Mise à l’échelle de l’inférence pour améliorer la RAG multimodale

import sys
assert sys.version_info >= (3, 10) and sys.version_info < (3, 13), "Use Python 3.10, 3.11, or 3.12 to run this notebook."

! pip install "git+https://github.com/ibm-granite-community/utils.git" \
    transformers \
    pillow \
    langchain_community \
    langchain_huggingface \
    langchain_milvus \
    docling \
    replicate

import logging

logging.basicConfig(level=logging.INFO)

from langchain_huggingface import HuggingFaceEmbeddings
from transformers import AutoTokenizer

embeddings_model_path = "ibm-granite/granite-embedding-30m-english"
embeddings_model = HuggingFaceEmbeddings(
    model_name=embeddings_model_path,
)
embeddings_tokenizer = AutoTokenizer.from_pretrained(embeddings_model_path)

from ibm_granite_community.notebook_utils import get_env_var
from langchain_community.llms import Replicate
from transformers import AutoProcessor

vision_model_path = "ibm-granite/granite-vision-3.2-2b"
vision_model = Replicate(
    model=vision_model_path,
    replicate_api_token=get_env_var("REPLICATE_API_TOKEN"),
    model_kwargs={
        "max_tokens": embeddings_tokenizer.max_len_single_sentence, # Set the maximum number of tokens to generate as output.
        "min_tokens": 100, # Set the minimum number of tokens to generate as output.
        "temperature": 0.01,
    },
)
vision_processor = AutoProcessor.from_pretrained(vision_model_path)

model_path = "ibm-granite/granite-3.3-8b-instruct"
model = Replicate(
    model=model_path,
    replicate_api_token=get_env_var("REPLICATE_API_TOKEN"),
    model_kwargs={
        "max_tokens": 1000, # Set the maximum number of tokens to generate as output.
        "min_tokens": 100, # Set the minimum number of tokens to generate as output.
        "temperature": 0.01
    },
)
tokenizer = AutoTokenizer.from_pretrained(model_path)

from docling.document_converter import DocumentConverter, PdfFormatOption
from docling.datamodel.base_models import InputFormat
from docling.datamodel.pipeline_options import PdfPipelineOptions

pdf_pipeline_options = PdfPipelineOptions(
    do_ocr=False,
    generate_picture_images=True,
)
format_options = {
    InputFormat.PDF: PdfFormatOption(pipeline_options=pdf_pipeline_options),
}
converter = DocumentConverter(format_options=format_options)

sources = [
    "https://midwestfoodbank.org/images/AR_2020_WEB2.pdf",
]
conversions = { source: converter.convert(source=source).document for source in sources }

from docling_core.transforms.chunker.hybrid_chunker import HybridChunker
from docling_core.types.doc import DocItem, TableItem
from langchain_core.documents import Document

doc_id = 0
texts: list[Document] = []
for source, docling_document in conversions.items():
    for chunk in HybridChunker(tokenizer=embeddings_tokenizer).chunk(docling_document):
        items: list[DocItem] = chunk.meta.doc_items # type: ignore
        if len(items) == 1 and isinstance(items[0], TableItem):
            continue # we will process tables later
        refs = " ".join(map(lambda item: item.get_ref().cref, items))
        print(refs)
        text = chunk.text
        document = Document(
            page_content=text,
            metadata={
                "doc_id": (doc_id:=doc_id+1),
                "source": source,
                "ref": refs,
            },
        )
        texts.append(document)

print(f"{len(texts)} text document chunks created")

from docling_core.types.doc import DocItemLabel

doc_id = len(texts)
tables: list[Document] = []
for source, docling_document in conversions.items():
    for table in docling_document.tables:
        if table.label in [DocItemLabel.TABLE]:
            ref = table.get_ref().cref
            print(ref)
            text = table.export_to_markdown(docling_document)
            document = Document(
                page_content=text,
                metadata={
                    "doc_id": (doc_id:=doc_id+1),
                    "source": source,
                    "ref": ref
                },
            )
            tables.append(document)


print(f"{len(tables)} table documents created")

import base64
import io
import PIL.Image
import PIL.ImageOps

def encode_image(image: PIL.Image.Image, format: str = "png") -> str:
    image = PIL.ImageOps.exif_transpose(image) or image
    image = image.convert("RGB")

    buffer = io.BytesIO()
    image.save(buffer, format)
    encoding = base64.b64encode(buffer.getvalue()).decode("utf-8")
    uri = f"data:image/{format};base64,{encoding}"
    return uri

