Create app.py

app.py

@@ -0,0 +1,90 @@
+from transformers import AutoModel
+import torch
+import transformers
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from sklearn.metrics.pairwise import cosine_similarity
+from sentence_transformers import SentenceTransformer
+
+import gdown
+import json
+import textwrap
+import warnings
+import openai
+import pandas
+import gradio as gr
+
+warnings.filterwarnings("ignore")
+
+openai.api_key = "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"
+
+
+def generate_prompt(question):
+  prompt = f"""
+### <instruction>: Given an suitable answer for the question asked.
+### <human>: {question}
+### <assistant>:
+  """.strip()
+  return prompt
+
+file_id = '1CjJ-CQhZyr8QowwSksw5uo7O9OYgbq96'
+
+url = f'https://drive.google.com/uc?id={file_id}'
+
+output_file = 'data.xlsx'
+
+gdown.download(url, output_file, quiet=False)
+
+df = pd.read_csv(output_file, encoding='latin-1')
+
+df.head()
+
+sentences = []
+for row in df['QUESTION']:
+    sentences.append(row)
+
+
+model_encode = SentenceTransformer('sentence-transformers/all-mpnet-base-v2')
+embeddings = model_encode.encode(sentences)
+
+answer = []
+for index, val in enumerate(df['ORIGINAL/SYNONYM']):
+    if str(val) == "Original":
+        answer.append(index)
+
+def answer_prompt(text):
+
+  ind, sim = 0, 0
+  bot_response = ''
+  text_embedding = model_encode.encode(text)
+  for index, val in enumerate(embeddings):
+    res = cosine_similarity(text_embedding.reshape(1,-1),embeddings[index].reshape(1,-1))
+    if res[0][0] > sim:
+      sim = res[0][0]
+      ind = index
+
+  for i in range(len(answer)):
+    if answer[i] > ind:
+      bot_response =  bot_response =  f'Similarity Score is {round(sim * 100)} %' + '\n\n' + f'The issue is raised for {df["TECHNOLOGY"][answer[i - 1]]}' + '\n\n' + df['SOLUTION'][answer[i - 1]]
+      break
+
+  if sim > 0.5:
+    return bot_response
+
+  else:
+
+    prompt = generate_prompt(text)
+    response = openai.Completion.create(
+                     engine="gpt-3.5-turbo-instruct",
+                     prompt = prompt,
+                     max_tokens = 1024,
+                     top_p = 0.7,
+                     temperature = 0.3,
+                     presence_penalty = 0.7,
+                  )
+
+    return 'This response is generated by our LLM' + '\n' + response['choices'][0]['text']
+
+iface = gr.Interface(fn=answer_prompt, inputs="text",
+                                       outputs="text")
+
+iface.launch(inline=False)