Update app.py

app.py

@@ -1,25 +1,102 @@
+# Read the data
+df = pd.read_csv("Automobile_data.csv")
+df = df.drop(columns = ['normalized-losses','symboling'], axis = 1)
+
+context_data = []
+for i in range(len(df)):  # Loop over rows
+    context = ""
+    for j in range(10):  # Loop over the first 8 columns
+        context += df.columns[j]  # Add column name
+        context += ": "
+        context += str(df.iloc[i][j])  # Convert value to string
+        context += " "
+    context_data.append(context)
+
+from langchain_groq import ChatGroq
+llm = ChatGroq(model ="llama-3.1-70b-versatile",api_key = "beza")
+
+qa_pair = []
+for i in range(len(df)):
+  Question = "Given the type of  "+df['make'][i]+ " "+ df['body-style'][i][:-1]+", "" what is the price?"
+  Answer   = df['price'][i]
+  input = f"Instruction:\n{Question}\n\nResponse:\n{Answer}"
+  qa_pair.append(input)
+
+# from langchain_groq import ChatGroq
+
+# llm = ChatGroq(model="llama-3.1-70b-versatile",api_key= "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")
+## 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="car_dataset_store",
+    embedding_function=embed_model,
+    persist_directory="./",
+)
+
+vectorstore.get().keys()
+# add data to vector nstore
+vectorstore.add_texts(context_data)
+
+query = "What is make, number of doors and fuel type?"
+docs = vectorstore.similarity_search(query)
+print(docs[0].page_content)
+
+retriever = vectorstore.as_retriever()
+
+from langchain_core.prompts import PromptTemplate
+
+template = ("""You are a car 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 is Capital of Rwanda?")
+Markdown(response)
+
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-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")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "conten
+
+def rag_memory_stream(text):
+    partial_text = ""
+    for new_text in rag_chain.stream(text):
+        partial_text += new_text
+        yield partial_text
+
+
+title = "Real-time AI App with Groq API and LangChain to Answer car questions"
+demo = gr.Interface(
+    title=title,
+    fn=rag_memory_stream,
+    inputs="text",
+    outputs="text",
+    allow_flagging="never",
+)
+
+demo.launch(share=True)
 
 if __name__ == "__main__":
     demo.launch()