# Feel free to experiment with this prompt
image_prompt = "Give a detailed description of what is depicted in the image"
conversation = [
    {
        "role": "user",
        "content": [
            {"type": "image"},
            {"type": "text", "text": image_prompt},
        ],
    },
]
vision_prompt = vision_processor.apply_chat_template(
    conversation=conversation,
    add_generation_prompt=True,
)
pictures: list[Document] = []
doc_id = len(texts) + len(tables)
for source, docling_document in conversions.items():
    for picture in docling_document.pictures:
        ref = picture.get_ref().cref
        print(ref)
        image = picture.get_image(docling_document)
        if image:
            text = vision_model.invoke(vision_prompt, image=encode_image(image))
            document = Document(
                page_content=text,
                metadata={
                    "doc_id": (doc_id:=doc_id+1),
                    "source": source,
                    "ref": ref,
                },
            )
            pictures.append(document)

print(f"{len(pictures)} image descriptions created")

import itertools
from docling_core.types.doc import RefItem
from IPython.display import display

# Print all created documents
for document in itertools.chain(texts, tables):
    print(f"Document ID: {document.metadata['doc_id']}")
    print(f"Source: {document.metadata['source']}")
    print(f"Content:\n{document.page_content}")
    print("=" * 80)  # Separator for clarity

for document in pictures:
    print(f"Document ID: {document.metadata['doc_id']}")
    source = document.metadata['source']
    print(f"Source: {source}")
    print(f"Content:\n{document.page_content}")
    docling_document = conversions[source]
    ref = document.metadata['ref']
    picture = RefItem(cref=ref).resolve(docling_document)
    image = picture.get_image(docling_document)
    print("Image:")
    display(image)
    print("=" * 80)  # Separator for clarity

import tempfile
from langchain_core.vectorstores import VectorStore, VectorStoreRetriever
from langchain_milvus import Milvus

db_file = tempfile.NamedTemporaryFile(prefix="vectorstore_", suffix=".db", delete=False).name
print(f"The vector database will be saved to {db_file}")

vector_db: VectorStore = Milvus(
    embedding_function=embeddings_model,
    connection_args={"uri": db_file},
    auto_id=True,
    enable_dynamic_field=True,
    index_params={"index_type": "AUTOINDEX"},
)

import itertools

documents = list(itertools.chain(texts, tables, pictures))
ids = vector_db.add_documents(documents)
print(f"{len(ids)} documents added to the vector database")
retriever: VectorStoreRetriever = vector_db.as_retriever(search_kwargs={"k": 10})

query = "Analyze how Midwest Food Bank's financial efficiency changed during the pandemic by comparing their 2019 and 2020 performance metrics. What specific pandemic adaptations had the greatest impact on their operational capacity, and how did their volunteer management strategy evolve to maintain service levels despite COVID-19 restrictions? Provide specific statistics from the report to support your analysis."
for doc in vector_db.as_retriever().invoke(query):
    print(doc)
    print("=" * 80)  # Separator for clarity

Les documents renvoyés doivent répondre à la requête. Allons-y et créons notre pipeline RAG.

from ibm_granite_community.notebook_utils import escape_f_string
from langchain.prompts import PromptTemplate
from langchain.chains.retrieval import create_retrieval_chain
from langchain.chains.combine_documents import create_stuff_documents_chain

# Create a Granite prompt for question-answering with the retrieved context
prompt = tokenizer.apply_chat_template(
    conversation=[{
        "role": "user",
        "content": "{input}",
    }],
    documents=[{
        "doc_id": "0",
        "text": "{context}",
    }],
    add_generation_prompt=True,
    tokenize=False,
)
prompt_template = PromptTemplate.from_template(template=escape_f_string(prompt, "input", "context"))

