Build a Local AI Agent with Python, Ollama, LangChain and SingleStore

1
ollama serve
2
ollama pull llama3
3
ollama pull mxbai-embed-large

1
pip install poetry

1
poetry new ai_tutorial
2
cd ai_tutorial
3
poetry add langchain langchain-ollama langchain-singlestore docker pandas

1
Best Pizza in Town!,2025-01-06,1,The crust was perfectly crispy and the 
2
toppings were fresh. Will definitely return!
3
Delicious and Affordable,2024-08-12,1,"A bit overpriced for what you get, but 
4
overall a decent meal."
5
Mediocre Experience,2025-01-05,1,Incredible flavors! The margherita pizza 
6
reminded me of Italy.
7
Absolutely Loved It!,2024-06-14,5,"Service was slow and the place was crowded, 
8
but the pizza made up for it."
9
Won't Be Coming Back,2025-03-15,2,Disappointed by the soggy crust and bland 
10
sauce. Expected better.
11
A Slice of Heaven,2024-10-16,2,Amazing pizza with a great balance of cheese and
12
sauce.
13
Perfect for a Quick Bite,2024-08-21,2,"Nothing special, just an average pizza
14
place."
15
Not Worth the Hype,2024-10-21,4,Great for families. My kids loved the pepperoni
16
pizza!
17
Family Favorite,2024-11-15,4,The truffle mushroom pizza is a must-try!

1
import pandas as pd
2
from singlestoredb.server import docker
3
from langchain_ollama import OllamaLLM, OllamaEmbeddings
4
from langchain_singlestore import SingleStoreVectorStore
5
from langchain_core.prompts import ChatPromptTemplate
6
from langchain_core.documents import Document
7

8

9
def setup_database(s2db):
10
    """Initialize the SingleStore database."""
11
    with s2db.connect() as conn:
12
        with conn.cursor() as cursor:
13
            cursor.execute("CREATE DATABASE IF NOT EXISTS testdb")
14

15

16
def load_documents():
17
    """Load pizza reviews from CSV and convert to Document objects."""
18
    df = pd.read_csv("pizza_reviews.csv")
19
    documents = []
20
    for i, row in df.iterrows():
21
        content = f"{row['Title']} {row['Review']}"
22
        documents.append(
23
            Document(
24
                page_content=content,
25
                metadata={"rating": row["Rating"], "date": row["Date"]},
26
                id=str(i)
27
            )
28
        )
29
    return documents
30

31

32
def main():
33
    """
34
    Run a pizza review Q&A application using SingleStoreDB vector store and 
35
LLaMA.
36

37
    This example demonstrates:
38
    1. Setting up a vector database with SingleStoreDB
39
    2. Embedding pizza reviews with Ollama
40
    3. Creating a retrieval-based QA system that answers questions about pizza
41
reviews
42
    """
43
    print("Starting SingleStoreDB server for vector storage...")
44
    with docker.start(license="") as s2db:
45
        setup_database(s2db)
46

47
        print("Loading and embedding pizza reviews...")
48
        documents = load_documents()
49
        embedding = OllamaEmbeddings(model="mxbai-embed-large")
50

51
        # Set up vector store with the embedded documents
52
        vector_store = SingleStoreVectorStore(
53
            embedding=embedding,
54
            host=s2db.connection_url,
55
            database="testdb",
56
            table_name="pizza_reviews",
57
        )
58
        vector_store.add_documents(documents)
59

60
        # Create retriever that fetches the 2 most relevant reviews for each
61
query
62
        retriever = vector_store.as_retriever(search_kwargs={"k": 2})
63

64
        print("Initializing LLaMA 3.2 model...")
65
        model = OllamaLLM(model="llama3.2")
66

67
        # Define prompt template with clean formatting
68
        template = """
69
You are an expert in answering questions about a pizza restaurant.
70

71
Here are some relevant reviews: {reviews}
72

73
Here is the question: {question}
74
"""
75
        prompt = ChatPromptTemplate.from_template(template)
76
        chain = prompt | model
77

78
        print("\n------------------------------------------")
79
        print("Pizza Review Question & Answer System")
80
        print("Ask questions about pizza reviews, and the system will find 
81
relevant reviews")
82
        print("and generate an answer based on those reviews.")
83
        print("------------------------------------------\n")
84

85
        while True:
86
            user_input = input("\nEnter your question about pizza (or 'exit' to 
87
quit): ")
88
            if user_input.lower() == "exit":
89
                break
90
            print("\nFinding relevant reviews and generating answer...")
91
            reviews = retriever.invoke(user_input)
92
            result = chain.invoke({"reviews": reviews, "question": user_input})
93

94
            print("\n--- Answer ---")
95
            print(result)
96

97

98
if __name__ == "__main__":
99
    main()

1
poetry run python ai_tutorial/main.py

1
Starting SingleStoreDB server for vector storage...
2
Loading and embedding pizza reviews...
3
Initializing LLaMA 3.2 model...
4

5
------------------------------------------
6
Pizza Review Question & Answer System
7
Ask questions about pizza reviews, and the system will find relevant reviews
8
and generate an answer based on those reviews.
9
------------------------------------------
10

11

12
Enter your question about pizza (or 'exit' to quit): What do people think about 
13
the crust?
14

15
Finding relevant reviews and generating answer...
16
--- Answer ---
17
Based on the reviews provided, it seems that opinions about the crust are 
18
mixed. 
19

20
One reviewer mentioned that their base (likely referring to the crust) was 
21
soggy, which may indicate issues with the cooking or handling of the crust. On 
22
the other hand, another reviewer stated that they found the crust too salty and 
23
also mentioned that it was burnt, suggesting a problem with the quality control 
24
or preparation of the crust.
25

26
Overall, while not all reviews were negative, these two opinions suggest that 
27
some customers have had issues with the crust in terms of texture (soggy) and 
28
flavor (burnt).
29

30
Enter your question about pizza (or 'exit' to quit): Are there vegetarian 
31
options?
32

33
Finding relevant reviews and generating answer...
34

35
--- Answer ---
36
Unfortunately, based on the reviews provided, it seems that this pizza 
37
restaurant may not have many vegetarian options. The first review from 
38
2024-06-22 mentions "Needs Improvement" and specifically says "Wish there were
39
more vegetarian options." While the second review is positive, it doesn't 
40
mention anything about vegetarian options, implying that they might not be 
41
available or plentiful at this establishment.
42

43
Enter your question about pizza (or 'exit' to quit): Is the pizza overpriced?
44

45
Finding relevant reviews and generating answer...
46

47
--- Answer ---
48
Based on the reviews provided, it seems that opinions about the pricing of the
49
pizza are mixed.
50

51
The first review (Document #6) states that "Nothing special, just an average 
52
pizza place." while giving a rating of 2 out of presumably 5. This suggests 
53
that the reviewer was somewhat disappointed with their experience and didn't 
54
think it was particularly good or worth the price.
55

56
On the other hand, the second review (Document #7) gives a higher rating (4 out 
57
of 5) but notes that "Not Worth the Hype". Although the reviewer mentions that 
58
it's "Great for families" and their kids enjoyed the pizza, they don't mention 
59
anything about the pricing being over or under par. 
60

61
Based on these reviews alone, I would say that opinions about the price are not 
62
strongly supported either way, but some reviewers do seem to think it might be 
63
a bit pricey (although this is purely based on limited evidence).
64

65
Enter your question about pizza (or 'exit' to quit): exit