Pixeltable + LangGraph

import pixeltable as pxt
from pixeltable.functions.document import document_splitter
from pixeltable.functions.huggingface import sentence_transformer, clip
from pixeltable.functions.openai import chat_completions, invoke_tools

TableModel = pxt.model_base()
embed = sentence_transformer.using(
    model_id='sentence-transformers/all-MiniLM-L6-v2'
)
visual = clip.using(model_id='openai/clip-vit-base-patch32')

class Docs(TableModel, name='docs'):
    document: pxt.Document
    image: pxt.Image
    title: pxt.String
    __indexes__ = [pxt.EmbeddingIndex(image, embedding=visual)]

class Chunks(
    TableModel,
    name='chunks',
    base=Docs,
    iterator=document_splitter(
        Docs.document, separators='sentence,token_limit', limit=512
    ),
):
    __indexes__ = [pxt.EmbeddingIndex(text, embedding=embed)]

@pxt.udf
def search_docs(question: str) -> str:
    chunks = pxt.get_table('app.chunks')
    sim = chunks.text.similarity(string=question)
    rows = (
        chunks.order_by(sim, asc=False)
        .limit(5)
        .select(chunks.text)
        .collect()
    )
    return '\n'.join(r['text'] for r in rows)

tools = pxt.tools(search_docs)

class Assistant(TableModel, name='assistant'):
    message: pxt.String
    response = chat_completions(
        messages=[{'role': 'user', 'content': message}],
        model='gpt-4o-mini',
        tools=tools,
    )
    tool_output = invoke_tools(tools, response)

# pxt schema update app.py app

from langchain_community.document_loaders import PyPDFLoader
from langchain_text_splitters import RecursiveCharacterTextSplitter
from langchain_openai import ChatOpenAI, OpenAIEmbeddings
from langchain_community.vectorstores import Chroma
from langchain_core.tools import tool
from langgraph.prebuilt import create_react_agent

docs = PyPDFLoader('handbook.pdf').load()
chunks = RecursiveCharacterTextSplitter(
    chunk_size=512, chunk_overlap=50
).split_documents(docs)
store = Chroma.from_documents(
    chunks, OpenAIEmbeddings(model='text-embedding-3-small')
)

@tool
def search_handbook(question: str) -> str:
    hits = store.similarity_search(question, k=5)
    return '\n'.join(d.page_content for d in hits)

agent = create_react_agent(
    ChatOpenAI(model='gpt-4o-mini'), tools=[search_handbook]
)
agent.invoke({'messages': [('user', 'What is the refund policy?')]})
# Images, versioning, and re-chunking on insert are still yours.