# Create a Granite document prompt template to wrap each retrieved document
document_prompt_template = PromptTemplate.from_template(template="""\
<|end_of_text|>
<|start_of_role|>document {{"document_id": "{doc_id}"}}<|end_of_role|>
{page_content}""")
document_separator=""

# Assemble the retrieval-augmented generation chain
combine_docs_chain = create_stuff_documents_chain(
    llm=model,
    prompt=prompt_template,
    document_prompt=document_prompt_template,
    document_separator=document_separator,
)
rag_chain = create_retrieval_chain(
    retriever=retriever,
    combine_docs_chain=combine_docs_chain,
)

outputs = rag_chain.invoke({"input": query})
print(outputs['answer'])

from dataclasses import dataclass, field, InitVar
from langchain_core.documents import Document

@dataclass
class DRAG_Demonstration:
    query: str
    answer: str
    retriever: InitVar[VectorStoreRetriever] = field(kw_only=True)
    documents: list[Document] = field(default_factory=list, kw_only=True)

    def __post_init__(self, retriever: VectorStoreRetriever):
        if not self.documents:
            self.documents = retriever.invoke(self.query)

    def __format__(self, format_spec: str) -> str:
        formatted_documents = "\n".join(
            f"Document {i+1}:\n{document.page_content}"
            for i, document in enumerate(self.documents)
        )
        return f"""\
{formatted_documents}
Question: {self.query}
Answer: {self.answer}
"""

def create_enhanced_drag_demonstrations(vector_db: VectorStore) -> list[DRAG_Demonstration]:
    """Create high-quality demonstrations for DRAG technique that showcase effective document analysis"""
    demonstration_retriever: VectorStoreRetriever = vector_db.as_retriever(search_kwargs={"k": 5})
    demonstrations = [
        DRAG_Demonstration(
            query="How did the COVID-19 pandemic impact Midwest Food Bank's operations in 2020?",
            answer="The COVID-19 pandemic significantly impacted Midwest Food Bank's operations in 2020. Despite challenges, MFB remained open and responsive to increased needs. They implemented safety protocols, reduced volunteer numbers for social distancing, and altered their distribution model to allow partner agencies to receive food safely. The pandemic created unprecedented food insecurity, with many people seeking assistance for the first time. MFB distributed 37% more food than in 2019, with a record 179 semi-loads of Disaster Relief family food boxes sent nationwide. The organization also faced supply chain disruptions and food procurement challenges in the early months but continued to find and distribute food. Community, business, and donor support helped fund operations and food purchases. Additionally, MFB began participating in the USDA Farmers to Families Food Box program in May 2020, distributing over $52 million worth of nutritious produce, protein, and dairy products.",
            retriever=demonstration_retriever
        ),
        DRAG_Demonstration(
            query="What role did volunteers play at Midwest Food Bank during 2020, and how were they affected by the pandemic?",
            answer="Volunteers were described as 'the life-blood of the organization' in the 2020 annual report. Despite the pandemic creating safety challenges, volunteers demonstrated courage and dedication by increasing their hours to meet growing needs. MFB implemented safety protocols at each location and limited volunteer group sizes to allow for social distancing. This created a challenge as food needs increased while fewer volunteers were available to help. To address this gap, multiple MFB locations received assistance from the National Guard, who filled vital volunteer positions driving trucks, operating forklifts, and helping with food distributions. In 2020, 17,930 individuals volunteered 300,898 hours of service, equivalent to 150 full-time employees. The volunteer-to-staff ratio was remarkable with 450 volunteers for every 1 paid MFB staff member, highlighting the volunteer-driven nature of the organization during the crisis.",
            retriever=demonstration_retriever
        ),
        DRAG_Demonstration(
            query="How did Midwest Food Bank's international programs perform during 2020, particularly in Haiti and East Africa?",
            answer="In 2020, Midwest Food Bank's international operations in East Africa and Haiti faced unique challenges but continued to serve communities. In East Africa (operated as Kapu Africa), strict lockdowns led to mass hunger, especially in slum areas. Kapu Africa distributed 7.2 million Tender Mercies meals, working with partner ministries to share food in food-insecure slums. A notable outcome was a spiritual awakening among recipients, with many asking why they were receiving help. In Haiti, the pandemic added to existing challenges, closing airports, seaports, factories, and schools. MFB Haiti more than doubled its food shipments to Haiti, delivering over 160 tons of food relief, nearly three-quarters being Tender Mercies meals. As Haitian children primarily receive nourishment from school lunches, MFB Haiti distributed Tender Mercies through faith-based schools and also partnered with over 20 feeding centers serving approximately 1,100 children daily. Nearly 1 million Tender Mercies meals were distributed in Haiti during 2020.",
            retriever=demonstration_retriever
        ),
    ]

