c50d4d054a4d3fa22723361beb6d664979685497b9235ec4db5731d7fdc1
+size 57489453

docs_db/index.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bc707921fd0cfceb0de06b536e584cd7b3c2746a521b915cf3a49a980b4d6f7
+size 9341865

requirements.txt

@@ -0,0 +1,10 @@
+langchain
+PyPDF2
+pypdf
+docx2txt
+unstructured
+gradio
+faiss-cpu
+openai
+tiktoken
+