Launch Open-Source Apps with LangChain

%%writefile requirements.txt
jinja2==3.0.3
langchain==0.0.339
openai==1.3.3
pdf2image
pdfminer
pdfminer.six
pillow_heif
tabulate
tiktoken
unstructured
opencv-python-headless
unstructured.pytesseract
unstructured.inference

%pip install -r requirements.txt --quiet

from langchain.document_loaders import OnlinePDFLoader

loader = OnlinePDFLoader("http://leavcom.com/pdf/DBpdf.pdf")

data = loader.load()

from langchain.text_splitter import RecursiveCharacterTextSplitter

print (f"You have {len(data)} document(s) in your data")
print (f"There are {len(data[0].page_content)} characters in your document")

text_splitter = RecursiveCharacterTextSplitter(chunk_size=2000, chunk_overlap=0)
texts = text_splitter.split_documents(data)

print (f"You have {len(texts)} pages")

%%sql
DROP DATABASE IF EXISTS pdf_db;
CREATE DATABASE IF NOT EXISTS pdf_db;

%%sql
DROP TABLE IF EXISTS pdf_docs1;
CREATE TABLE IF NOT EXISTS pdf_docs1 (
    id INT PRIMARY KEY,
    content TEXT CHARACTER SET utf8mb4 COLLATE utf8mb4_general_ci,
    vector BLOB
);

import os
import getpass

os.environ["OPENAI_API_KEY"] = getpass.getpass("OpenAI API Key:")

import json
import sqlalchemy as sa
from langchain.embeddings import OpenAIEmbeddings
from singlestoredb import create_engine

conn = create_engine().connect()

embedder = OpenAIEmbeddings()

# Fetch all embeddings in one call
embeddings = embedder.embed_documents([doc.page_content for doc in texts])

# Build query parameters
params = []
for i, (text_content, embedding) in enumerate(zip(texts, embeddings)):
    params.append(dict(id=i+1, content=text_content, vector=json.dumps(embedding)))

stmt = sa.text("""
    INSERT INTO pdf_docs1 (
        id,
        content,
        vector
    )
    VALUES (
        :id,
        :content,
        JSON_ARRAY_PACK_F32(:vector)
    )
""")

conn.execute(stmt, params)

%%sql
SELECT JSON_ARRAY_UNPACK_F32(vector) as vector
FROM pdf_docs1
LIMIT 1;

query_text = "Will object-oriented databases be commercially successful?"

query_embedding = embedder.embed_documents([query_text])[0]

stmt = sa.text("""
    SELECT
        content,
        DOT_PRODUCT_F32(JSON_ARRAY_PACK_F32(:embedding), vector) AS score
    FROM pdf_docs1
    ORDER BY score DESC
    LIMIT 1
""")

results = conn.execute(stmt, dict(embedding=json.dumps(query_embedding)))

for row in results:
    print(row[0])

import openai

client = openai.OpenAI()

prompt = f"The user asked: {query_text}. The most similar text from the document is: {row[0]}"

response = client.chat.completions.create(
    model="gpt-3.5-turbo",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
)

print(response.choices[0].message.content)

%%sql
DROP DATABASE IF EXISTS pdf_db