Duplicate from ADOPLE/Adopleai-DocumentQA

.gitattributes

@@ -0,0 +1,35 @@
+*.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
+*.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: DocumentQA
+emoji: 🏃
+colorFrom: red
+colorTo: red
+sdk: gradio
+sdk_version: 3.35.2
+app_file: app.py
+pinned: false
+duplicated_from: ADOPLE/Adopleai-DocumentQA
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,112 @@
+from pydantic import NoneStr
+import os
+from langchain.chains.question_answering import load_qa_chain
+from langchain.document_loaders import UnstructuredFileLoader
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.llms import OpenAI
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.vectorstores import FAISS
+from pypdf import PdfReader
+import mimetypes
+import validators
+import requests
+import tempfile
+import gradio as gr
+import openai
+
+def get_empty_state():
+    return {"knowledge_base": None}
+
+
+def create_knowledge_base(docs):
+    # split into chunks
+    text_splitter = CharacterTextSplitter(
+        separator="\n", chunk_size=500, chunk_overlap=0, length_function=len
+    )
+    chunks = text_splitter.split_documents(docs)
+
+    # Create embeddings
+    embeddings = OpenAIEmbeddings()
+    knowledge_base = FAISS.from_documents(chunks, embeddings)
+    return knowledge_base
+
+
+def upload_file(file_obj):
+    try:
+      loader = UnstructuredFileLoader(file_obj.name, strategy="fast")
+      docs = loader.load()
+
+      knowledge_base = create_knowledge_base(docs)
+    except:
+      text="Try Another file"
+      return  file_obj.name, text
+
+    return file_obj.name, {"knowledge_base": knowledge_base}
+
+
+def upload_via_url(url):
+    if validators.url(url):
+        r = requests.get(url)
+
+        if r.status_code != 200:
+            raise ValueError(
+                "Check the url of your file; returned status code %s" % r.status_code
+            )
+
+        content_type = r.headers.get("content-type")
+        file_extension = mimetypes.guess_extension(content_type)
+        temp_file = tempfile.NamedTemporaryFile(suffix=file_extension, delete=False)
+        temp_file.write(r.content)
+        file_path = temp_file.name
+        loader = UnstructuredFileLoader(file_path, strategy="fast")
+        docs = loader.load()
+        with open(file_path, mode="rb") as f:
+            pass
+        knowledge_base = create_knowledge_base(docs)
+        return file_path, {"knowledge_base": knowledge_base}
+    else:
+        raise ValueError("Please enter a valid URL")
+
+
+def answer_question(question, state):
+
+    try:
+        knowledge_base = state["knowledge_base"]
+        docs = knowledge_base.similarity_search(question)
+
+        llm = OpenAI(temperature=0.4)
+        chain = load_qa_chain(llm, chain_type="stuff")
+        response = chain.run(input_documents=docs, question=question)
+        return response
+    except:
+        return "Please upload Proper Document"
+title = """<br><br><br><div style="text-align: center;max-width: 700px;">
+            <h1><a style="display:inline-block; margin-left: 1em; text-decoration:none; font-weight:bold;" href="https://www.adople.com">ADOPLE AI</a> - Document QA</h1>
+            </p>"""
+with gr.Blocks(css="style.css",theme=gr.themes.Soft()) as demo:
+    state = gr.State(get_empty_state())
+    with gr.Column(elem_id="col-container"):
+        gr.HTML(title)
+        gr.Markdown("**Upload your file**")
+        with gr.Row(elem_id="row-flex"):
+            with gr.Column(scale=0.85):
+                file_url = gr.Textbox(
+                      value="",
+                      label="Upload your file",
+                      placeholder="Enter a url",
+                      show_label=False,
+                      visible=True,elem_classes="filenameshow")
+            with gr.Column(scale=0.15, min_width=160):
+                upload_button = gr.UploadButton("Browse File", file_types=[".txt", ".pdf", ".doc", ".docx"],elem_classes="filenameshow")
+        file_output = gr.File(elem_classes="filenameshow")
+        with gr.Row():
+            with gr.Column(scale=1, min_width=0):
+                user_question = gr.Textbox(value="",label='Question Box :',show_label=True, placeholder="Ask a question about your file:",elem_classes="spaceH")
+        with gr.Row():
+            with gr.Column(scale=1, min_width=0):
+                answer = gr.Textbox(value="",label='Answer Box :',show_label=True, placeholder="",lines=5)
+    file_url.submit(upload_via_url, file_url, [file_output, state])
+    upload_button.upload(upload_file, upload_button, [file_output,state])
+    user_question.submit(answer_question, [user_question, state], [answer])
+
+demo.launch()

requirements.txt

@@ -0,0 +1,14 @@
+openai
+tiktoken
+langchain
+gradio
+pypdf
+requests
+unstructured
+validators
+pytesseract
+pdf2image
+tabulate
+nltk
+python-dotenv
+faiss-cpu

style.css

@@ -0,0 +1,28 @@
+#col-container {
+  max-width: 700px;
+  margin-left: auto;
+  margin-right: auto;
+}
+#row-flex {
+  display: flex;
+  align-items: center;
+  justify-content: center;
+}
+.filenameshow{
+  height:85px;
+}
+.spaceH{
+  padding-top:45px;
+}
+.leftimage .rightimage{
+  float:left;
+}
+.leftimage{
+  padding-top:26px;
+  margin-left:340px;
+}
+.rightimage{
+  margin-right:360px;
+  margin-top:15px;
+}
+