    return demonstrations

# Format all demonstrations together
demonstrations = create_enhanced_drag_demonstrations(vector_db)

formatted_demonstrations = "\n\n".join(
    f"Example {i+1}:\n{demo}"
    for i, demo in enumerate(demonstrations)
)

drag_prompt = tokenizer.apply_chat_template(
    conversation=[{
        "role": "user",
        "content": f"""\
Here are examples of effectively extracting information from documents to answer questions.

{formatted_demonstrations}

Follow these examples when answering the user's question:

{{input}}""",
    }],
    documents=[{
        "doc_id": "0",
        "text": "Placeholder{context}",
    }],
    add_generation_prompt=True,
    tokenize=False,
)

# Convert to prompt template
drag_prompt_template = PromptTemplate.from_template(template=escape_f_string(drag_prompt, "input", "context"))

import typing
from langchain_core.retrievers import BaseRetriever, RetrieverInput, RetrieverOutput
from langchain_core.callbacks.manager import CallbackManagerForRetrieverRun

class ReorderingRetriever(BaseRetriever):
    base_retriever: BaseRetriever

    def _get_relevant_documents(
        self, query: RetrieverInput, *, run_manager: CallbackManagerForRetrieverRun, **kwargs: typing.Any
    ) -> RetrieverOutput:
        docs = self.base_retriever._get_relevant_documents(query, run_manager=run_manager, **kwargs)
        return list(reversed(docs))  # Reverse the order so higher-ranked docs are closer to query in prompt

reordering_retriever = ReorderingRetriever(base_retriever=retriever)

drag_combine_docs_chain = create_stuff_documents_chain(
    llm=model,
    prompt=drag_prompt_template,
    document_prompt=document_prompt_template,
    document_separator=document_separator,
)

drag_chain = create_retrieval_chain(
    retriever=reordering_retriever,
    combine_docs_chain=drag_combine_docs_chain,
)

drag_outputs = drag_chain.invoke({"input": query})
print("\n=== DRAG-Enhanced Answer ===")
print(drag_outputs['answer'])

decompose_prompt = tokenizer.apply_chat_template(
    conversation=[{
        "role": "user",
        "content": """\
You are a helpful assistant that breaks down complex questions into simpler sub-questions.
For multi-part or complex questions, generate 1-3 sub-questions that would help answer the main question.

Here are examples of how to decompose complex questions:
{demonstrations}

Follow the above examples when breaking down the user's question.
If the following question is already simple enough, just respond with "No follow-up needed."

Otherwise, break down the following question into simpler sub-questions. Format your response as:
Follow up: [sub-question]

Question: {input}"""
    }],
    add_generation_prompt=True,
    tokenize=False,
)

decompose_prompt_template = PromptTemplate.from_template(template=escape_f_string(decompose_prompt, "input", "demonstrations"))
decompose_chain = decompose_prompt_template | model

intermediate_prompt = tokenizer.apply_chat_template(
    conversation=[{
        "role": "user",
        "content": """\
You are a helpful assistant that answers specific questions based on the provided documents.

