Upload 3 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
+electricity_corpus.json filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,79 @@
+{\rtf1\ansi\ansicpg1252\cocoartf2822
+\cocoatextscaling0\cocoaplatform0{\fonttbl\f0\fmodern\fcharset0 Courier;}
+{\colortbl;\red255\green255\blue255;\red131\green0\blue165;\red245\green245\blue245;\red0\green0\blue0;
+\red15\green112\blue1;\red86\green65\blue25;\red144\green1\blue18;\red0\green0\blue255;\red0\green0\blue109;
+\red19\green85\blue52;}
+{\*\expandedcolortbl;;\cssrgb\c59216\c13725\c70588;\cssrgb\c96863\c96863\c96863;\cssrgb\c0\c0\c0;
+\cssrgb\c0\c50196\c0;\cssrgb\c41569\c32157\c12941;\cssrgb\c63922\c8235\c8235;\cssrgb\c0\c0\c100000;\cssrgb\c0\c6275\c50196;
+\cssrgb\c6667\c40000\c26667;}
+\margl1440\margr1440\vieww11520\viewh8400\viewkind0
+\deftab720
+\pard\pardeftab720\partightenfactor0
+
+\f0\fs28 \cf2 \cb3 \expnd0\expndtw0\kerning0
+\outl0\strokewidth0 \strokec2 import\cf0 \strokec4  json\cb1 \
+\cf2 \cb3 \strokec2 from\cf0 \strokec4  sklearn.feature_extraction.text \cf2 \strokec2 import\cf0 \strokec4  TfidfVectorizer\cb1 \
+\cf2 \cb3 \strokec2 from\cf0 \strokec4  sklearn.metrics.pairwise \cf2 \strokec2 import\cf0 \strokec4  cosine_similarity\cb1 \
+\cf2 \cb3 \strokec2 from\cf0 \strokec4  transformers \cf2 \strokec2 import\cf0 \strokec4  pipeline\cb1 \
+\cf2 \cb3 \strokec2 import\cf0 \strokec4  gradio \cf2 \strokec2 as\cf0 \strokec4  gr\cb1 \
+\
+\pard\pardeftab720\partightenfactor0
+\cf5 \cb3 \strokec5 # Load your natural-language corpus\cf0 \cb1 \strokec4 \
+\pard\pardeftab720\partightenfactor0
+\cf2 \cb3 \strokec2 with\cf0 \strokec4  \cf6 \strokec6 open\cf0 \strokec4 (\cf7 \strokec7 "electricity_corpus.json"\cf0 \strokec4 , \cf7 \strokec7 "r"\cf0 \strokec4 ) \cf2 \strokec2 as\cf0 \strokec4  f:\cb1 \
+\pard\pardeftab720\partightenfactor0
+\cf0 \cb3     corpus = json.load(f)\cb1 \
+\
+\pard\pardeftab720\partightenfactor0
+\cf5 \cb3 \strokec5 # Build TF-IDF index\cf0 \cb1 \strokec4 \
+\pard\pardeftab720\partightenfactor0
+\cf0 \cb3 vectorizer = TfidfVectorizer()\cb1 \
+\cb3 tfidf_matrix = vectorizer.fit_transform(corpus)\cb1 \
+\
+\pard\pardeftab720\partightenfactor0
+\cf5 \cb3 \strokec5 # Load the QA model\cf0 \cb1 \strokec4 \
+\pard\pardeftab720\partightenfactor0
+\cf0 \cb3 qa_pipeline = pipeline(\cf7 \strokec7 "question-answering"\cf0 \strokec4 , model=\cf7 \strokec7 "distilbert-base-cased-distilled-squad"\cf0 \strokec4 )\cb1 \
+\
+\pard\pardeftab720\partightenfactor0
+\cf5 \cb3 \strokec5 # Function to retrieve top matching rows\cf0 \cb1 \strokec4 \
+\pard\pardeftab720\partightenfactor0
+\cf8 \cb3 \strokec8 def\cf0 \strokec4  \cf6 \strokec6 get_top_contexts\cf0 \strokec4 (\cf9 \strokec9 question\cf0 \strokec4 , \cf9 \strokec9 top_k\cf0 \strokec4 =\cf10 \strokec10 3\cf0 \strokec4 ):\cb1 \
+\pard\pardeftab720\partightenfactor0
+\cf0 \cb3     question_vec = vectorizer.transform([question])\cb1 \
+\cb3     similarities = cosine_similarity(question_vec, tfidf_matrix).flatten()\cb1 \
