langchain/templates/rag-semi-structured/rag_semi_structured/chain.py

# Load
import uuid

from langchain.retrievers.multi_vector import MultiVectorRetriever
from langchain.storage import InMemoryStore
from langchain_community.chat_models import ChatOpenAI
from langchain_community.embeddings import OpenAIEmbeddings
from langchain_community.vectorstores import Chroma
from langchain_core.documents import Document
from langchain_core.output_parsers import StrOutputParser
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.pydantic_v1 import BaseModel
from langchain_core.runnables import RunnablePassthrough
from unstructured.partition.pdf import partition_pdf

# Path to docs
path = "docs"
raw_pdf_elements = partition_pdf(
    filename=path + "/LLaVA.pdf",
    # Unstructured first finds embedded image blocks
    extract_images_in_pdf=False,
    # Use layout model (YOLOX) to get bounding boxes (for tables) and find titles
    # Titles are any sub-section of the document
    infer_table_structure=True,
    # Post processing to aggregate text once we have the title
    chunking_strategy="by_title",
    # Chunking params to aggregate text blocks
    # Attempt to create a new chunk 3800 chars
    # Attempt to keep chunks > 2000 chars
    max_characters=4000,
    new_after_n_chars=3800,
    combine_text_under_n_chars=2000,
    image_output_dir_path=path,
)

# Categorize by type
tables = []
texts = []
for element in raw_pdf_elements:
    if "unstructured.documents.elements.Table" in str(type(element)):
        tables.append(str(element))
    elif "unstructured.documents.elements.CompositeElement" in str(type(element)):
        texts.append(str(element))

# Summarize

prompt_text = """You are an assistant tasked with summarizing tables and text. \ 
Give a concise summary of the table or text. Table or text chunk: {element} """
prompt = ChatPromptTemplate.from_template(prompt_text)
model = ChatOpenAI(temperature=0, model="gpt-4")
summarize_chain = {"element": lambda x: x} | prompt | model | StrOutputParser()

# Apply
table_summaries = summarize_chain.batch(tables, {"max_concurrency": 5})
# To save time / cost, only do text summaries if chunk sizes are large
# text_summaries = summarize_chain.batch(texts, {"max_concurrency": 5})
# We can just assign text_summaries to the raw texts
text_summaries = texts

# Use multi vector retriever

# The vectorstore to use to index the child chunks
vectorstore = Chroma(collection_name="summaries", embedding_function=OpenAIEmbeddings())

# The storage layer for the parent documents
store = InMemoryStore()
id_key = "doc_id"

# The retriever (empty to start)
retriever = MultiVectorRetriever(
    vectorstore=vectorstore,
    docstore=store,
    id_key=id_key,
)

# Add texts
doc_ids = [str(uuid.uuid4()) for _ in texts]
summary_texts = [
    Document(page_content=s, metadata={id_key: doc_ids[i]})
    for i, s in enumerate(text_summaries)
]
retriever.vectorstore.add_documents(summary_texts)
retriever.docstore.mset(list(zip(doc_ids, texts)))

# Add tables
table_ids = [str(uuid.uuid4()) for _ in tables]
summary_tables = [
    Document(page_content=s, metadata={id_key: table_ids[i]})
    for i, s in enumerate(table_summaries)
]
retriever.vectorstore.add_documents(summary_tables)
retriever.docstore.mset(list(zip(table_ids, tables)))

# RAG

# Prompt template
template = """Answer the question based only on the following context, which can include text and tables:
{context}
Question: {question}
"""  # noqa: E501
prompt = ChatPromptTemplate.from_template(template)

# LLM
model = ChatOpenAI(temperature=0, model="gpt-4")

# RAG pipeline
chain = (
    {"context": retriever, "question": RunnablePassthrough()}
    | prompt
    | model
    | StrOutputParser()
)


# Add typing for input
class Question(BaseModel):
    __root__: str


chain = chain.with_types(input_type=Question)