Update app.py

app.py

@@ -1,64 +1,138 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
+import pandas as pd
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+df = pd.read_csv("./drugs_side_effects_drugs_com.csv")
+df.info()
 
+df = df[['drug_name', 'medical_condition', 'side_effects']]
+df.dropna(inplace=True)
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+df.info()
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+context_data = pd.read_csv("drugs_side_effects_drugs_com.csv")
 
-    messages.append({"role": "user", "content": message})
+import os
+from google.colab import userdata
+groq_api_key = userdata.get('Groq_API_key')
 
-    response = ""
+from langchain_groq import ChatGroq
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+llm = ChatGroq(model="llama-3.1-70b-versatile",api_key=groq_api_key)
 
-        response += token
-        yield response
+## Embedding model!
+from langchain_huggingface import HuggingFaceEmbeddings
+embed_model = HuggingFaceEmbeddings(model_name="mixedbread-ai/mxbai-embed-large-v1")
 
+# create vector store!
+from langchain_chroma import Chroma
+
+vectorstore = Chroma(
+    collection_name="medical_dataset_store",
+    embedding_function=embed_model,
+    persist_directory="./",
+)
+
+vectorstore.get().keys()
+
+# add data to vector nstore
+vectorstore.add_texts(context_data)
+
+query = "What drug that causes these side effects hives ; difficulty breathing; swelling of your face, lips, tongue, or throat."
+docs = vectorstore.similarity_search(query)
+print(docs[0].page_content)
+
+retriever = vectorstore.as_retriever()
+
+from langchain_core.prompts import PromptTemplate
+
+template = ("""You are a medical expert.
+    Use the provided context to answer the question.
+    If you don't know the answer, say so. Explain your answer in detail.
+    Do not discuss the context in your response; just provide the answer directly.
+
+    Context: {context}
+
+    Question: {question}
+
+    Answer:""")
+
+rag_prompt = PromptTemplate.from_template(template)
+
+from langchain_core.output_parsers import StrOutputParser
+from langchain_core.runnables import RunnablePassthrough
+
+rag_chain = (
+    {"context": retriever, "question": RunnablePassthrough()}
+    | rag_prompt
+    | llm
+    | StrOutputParser()
+)
+
+from IPython.display import display, Markdown
+
+response = rag_chain.invoke("What drug that causes these side effects hives ; difficulty breathing; swelling of your face, lips, tongue, or throat")
+Markdown(response)
+
+from IPython.display import display, Markdown
+
+response = rag_chain.invoke("What is Capital of Greece?")
+Markdown(response)
+
+"""# Deployment
 
 """
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
+
+import gradio as gr
+
+def rag_memory_stream(text):
+    partial_text = ""
+    for new_text in rag_chain.stream(text):
+        partial_text += new_text
+        yield partial_text
+
+
+title = "MediGuide ChatBot"
+demo = gr.Interface(
+    title=title,
+    fn=rag_memory_stream,
+    inputs="text",
+    outputs="text",
+    allow_flagging="never",
 )
 
 
 if __name__ == "__main__":
     demo.launch()
+
+"""# Evaluating Using Blue Score and Rouge Score"""
+
+# qa_pair = []
+# for i in range(len(context_data)):
+#   drug_name = str(context_data['drug_name'][i])
+#   medical_condition = str(context_data['medical_condition'][i])
+#   side_effects = str(context_data['side_effects'][i])
+
+#   Question = f"What are the side effect of {drug_name} ?"
+#   Answer = f"Side Effects: {side_effects}"
+
+#   qa_pair.append([Question,Answer])
+
+# df = pd.DataFrame(qa_pair, columns=['Questions', 'Answers'])
+
+# question = [df['Questions'][0]]
+
+# import sacrebleu
+# from rouge_score import rouge_scorer
+
+# predicted_answer = rag_chain.invoke("What are the side effects of doxycycline?")
+# predicted_answer
+
+# reference_answer =df['Answers'][0]
+# reference_answer
+
+# blue_score = sacrebleu.corpus_bleu([predicted_answer], reference_answer).score
+# blue_score
+
+# scorer = rouge_scorer.RougeScorer(['rougeL'], use_stemmer=True)
+# rouge_score = scorer.score(reference_answer, predicted_answer)
+# rouge_score
+