Focus only on the sub-question and provide a concise intermediate answer.
Please answer the following sub-question based on the provided documents.
Format your response as:
Intermediate answer: [your concise answer to the sub-question]

Sub-question: {input}
"""
    }],
    documents=[{
        "doc_id": "0",
        "text": "Placeholder{context}",
    }],
    add_generation_prompt=True,
    tokenize=False,
)

intermediate_prompt_template = PromptTemplate.from_template(template=escape_f_string(intermediate_prompt, "input", "context"))
intermediate_combine_docs_chain = create_stuff_documents_chain(
    llm=model,
    prompt=intermediate_prompt_template,
    document_prompt=document_prompt_template,
    document_separator=document_separator,
)
intermediate_chain = create_retrieval_chain(
    retriever=reordering_retriever,
    combine_docs_chain=intermediate_combine_docs_chain,
)

final_prompt = tokenizer.apply_chat_template(
    conversation=[{
        "role": "user",
        "content": """\
You are a helpful assistant that provides comprehensive answers to questions.
Use the intermediate answers to sub-questions to formulate a complete final answer.
Please provide a final answer to the main question based on the intermediate answers to sub-questions.
Format your response as:
So the final answer is: [your comprehensive answer to the main question]

Main question: {input}

Sub-questions and intermediate answers:
{context}"""
    }],
    add_generation_prompt=True,
    tokenize=False,
)

final_prompt_template = PromptTemplate.from_template(template=escape_f_string(final_prompt, "input", "context"))
final_chain = final_prompt_template | model

@dataclass
class IterDRAG_Demonstration_Base:
    query: str
    answer: str

@dataclass
class IterDRAG_Demonstration(IterDRAG_Demonstration_Base):
    intermediate: list[IterDRAG_Demonstration_Base]

    def __format__(self, format_spec: str) -> str:
        sub_questions="\n".join(
            f"Follow up: {sub.query}"
            for sub in self.intermediate
        )

        return f"Question: {self.query}\n{sub_questions}"

def create_iterdrag_demonstrations() -> list[IterDRAG_Demonstration]:
    """Create examples showing how to decompose and answer complex questions"""

    demonstrations = [
        IterDRAG_Demonstration(
            query="What impact did the pandemic have on the food bank's operations and distribution?",
            answer="The pandemic had a profound impact on food bank operations and distribution. Distribution volume increased by 60% to over 100 million pounds of food in 2020. Operationally, the food bank faced supply chain disruptions, volunteer shortages, and safety protocol challenges. In response, they implemented contactless distribution, expanded mobile pantries, created emergency food boxes for vulnerable populations, and developed virtual nutrition education. Despite these challenges, they successfully scaled operations to meet the unprecedented community need during the crisis.",
            intermediate=[
                IterDRAG_Demonstration_Base(
                    query="How did food distribution volume change during the pandemic?",
                    answer="Food distribution volume increased by 60% during the pandemic, rising from approximately 62 million pounds in 2019 to over 100 million pounds in 2020.",
                ),
                IterDRAG_Demonstration_Base(
                    query="What operational challenges did the food bank face during the pandemic?",
                    answer="The food bank faced challenges including supply chain disruptions, volunteer shortages due to social distancing requirements, and the need to implement new safety protocols for food handling and distribution.",
                ),
                IterDRAG_Demonstration_Base(
                    query="What new programs were implemented in response to the pandemic?",
                    answer="New programs included contactless distribution methods, expanded mobile pantry operations, emergency food boxes for vulnerable populations, and virtual nutrition education classes.",
                ),
            ],
        ),
        IterDRAG_Demonstration(
            query="How does the food bank's financial management compare to industry standards for non-profits?",
            answer="The food bank demonstrates excellent financial management compared to industry standards. With 94% of its budget allocated to program services and only 6% to administrative and fundraising costs, it exceeds the industry benchmark of 85-90% for program spending. This financial efficiency places the food bank among the top-performing non-profits in terms of maximizing donor impact and minimizing overhead expenses.",
            intermediate=[
                IterDRAG_Demonstration_Base(
                    query="What percentage of the food bank's budget goes to program services versus administrative costs?",
                    answer="94% of the food bank's budget goes directly to program services, with only 6% allocated to administrative and fundraising costs.",
                ),
                IterDRAG_Demonstration_Base(
                    query="What are the industry standards for program spending versus overhead for food banks?",
                    answer="Industry standards suggest that well-run food banks typically allocate 85-90% of their budget to program services, with 10-15% for administrative and fundraising expenses.",
                ),
            ],
        ),
    ]
    return demonstrations

