Duplicate from fedor-ch/langchain-ynp-test

Co-authored-by: Chemashkinf <fedor-ch@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

README.md

@@ -0,0 +1,13 @@
+---
+title: "Chat with PDF •\_OpenAI"
+emoji: 📄🤖
+colorFrom: purple
+colorTo: pink
+sdk: gradio
+sdk_version: 3.27.0
+python_version: 3.10.9
+app_file: app.py
+pinned: false
+duplicated_from: fedor-ch/langchain-ynp-test
+---
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,287 @@
+import gradio as gr
+import os
+import time
+
+from langchain.document_loaders import OnlinePDFLoader
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.llms import OpenAI
+from langchain.embeddings import OpenAIEmbeddings
+from langchain.vectorstores import Chroma
+from langchain.chains import ConversationalRetrievalChain
+from langchain import PromptTemplate
+from transformers import Pix2StructForConditionalGeneration, Pix2StructProcessor
+import requests
+from PIL import Image
+import torch
+
+
+
+# _template = """Given the following conversation and a follow up question, rephrase the follow up question to be a standalone question.
+# Chat History:
+# {chat_history}
+# Follow Up Input: {question}
+# Standalone question:"""
+
+# CONDENSE_QUESTION_PROMPT = PromptTemplate.from_template(_template)
+
+# template = """
+# You are given the following extracted parts of a long document and a question. Provide a short structured answer.
+# If you don't know the answer, look on the web. Don't try to make up an answer.
+# Question: {question}
+# =========
+# {context}
+# =========
+# Answer in Markdown:"""
+
+torch.hub.download_url_to_file('https://raw.githubusercontent.com/vis-nlp/ChartQA/main/ChartQA%20Dataset/val/png/20294671002019.png', 'chart_example.png')
+torch.hub.download_url_to_file('https://raw.githubusercontent.com/vis-nlp/ChartQA/main/ChartQA%20Dataset/test/png/multi_col_1081.png', 'chart_example_2.png')
+torch.hub.download_url_to_file('https://raw.githubusercontent.com/vis-nlp/ChartQA/main/ChartQA%20Dataset/test/png/18143564004789.png', 'chart_example_3.png')
+torch.hub.download_url_to_file('https://sharkcoder.com/files/article/matplotlib-bar-plot.png', 'chart_example_4.png')
+
+
+model_name = "google/matcha-chartqa"
+model = Pix2StructForConditionalGeneration.from_pretrained(model_name)
+processor = Pix2StructProcessor.from_pretrained(model_name)
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+model.to(device)
+
+def filter_output(output):
+    return output.replace("<0x0A>", "")
+
+def chart_qa(image, question):
+    inputs = processor(images=image, text=question, return_tensors="pt").to(device)
+    predictions = model.generate(**inputs, max_new_tokens=512)
+    return filter_output(processor.decode(predictions[0], skip_special_tokens=True))
+
+def loading_pdf():
+    return "Loading..."
+
+
+def pdf_changes(pdf_doc, open_ai_key):
+    if open_ai_key is not None:
+        os.environ['OPENAI_API_KEY'] = open_ai_key
+        loader = OnlinePDFLoader(pdf_doc.name)
+        documents = loader.load()
+        text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
+        texts = text_splitter.split_documents(documents)
+        embeddings = OpenAIEmbeddings()
+        db = Chroma.from_documents(texts, embeddings)
+        retriever = db.as_retriever()
+        global qa
+        qa = ConversationalRetrievalChain.from_llm(
+            llm=OpenAI(temperature=0.5), 
+            retriever=retriever, 
+            return_source_documents=True)
+        return "Ready"
+    else:
+        return "You forgot OpenAI API key"
+
+def add_text(history, text):
+    history = history + [(text, None)]
+    return history, ""
+
+def bot(history):
+    response = infer(history[-1][0], history)
+    history[-1][1] = ""
+    
+    for character in response:     
+        history[-1][1] += character
+        time.sleep(0.05)
+        yield history
+    
+
+def infer(question, history):  
+    res = []
+    for human, ai in history[:-1]:
+        pair = (human, ai)
+        res.append(pair)
+    
+    chat_history = res
+    #print(chat_history)
+    query = question
+    result = qa({"question": query, "chat_history": chat_history})
+    #print(result)
+    return result["answer"]
+
+css="""
+#col-container {max-width: 700px; margin-left: auto; margin-right: auto;}
+"""
+
+title = """
+<div style="text-align: center;">
+    <h1>YnP LangChain Test </h1>
+    <p style="text-align: center;">Please specify OpenAI Key before use</p>
+</div>
+"""
+
+
+# with gr.Blocks(css=css) as demo:
+#     with gr.Column(elem_id="col-container"):
+#         gr.HTML(title)
+        
+#         with gr.Column():
+#             openai_key = gr.Textbox(label="You OpenAI API key", type="password")
+#             pdf_doc = gr.File(label="Load a pdf", file_types=['.pdf'], type="file")
+#             with gr.Row():
+#                 langchain_status = gr.Textbox(label="Status", placeholder="", interactive=False)
+#                 load_pdf = gr.Button("Load pdf to langchain")
+        
+#         chatbot = gr.Chatbot([], elem_id="chatbot").style(height=350)
+#         question = gr.Textbox(label="Question", placeholder="Type your question and hit Enter ")
+#         submit_btn = gr.Button("Send Message")
+        
+#     load_pdf.click(loading_pdf, None, langchain_status, queue=False)    
+#     load_pdf.click(pdf_changes, inputs=[pdf_doc, openai_key], outputs=[langchain_status], queue=False)
