Duplicate from chomakov/GPT-4_PDF_summary

Co-authored-by: Ivan Chomakov <chomakov@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

Dockerfile

@@ -0,0 +1,14 @@
+FROM python:3.9
+
+COPY ./requirements.txt /requirements.txt
+RUN python3 -m pip install --no-cache-dir --upgrade pip
+RUN python3 -m pip install --no-cache-dir --upgrade -r /requirements.txt
+
+COPY . .
+
+CMD ["panel", "serve", "GPT-4_PDF_summary.py", "--address", "0.0.0.0", "--port", "7860", "--allow-websocket-origin", "chomakov-gpt-4-pdf-summary.hf.space", "--allow-websocket-origin", "0.0.0.0:7860"]
+
+RUN mkdir /.cache
+RUN chmod 777 /.cache
+RUN mkdir .chroma
+RUN chmod 777 .chroma

GPT-4_PDF_summary.py

@@ -0,0 +1,155 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+# !pip install langchain openai chromadb tiktoken pypdf panel
+# In[ ]:
+
+
+import os
+from langchain.chains import RetrievalQA
+from langchain.llms import OpenAI
+from langchain.document_loaders import TextLoader
+from langchain.document_loaders import PyPDFLoader
+from langchain.indexes import VectorstoreIndexCreator
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.embeddings import OpenAIEmbeddings
+from langchain.vectorstores import Chroma
+import panel as pn
+import tempfile
+
+
+# In[ ]:
+
+
+pn.extension('texteditor', template="bootstrap", sizing_mode='stretch_width')
+pn.state.template.param.update(
+    main_max_width="690px",
+    header_background="#F08080",
+)
+
+
+# In[3]:
+
+
+file_input = pn.widgets.FileInput(width=300)
+
+openaikey = pn.widgets.PasswordInput(
+    value="", placeholder="Enter your OpenAI API Key here...", width=300
+)
+prompt = pn.widgets.TextEditor(
+    value="", placeholder="Enter your questions here...", height=160, toolbar=False
+)
+run_button = pn.widgets.Button(name="Run!")
+
+select_k = pn.widgets.IntSlider(
+    name="Number of relevant chunks", start=1, end=5, step=1, value=2
+)
+select_chain_type = pn.widgets.RadioButtonGroup(
+    name='Chain type',
+    options=['stuff', 'map_reduce', "refine", "map_rerank"]
+)
+
+widgets = pn.Row(
+    pn.Column(prompt, run_button, margin=5),
+    pn.Card(
+        "Chain type:",
+        pn.Column(select_chain_type, select_k),
+        title="Advanced settings", margin=10
+    ), width=600
+)
+
+
+# In[4]:
+
+
+def qa(file, query, chain_type, k):
+    # load document
+    loader = PyPDFLoader(file)
+    documents = loader.load()
+    # split the documents into chunks
+    text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
+    texts = text_splitter.split_documents(documents)
+    # select which embeddings we want to use
+    embeddings = OpenAIEmbeddings()
+    # create the vectorestore to use as the index
+    db = Chroma.from_documents(texts, embeddings)
+    # expose this index in a retriever interface
+    retriever = db.as_retriever(
+        search_type="similarity", search_kwargs={"k": k})
+    # create a chain to answer questions
+    qa = RetrievalQA.from_chain_type(
+        llm=OpenAI(), chain_type=chain_type, retriever=retriever, return_source_documents=True)
+    result = qa({"query": query})
+    print(result['result'])
+    return result
+
+
+# In[6]:
+
+
+convos = []  # store all panel objects in a list
+
+
+def qa_result(_):
+    os.environ["OPENAI_API_KEY"] = openaikey.value
+
+    # save pdf file to a temp file
+    if file_input.value is not None:
+        file_input.save("/.cache/temp.pdf")
+
+        prompt_text = prompt.value
+        if prompt_text:
+            result = qa(file="/.cache/temp.pdf", query=prompt_text,
+                        chain_type=select_chain_type.value, k=select_k.value)
+            convos.extend([
+                pn.Row(
+                    pn.panel("\U0001F60A", width=10),
+                    prompt_text,
+                    width=600
+                ),
+                pn.Row(
+                    pn.panel("\U0001F916", width=10),
+                    pn.Column(
+                        result["result"],
+                        "Relevant source text:",
+                        pn.pane.Markdown('\n--------------------------------------------------------------------\n'.join(
+                            doc.page_content for doc in result["source_documents"]))
+                    )
+                )
+            ])
+            # return convos
+    return pn.Column(*convos, margin=15, width=575, min_height=400)
+
+
+# In[7]:
+
+
+qa_interactive = pn.panel(
+    pn.bind(qa_result, run_button),
+    loading_indicator=True,
+)
+
+
+# In[8]:
+
+
+output = pn.WidgetBox('*Output will show up here:*',
+                      qa_interactive, width=630, scroll=True)
+
+
+# In[9]:
+
+
+# layout
+pn.Column(
+    pn.pane.Markdown("""
+    ## \U0001F60A! Question Answering with your PDF file
+    
+    1) Upload a PDF. 2) Enter OpenAI API key. This costs $. Set up billing at [OpenAI](https://platform.openai.com/account). 3) Type a question and click "Run".
+    
+    """),
+    pn.Row(file_input, openaikey),
+    output,
+    widgets
+
+).servable()

README.md

@@ -0,0 +1,12 @@
+---
+title: GPT-4 PDF Summary
+emoji: 💩
+colorFrom: yellow
+colorTo: indigo
+sdk: docker
+pinned: false
+license: creativeml-openrail-m
+duplicated_from: chomakov/GPT-4_PDF_summary
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

requirements.txt

@@ -0,0 +1,7 @@
+langchain
+openai
+chromadb
+pypdf
+tiktoken
+panel
+notebook