Contents Menu Expand Light mode Dark mode Auto light/dark, in light mode Auto light/dark, in dark mode Skip to content
Build and Optimize LM Workflows
Light Logo Dark Logo
Build and Optimize LM Workflows
GitHub
  • Tutorials
    • Introduction
    • Prompt
    • Parser and Structured Output
    • Generator
    • Embedder
  • Integrations
    • All Providers
  • Use Cases
    • Question Answering
    • Q&A Computation Graph
    • Q&A Text Grad Trace Graph
    • Q&A Few Shot Demo Trace Graph
    • Classification Optimization
    • RAG optimization
  • Contributor Guide
    • Contributing Process
    • Development Essentials
  • Developer Notes
    • Design Philosophy
    • Class Hierarchy
    • AdalFlow Trace Graph
    • Component
    • DataClass
    • Prompt
    • ModelClient
    • Generator
    • Basic Generator Tutorial
    • Parser
    • Embedder
    • Retriever
    • Text Splitter
    • Data (Database/Pipeline)
    • RAG Playbook
    • RAG with Memory
    • Function calls
    • Agent
    • LLM Evaluation
    • Datasets
    • Logger Example
    • Design
    • Use Logger in Projects
    • Tracing
  • API Reference
    • Core
      • base_data_class
      • component
      • container
      • default_prompt_template
      • embedder
      • generator
      • model_client
      • prompt_builder
      • retriever
      • string_parser
      • func_tool
      • tool_manager
      • types
      • db
      • functional
      • tokenizer
    • Components
      • model_client
        • anthropic_client
        • azureai_client
        • bedrock_client
        • cohere_client
        • deepseek_client
        • fireworks_client
        • google_client
        • groq_client
        • mistral_client
        • ollama_client
        • openai_client
        • sambanova_client
        • together_client
        • transformers_client
        • utils
        • xai_client
      • retriever
        • bm25_retriever
        • faiss_retriever
        • lancedb_retriver
        • llm_retriever
        • postgres_retriever
        • qdrant_retriever
        • reranker_retriever
      • output_parsers
        • dataclass_parser
        • outputs
      • agent
        • react
      • data_process
        • data_components
        • text_splitter
      • memory
        • memory
    • Datasets
      • big_bench_hard
      • trec
      • hotpot_qa
      • types
    • Evaluation
      • base
      • answer_match_acc
      • retriever_recall
      • llm_as_judge
      • g_eval
    • Optimization
      • parameter
      • optimizer
      • grad_component
      • loss_component
      • types
      • few_shot
        • bootstrap_optimizer
      • text_grad
        • backend_engine_prompt
        • llm_text_loss
        • ops
        • text_loss_with_eval_fn
        • tgd_optimizer
      • trainer
        • adal
        • trainer
    • Tracing
      • decorators
      • generator_state_logger
      • generator_call_logger
    • Utils
      • data
      • setup_env
      • logger
      • file_io
      • config
      • lazy_import
      • registry
      • serialization
      • cache
Back to top

utils¶

Functions

f1_score(y, y_gt)

normalize_answer(s)

normalize_answer(s)[source]¶
f1_score(y: str, y_gt: str) → float[source]¶
Copyright © 2025, SylphAI, Inc
Made with Furo
On this page
  • utils
    • normalize_answer()
    • f1_score()