HyDE (Hypothetical Document Embeddings)

from langchain_openai import ChatOpenAI, OpenAIEmbeddings

# Creative model for hypothetical document generation
llm_hyde = ChatOpenAI(model_name="gpt-3.5-turbo", temperature=0.7)

# Precise model for final answer generation
llm_answer = ChatOpenAI(model_name="gpt-4o", temperature=0)

# Embeddings for retrieval
embeddings = OpenAIEmbeddings(model="text-embedding-3-small")

hyde_prompt_template = """
You are a medical expert writing a detailed section for a medical guide on pregnancy and childbirth.

Based on this question: {question}

Write a detailed and comprehensive medical document that would perfectly answer this question.
The document should include:
- Accurate medical information on the topic
- Relevant clinical details
- Appropriate medical recommendations
- Important considerations for maternal health
- Practical information and advice

Write the document as if it were part of an official medical guide on pregnancy and childbirth.
Be specific, detailed, and use appropriate medical terminology.

HYPOTHETICAL DOCUMENT:
"""

def process_hyde_query(
    query: str, 
    custom_hyde_llm: ChatOpenAI = None, 
    custom_answer_llm: ChatOpenAI = None
) -> Dict[str, Any]:
    """
    Processes a query using the full HyDE RAG pipeline.
    
    Args:
        query (str): The user's question.
        custom_hyde_llm (ChatOpenAI, optional): Custom model for hypothetical document generation.
        custom_answer_llm (ChatOpenAI, optional): Custom model for answer generation.
    
    Returns:
        Dict[str, Any]: Answer, contexts, hypothetical document, and detailed metrics.
    """
    # 1. Generate hypothetical document
    hypothetical_doc, hyde_result = _invoke_text_with_usage(
        current_hyde_llm,
        hyde_prompt.format_messages(question=query)
    )
    
    # 2. Retrieve similar documents using hypothetical doc
    retrieved_docs = retriever.invoke(hypothetical_doc)
    
    # 3. Format context
    formatted_context = format_docs(retrieved_docs)
    
    # 4. Generate final answer from real documents
    answer_text, answer_metrics = _invoke_text_with_usage(
        current_answer_llm,
        qa_prompt.format_messages(
            context=formatted_context,
            question=query
        )
    )
    
    # 5. Return comprehensive results
    return {
        'answer': answer_text,
        'contexts': [doc.page_content for doc in retrieved_docs],
        'hypothetical_document': hypothetical_doc,
        'hyde_metrics': hyde_result,
        'answer_metrics': answer_metrics,
        'total_cost': hyde_result['cost'] + answer_metrics['cost'],
        'total_input_tokens': hyde_result['input_tokens'] + answer_metrics['input_tokens'],
        'total_output_tokens': hyde_result['output_tokens'] + answer_metrics['output_tokens']
    }

La preeclampsia es una complicación grave del embarazo caracterizada por 
hipertensión arterial y daño a órganos, típicamente después de la semana 20 
de gestación. Se manifiesta con presión arterial superior a 140/90 mmHg y 
proteinuria. Los síntomas incluyen dolores de cabeza severos, cambios en la 
visión, dolor abdominal superior y edema significativo. Los factores de 
riesgo incluyen primer embarazo, embarazo múltiple, hipertensión crónica, 
diabetes, obesidad, y antecedentes familiares. El tratamiento requiere 
monitoreo cercano de la presión arterial, pruebas de función renal y 
hepática, y evaluación fetal frecuente. En casos graves, el único 
tratamiento definitivo es el parto, que puede necesitar inducirse 
prematuramente. Las complicaciones potenciales incluyen eclampsia, 
síndrome HELLP, desprendimiento de placenta, y restricción del crecimiento 
fetal...

from src.rag.hyde import query_for_evaluation

# Basic usage with default models
result = query_for_evaluation(
    question="¿Cuáles son los síntomas del parto prematuro?"
)

# With custom models for each stage
result = query_for_evaluation(
    question="¿Qué es la diabetes gestacional?",
    hyde_model="gpt-3.5-turbo",    # Hypothetical doc generation
    answer_model="gpt-4o-mini"      # Final answer generation
)

# With custom LLM instances
from langchain_openai import ChatOpenAI
hyde_llm = ChatOpenAI(model_name="gpt-3.5-turbo", temperature=0.8)
answer_llm = ChatOpenAI(model_name="gpt-4o", temperature=0)

result = query_for_evaluation(
    question="¿Qué cuidados necesito en el embarazo?",
    custom_hyde_llm=hyde_llm,
    custom_answer_llm=answer_llm
)

{
    "question": str,
    "answer": str,
    "contexts": List[str],
    "metadata": {
        "execution_time": 4.52,
        "input_tokens": 2341,      # Total for both LLM calls
        "output_tokens": 456,       # Total for both LLM calls
        "total_cost": 0.003892,
        "retrieval_method": "hyde",
        "llm_hyde_model": "gpt-3.5-turbo",
        "llm_answer_model": "gpt-4o",
        "hyde_provider": "openai",
        "answer_provider": "openai",
        "hyde_cost": 0.000234,      # Cost breakdown
        "answer_cost": 0.003658,
        "usage_source": "provider+provider"
    }
}

def multi_hyde_retrieval(query: str, num_hypotheses: int = 3) -> List[Document]:
    """Generate multiple hypothetical documents and retrieve from each."""
    all_docs = []
    
    for i in range(num_hypotheses):
        # Generate hypothesis (temperature > 0 gives variety)
        hyde_llm = ChatOpenAI(model_name="gpt-3.5-turbo", temperature=0.7)
        hypothetical_doc = hyde_llm.invoke(
            hyde_prompt.format_messages(question=query)
        ).content
        
        # Retrieve based on this hypothesis
        docs = retriever.invoke(hypothetical_doc)
        all_docs.extend(docs)
    
    # Deduplicate and re-rank
    return deduplicate_and_rerank(all_docs)