File size: 2,232 Bytes
07037b8
51782e8
086f34e
07037b8
 
 
4d09653
 
 
 
 
 
 
 
07037b8
 
4d09653
 
 
619c894
4d09653
 
 
07037b8
4d09653
07037b8
 
 
 
 
 
 
 
 
5be2eda
07037b8
 
 
 
 
 
 
 
 
 
 
5be2eda
07037b8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
015e894
07037b8
 
 
 
 
 
 
5be2eda
4d09653
 
 
07037b8
5be2eda
07037b8
 
 
 
 
4d09653
07037b8
 
 
015e894
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
# Read the data
import pandas as pd
df = pd.read_csv('./Automobile_data.csv')
df = df.drop(columns = ['normalized-losses','symboling'], axis = 1)

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)


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="car_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 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()
)

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 need a car', 'what is the make and fuel type of a car?']




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",
    examples=examples,
    allow_flagging="never",
)


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