app.py

import pandas as pd


df = pd.read_csv('./medical_data.csv')
df11=pd.read_csv('./drugs_side_effects_drugs_com.csv')
df1=pd.read_csv('./DrugData.csv')

context_data = []
for i in range(len(df)):
  context = ""
  for j in range(3):
    context += df.columns[j]
    context += ": "
    context += df.iloc[i][j]
    context += " "
  context_data.append(context)

context_data # Initialize the list to store context data

for i in range(len(df1)):  # Iterate through the rows of df1
    context = ""
    for j in range(19):  # Iterate through the first 19 columns
        context += df1.columns[j]  # Add the column name
        context += ": "
        context += str(df1.iloc[i][j])  # Convert the value to a string
        context += " "  # Add a space between entries
    context_data.append(context)  # Append the generated context to the list


# context_data # Initialize the list to store context data

# for i in range(len(df11)):  # Iterate through the rows of df1
#     context = ""
#     for j in range(17):  # Iterate through the first 19 columns
#         context += df11.columns[j]  # Add the column name
#         context += ": "
#         context += str(df11.iloc[i][j])  # Convert the value to a string
#         context += " "  # Add a space between entries
#     context_data.append(context)  # Append the generated context to the list



import os

# Get the secret key from the environment
groq_key = os.environ.get('groq_api_keys')

## LLM used for RAG
from langchain_groq import ChatGroq

llm = ChatGroq(model="llama-3.1-70b-versatile",api_key=groq_key)

## 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="./",
)

# add data to vector nstore
vectorstore.add_texts(context_data)

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()
)

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

examples = ['I feel dizzy', 'what is the possible sickness for fatigue']




title = "CARE360BOT"
demo = gr.Interface(
    title=title,
    fn=rag_memory_stream,
    inputs="text",
    outputs="text",
    examples=examples,
    allow_flagging="never",
)


if __name__ == "__main__":
    demo.launch()