Uptading

.idea/.gitignore

@@ -0,0 +1,3 @@
+# Default ignored files
+/shelf/
+/workspace.xml

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/question-answer.iml" filepath="$PROJECT_DIR$/.idea/question-answer.iml" />
+    </modules>
+  </component>
+</project>

.idea/question-answer.iml

@@ -0,0 +1,10 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$">
+      <excludeFolder url="file://$MODULE_DIR$/.venv" />
+    </content>
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="" vcs="Git" />
+  </component>
+</project>

app.py

@@ -1,28 +1,20 @@
 import gradio as gr
-import tensorflow as tf
-import gradio as gr
-from transformers import pipeline, AutoTokenizer, TFAutoModelForQuestionAnswering
-
-#Option 1: Load the tokenizer and model separately
-#tokenizer = AutoTokenizer.from_pretrained("bert-large-uncased-whole-word-masking-finetuned-squad")
-#model = TFAutoModelForQuestionAnswering.from_pretrained("bert-large-uncased-whole-word-masking-finetuned-squad", return_dict=False)
-
-#Option 2: Use the HuggingFace pipeline function
-nlp = pipeline("question-answering", model=model, tokenizer=tokenizer)
 
-def func(context, question):
-    result = nlp(question=question, context=context)
-    return result['answer']
+def answer_doc_question(pdf_file, question):
+    pdf_text = get_text_from_pdf(pdf_file)
+    answer = question_answerer(question, pdf_text)
+    return answer["answer"]
 
-app = gr.Interface(fn=func,
-                   inputs = ['textbox', 'text'],
-                   outputs = gr.Textbox(lines=10),
-                   title = 'Question Answering Bot',
-                   description = 'Input context and question, then get answers!',
-                   examples = [[example_1, qst_1],
-                               [example_2, qst_2]],
-                   theme = "darkhuggingface",
-                   timeout = 120,
-                   allow_flagging="manual",
-                   flagging_options=["incorrect", "ambiguous", "offensive", "other"],
-                   ).queue()
+# Add default a file and question, so it's easy to try out the app.
+pdf_input = gr.File(
+    value="https://comptroller.defense.gov/Portals/45/Documents/defbudget/FY2025/FY2025_Budget_Request.pdf"
+    file_types=[".pdf"],
+    label="Upload a PDF document and ask a question about it.",
+)
+question = gr.Textbox(
+    value="What is the grand total (AC + RC) amount for FY 2025 Request?",
+    label="Type a question regarding the uploaded document here.",
+)
+gr.Interface(
+    fn=answer_doc_question, inputs=[pdf_input, question], outputs="text"
+).launch()