+\cb3     top_indices = similarities.argsort()[-top_k:][::\cf10 \strokec10 -1\cf0 \strokec4 ]\cb1 \
+\cb3     \cf2 \strokec2 return\cf0 \strokec4  [corpus[i] \cf2 \strokec2 for\cf0 \strokec4  i \cf8 \strokec8 in\cf0 \strokec4  top_indices]\cb1 \
+\
+\pard\pardeftab720\partightenfactor0
+\cf5 \cb3 \strokec5 # Main logic to get answer\cf0 \cb1 \strokec4 \
+\pard\pardeftab720\partightenfactor0
+\cf8 \cb3 \strokec8 def\cf0 \strokec4  \cf6 \strokec6 answer_question\cf0 \strokec4 (\cf9 \strokec9 question\cf0 \strokec4 , \cf9 \strokec9 top_k\cf0 \strokec4 =\cf10 \strokec10 3\cf0 \strokec4 ):\cb1 \
+\pard\pardeftab720\partightenfactor0
+\cf0 \cb3     \cf2 \strokec2 if\cf0 \strokec4  \cf8 \strokec8 not\cf0 \strokec4  question.strip():\cb1 \
+\cb3         \cf2 \strokec2 return\cf0 \strokec4  \cf7 \strokec7 "Please enter a valid question."\cf0 \cb1 \strokec4 \
+\
+\cb3     contexts = get_top_contexts(question, top_k)\cb1 \
+\cb3     combined_context = \cf7 \strokec7 " "\cf0 \strokec4 .join(contexts)[:\cf10 \strokec10 4096\cf0 \strokec4 ]  \cf5 \strokec5 # truncate to model max input\cf0 \cb1 \strokec4 \
+\cb3     result = qa_pipeline(question=question, context=combined_context)\cb1 \
+\cb3     \cf2 \strokec2 return\cf0 \strokec4  result[\cf7 \strokec7 "answer"\cf0 \strokec4 ]\cb1 \
+\
+\pard\pardeftab720\partightenfactor0
+\cf5 \cb3 \strokec5 # Gradio interface\cf0 \cb1 \strokec4 \
+\pard\pardeftab720\partightenfactor0
+\cf0 \cb3 iface = gr.Interface(\cb1 \
+\cb3     fn=answer_question,\cb1 \
+\cb3     inputs=gr.Textbox(label=\cf7 \strokec7 "Ask your question about electricity usage..."\cf0 \strokec4 ),\cb1 \
+\cb3     outputs=gr.Textbox(label=\cf7 \strokec7 "Answer"\cf0 \strokec4 ),\cb1 \
+\cb3     title=\cf7 \strokec7 "\uc0\u55357 \u56588  Electricity Data Q&A"\cf0 \strokec4 ,\cb1 \
+\cb3     description=\cf7 \strokec7 "Ask questions like 'What was the price for residential in Texas in Jan 2001?' or 'Which state had highest revenue in Jan 2001?'"\cf0 \strokec4 ,\cb1 \
+\cb3 )\cb1 \
+\
+\pard\pardeftab720\partightenfactor0
+\cf5 \cb3 \strokec5 # Run the app\cf0 \cb1 \strokec4 \
+\pard\pardeftab720\partightenfactor0
+\cf2 \cb3 \strokec2 if\cf0 \strokec4  \cf9 \strokec9 __name__\cf0 \strokec4  == \cf7 \strokec7 "__main__"\cf0 \strokec4 :\cb1 \
+\pard\pardeftab720\partightenfactor0
+\cf0 \cb3     iface.launch()\cb1 \
+\
+}

electricity_corpus.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b38b73e99e20d7cbdaf2e0807a4f7784d7ebd549803bbece88d624bbb07d21b0
+size 13422039

requirements.txt

@@ -0,0 +1,11 @@
+{\rtf1\ansi\ansicpg1252\cocoartf2822
+\cocoatextscaling0\cocoaplatform0{\fonttbl\f0\fswiss\fcharset0 Helvetica;}
+{\colortbl;\red255\green255\blue255;}
+{\*\expandedcolortbl;;}
+\margl1440\margr1440\vieww11520\viewh8400\viewkind0
+\pard\tx720\tx1440\tx2160\tx2880\tx3600\tx4320\tx5040\tx5760\tx6480\tx7200\tx7920\tx8640\pardirnatural\partightenfactor0
+
+\f0\fs24 \cf0 transformers\
+scikit-learn\
+gradio\
+}