+#     question.submit(add_text, [chatbot, question], [chatbot, question]).then(
+#         bot, chatbot, chatbot
+#     )
+#     submit_btn.click(add_text, [chatbot, question], [chatbot, question]).then(
+#         bot, chatbot, chatbot)
+
+# demo.launch()
+
+
+"""functions"""
+
+def load_file():
+    return "Loading..."
+
+def load_xlsx(name):
+    import pandas as pd
+    
+    xls_file = rf'{name}'
+    data = pd.read_excel(xls_file)  
+    return data
+
+def table_loader(table_file, open_ai_key):
+    import os
+    from langchain.llms import OpenAI
+    from langchain.agents import create_pandas_dataframe_agent    
+    from pandas import read_csv
+    
+    global agent
+    if open_ai_key is not None:
+        os.environ['OPENAI_API_KEY'] = open_ai_key
+    else:
+        return "Enter API"
+    
+    if table_file.name.endswith('.xlsx') or table_file.name.endswith('.xls'):
+        data = load_xlsx(table_file.name)
+        agent = create_pandas_dataframe_agent(OpenAI(temperature=0), data)
+        return "Ready!"
+    elif table_file.name.endswith('.csv'):
+        data = read_csv(table_file.name)
+        agent = create_pandas_dataframe_agent(OpenAI(temperature=0), data)
+        return "Ready!"
+    else:
+        return "Wrong file format! Upload excel file or csv!"
+    
+def run(query):
+    from langchain.callbacks import get_openai_callback
+    
+    with get_openai_callback() as cb:
+        response = (agent.run(query))
+        costs = (f"Total Cost (USD): ${cb.total_cost}")
+        output = f'{response} \n {costs}'
+        return output
+    
+def respond(message, chat_history):
+    import time
+    
+    bot_message = run(message)
+    chat_history.append((message, bot_message))
+    time.sleep(0.5)
+    return "", chat_history
+
+
+with gr.Blocks() as demo:
+    with gr.Column(elem_id="col-container"):
+        gr.HTML(title)
+        key = gr.Textbox(
+                show_label=False,
+                placeholder="Your OpenAI key",
+                type = 'password',
+                ).style(container=False)
+
+    # PDF processing tab
+    with gr.Tab("PDFs"):
+        
+        with gr.Row(): 
+            
+            with gr.Column(scale=0.5):
+                langchain_status = gr.Textbox(label="Status", placeholder="", interactive=False)
+                load_pdf = gr.Button("Load pdf to langchain")
+                
+            with gr.Column(scale=0.5):
+                pdf_doc = gr.File(label="Load a pdf", file_types=['.pdf'], type="file")
+                
+                
+        with gr.Row():
+            
+            with gr.Column(scale=1): 
+                chatbot = gr.Chatbot([], elem_id="chatbot").style(height=350)
+                
+        with gr.Row():
+            
+            with gr.Column(scale=0.85):
+                question = gr.Textbox(
+                show_label=False,
+                placeholder="Enter text and press enter, or upload an image",
+                ).style(container=False)
+                
+            with gr.Column(scale=0.15, min_width=0):
+                clr_btn = gr.Button("Clear!")
+                
+    load_pdf.click(loading_pdf, None, langchain_status, queue=False)    
+    load_pdf.click(pdf_changes, inputs=[pdf_doc, key], outputs=[langchain_status], queue=True)
+    question.submit(add_text, [chatbot, question], [chatbot, question]).then(
+        bot, chatbot, chatbot
+    )
+                
+    # XLSX and CSV processing tab
+    with gr.Tab("Spreadsheets"):
+        with gr.Row(): 
+            
+            with gr.Column(scale=0.5):
+                status_sh = gr.Textbox(label="Status", placeholder="", interactive=False)
+                load_table = gr.Button("Load csv|xlsx to langchain")
+                
+            with gr.Column(scale=0.5):
+                raw_table = gr.File(label="Load a table file (xls or csv)", file_types=['.csv, xlsx, xls'], type="file")
+                
+                
+        with gr.Row():
+            
+            with gr.Column(scale=1): 
+                chatbot_sh = gr.Chatbot([], elem_id="chatbot").style(height=350)
+                
+                
+        with gr.Row():
+            
+            with gr.Column(scale=0.85):
+                question_sh = gr.Textbox(
+                show_label=False,
+                placeholder="Enter text and press enter, or upload an image",
+                ).style(container=False)
+                
+            with gr.Column(scale=0.15, min_width=0):
+                clr_btn = gr.Button("Clear!")
+            
+    load_table.click(load_file, None, status_sh, queue=False)    
+    load_table.click(table_loader, inputs=[raw_table, key], outputs=[status_sh], queue=False)
+   
+    question_sh.submit(respond, [question_sh, chatbot_sh], [question_sh, chatbot_sh])
+    clr_btn.click(lambda: None, None, chatbot_sh, queue=False)
+    
+
+    with gr.Tab("Charts"):
+            image = gr.Image(type="pil", label="Chart")
+            question = gr.Textbox(label="Question")
+            load_chart = gr.Button("Load chart and question!")
+            answer = gr.Textbox(label="Model Output")
+            
+    load_chart.click(chart_qa, [image, question], answer)
+
+        
+demo.queue(concurrency_count=3)
+demo.launch()

requirements.txt

@@ -0,0 +1,8 @@
+openai
+tiktoken
+chromadb
+langchain
+unstructured
+unstructured[local-inference]
+pandas
+tabulate