import re

def iterative_drag(main_question: str) -> dict[str, typing.Any]:
    """
    Implements IterDRAG: decomposing queries, retrieving documents for sub-queries,
    and generating a final answer based on intermediate answers.
    """
    print(f"\n=== Processing query with IterDRAG: '{main_question}' ===")

    # Step 1: Decompose the main question into sub-questions
    print("Step 1: Decomposing the query into sub-questions...")
    iterdrag_demonstrations = create_iterdrag_demonstrations()
    formatted_demonstrations = "\n\n".join(
        f"Example {i+1}:\n{demo}"
        for i, demo in enumerate(iterdrag_demonstrations)
    )
    decompose_result = decompose_chain.invoke({
        "input": main_question,
        "demonstrations": formatted_demonstrations,
    })
    decompose_answer = decompose_result

    # Extract sub-questions using regex
    sub_questions = re.findall(r"Follow up: (.*?)(?=Follow up:|\n|$)", decompose_answer, re.DOTALL)
    sub_questions = [sq.strip() for sq in sub_questions if sq.strip()]
    if not sub_questions:
        print("No decomposition needed or found. Using standard DRAG approach.")
        return drag_chain.invoke({"input": main_question})
    print(f"Decomposed into {len(sub_questions)} sub-questions")

    # Step 2: Answer each sub-question
    intermediate_pairs: list[dict[str, str]] = []
    for i, sub_question in enumerate(sub_questions):
        print(f"\nStep 2.{i+1}: Processing sub-question: '{sub_question}'")

        # Generate answer for this sub-question
        intermediate_result = intermediate_chain.invoke({"input": sub_question})
        intermediate_answer = intermediate_result["answer"]

        # Extract intermediate answer using regex
        intermediate_answer_match = re.search(r"Intermediate answer: (.*?)$", intermediate_answer, re.DOTALL)
        if intermediate_answer_match:
            intermediate_answer = intermediate_answer_match.group(1).strip()

        print(f"Generated intermediate answer: {intermediate_answer[:100]}...")

        # Store the sub-question and its answer
        intermediate_pairs.append({"input": sub_question, "answer": intermediate_answer})

    # Step 3: Generate the final answer based on sub-question answers
    print("\nStep 3: Generating final answer based on intermediate answers...")
    final_result = final_chain.invoke({
        "input": main_question,
        "context": "\n\n".join(
            f"Sub-question: {pair['input']}\nIntermediate answer: {pair['answer']}"
            for pair in intermediate_pairs
        ),
    })
    final_answer = final_result

    # Extract final answer
    final_answer_match = re.search(r"So the final answer is: (.*?)$", final_answer, re.DOTALL)
    if final_answer_match:
        final_answer = final_answer_match.group(1).strip()

    return {"input": main_question, "answer": final_answer, "intermediate": intermediate_pairs}

# Run all approaches on the same complex query
comparison_query = "What was the full impact chain of the National Guard's assistance during the pandemic? Specifically, how did their involvement affect volunteer operations, what specific tasks did they perform, and how did this ultimately translate to community impact in terms of food distribution capabilities and reach?"

print("\n=== Standard RAG ===")
standard_result = rag_chain.invoke({"input": comparison_query})
print(standard_result["answer"])

print("\n=== DRAG ===")
drag_result = drag_chain.invoke({"input": comparison_query})
print(drag_result["answer"])

print("\n=== IterDRAG ===")
iterdrag_result = iterative_drag(comparison_query)
print(iterdrag_result["answer"])