site_name: DSPy
site_description: The framework for programming—rather than prompting—language models.
site_url: https://dspy.ai/
repo_url: https://github.com/stanfordnlp/dspy
repo_name: stanfordnlp/dspy
edit_uri: blob/main/docs/docs/
docs_dir: "docs/"
nav:
- Get Started: index.md
- Learn DSPy:
- Learning DSPy: learn/index.md
- DSPy Programming:
- Programming Overview: learn/programming/overview.md
- Language Models: learn/programming/language_models.md
- Signatures: learn/programming/signatures.md
- Modules: learn/programming/modules.md
- Adapters: learn/programming/adapters.md
- Tools: learn/programming/tools.md
- MCP: learn/programming/mcp.md
- DSPy Evaluation:
- Evaluation Overview: learn/evaluation/overview.md
- Data Handling: learn/evaluation/data.md
- Metrics: learn/evaluation/metrics.md
- DSPy Optimization:
- Optimization Overview: learn/optimization/overview.md
- Optimizers: learn/optimization/optimizers.md
- Tutorials:
- Tutorials Overview: tutorials/index.md
- Build AI Programs with DSPy:
- Overview: tutorials/build_ai_program/index.md
- Managing Conversation History: tutorials/conversation_history/index.md
- Building AI Agents with DSPy: tutorials/customer_service_agent/index.ipynb
- Building AI Applications by Customizing DSPy Modules: tutorials/custom_module/index.ipynb
- Retrieval-Augmented Generation (RAG): tutorials/rag/index.ipynb
- Building RAG as Agent: tutorials/agents/index.ipynb
- Entity Extraction: tutorials/entity_extraction/index.ipynb
- Classification: tutorials/classification/index.md
- Multi-Hop RAG: tutorials/multihop_search/index.ipynb
- Privacy-Conscious Delegation: tutorials/papillon/index.md
- Program Of Thought: tutorials/program_of_thought/index.ipynb
- Image Generation Prompt iteration: tutorials/image_generation_prompting/index.ipynb
- Audio: tutorials/audio/index.ipynb
- Optimize AI Programs with DSPy:
- Overview: tutorials/optimize_ai_program/index.md
- Math Reasoning: tutorials/math/index.ipynb
- Classification Finetuning: tutorials/classification_finetuning/index.ipynb
- Advanced Tool Use: tutorials/tool_use/index.ipynb
- Finetuning Agents: tutorials/games/index.ipynb
- Reflective Prompt Evolution with dspy.GEPA:
- Overview: tutorials/gepa_ai_program/index.md
- GEPA for AIME (Math): tutorials/gepa_aime/index.ipynb
- GEPA for Structured Information Extraction for Enterprise Tasks: tutorials/gepa_facilitysupportanalyzer/index.ipynb
- GEPA for Privacy-Conscious Delegation: tutorials/gepa_papillon/index.ipynb
- GEPA for Code Backdoor Classification (AI control): tutorials/gepa_trusted_monitor/index.ipynb
- Experimental RL Optimization for DSPy:
- Overview: tutorials/rl_ai_program/index.md
- RL for Privacy-Conscious Delegation: tutorials/rl_papillon/index.ipynb
- RL for Multi-Hop Research: tutorials/rl_multihop/index.ipynb
- Tools, Development, and Deployment:
- Overview: tutorials/core_development/index.md
- Use MCP in DSPy: tutorials/mcp/index.md
- Output Refinement: tutorials/output_refinement/best-of-n-and-refine.md
- Saving and Loading: tutorials/saving/index.md
- Cache: tutorials/cache/index.md
- Deployment: tutorials/deployment/index.md
- Debugging & Observability: tutorials/observability/index.md
- Tracking DSPy Optimizers: tutorials/optimizer_tracking/index.md
- Streaming: tutorials/streaming/index.md
- Async: tutorials/async/index.md
- Real-World Examples:
- Overview: tutorials/real_world_examples/index.md
- Generating llms.txt: tutorials/llms_txt_generation/index.md
- Memory-Enabled ReAct Agents: tutorials/mem0_react_agent/index.md
- Financial Analysis with Yahoo Finance: tutorials/yahoo_finance_react/index.md
- Email Information Extraction: tutorials/email_extraction/index.md
- Code Generation for Unfamiliar Libraries: tutorials/sample_code_generation/index.md
- Building a Creative Text-Based AI Game: tutorials/ai_text_game/index.md
- DSPy in Production: production/index.md
- Community:
- Community Resources: community/community-resources.md
- Use Cases: community/use-cases.md
- Community Ports: community/community-ports.md
- Contributing: community/how-to-contribute.md
- FAQ:
- FAQ: faqs.md
- Cheatsheet: cheatsheet.md
- API Reference:
- API Reference: api/index.md
- Adapters:
- Adapter: api/adapters/Adapter.md
- ChatAdapter: api/adapters/ChatAdapter.md
- JSONAdapter: api/adapters/JSONAdapter.md
- TwoStepAdapter: api/adapters/TwoStepAdapter.md
- Evaluation:
- CompleteAndGrounded: api/evaluation/CompleteAndGrounded.md
- Evaluate: api/evaluation/Evaluate.md
- EvaluationResult: api/evaluation/EvaluationResult.md
- SemanticF1: api/evaluation/SemanticF1.md
- answer_exact_match: api/evaluation/answer_exact_match.md
- answer_passage_match: api/evaluation/answer_passage_match.md
- Experimental:
- Citations: api/experimental/Citations.md
- Document: api/experimental/Document.md
- Models:
- Embedder: api/models/Embedder.md
- LM: api/models/LM.md
- Modules:
- BestOfN: api/modules/BestOfN.md
- ChainOfThought: api/modules/ChainOfThought.md
- CodeAct: api/modules/CodeAct.md
- Module: api/modules/Module.md
- MultiChainComparison: api/modules/MultiChainComparison.md
- Parallel: api/modules/Parallel.md
- Predict: api/modules/Predict.md
- ProgramOfThought: api/modules/ProgramOfThought.md
- ReAct: api/modules/ReAct.md
- Refine: api/modules/Refine.md
- RLM: api/modules/RLM.md
- Optimizers:
- GEPA:
- 1. GEPA Overview: api/optimizers/GEPA/overview.md
- 2. GEPA Advanced: api/optimizers/GEPA/GEPA_Advanced.md
- BetterTogether: api/optimizers/BetterTogether.md
- BootstrapFewShot: api/optimizers/BootstrapFewShot.md
- BootstrapFewShotWithRandomSearch: api/optimizers/BootstrapFewShotWithRandomSearch.md
- BootstrapFinetune: api/optimizers/BootstrapFinetune.md
- BootstrapRS: api/optimizers/BootstrapRS.md
- COPRO: api/optimizers/COPRO.md
- Ensemble: api/optimizers/Ensemble.md
- InferRules: api/optimizers/InferRules.md
- KNN: api/optimizers/KNN.md
- KNNFewShot: api/optimizers/KNNFewShot.md
- LabeledFewShot: api/optimizers/LabeledFewShot.md
- MIPROv2: api/optimizers/MIPROv2.md
- SIMBA: api/optimizers/SIMBA.md
- Primitives:
- Audio: api/primitives/Audio.md
- Code: api/primitives/Code.md
- Example: api/primitives/Example.md
- History: api/primitives/History.md
- Image: api/primitives/Image.md
- Prediction: api/primitives/Prediction.md
- Tool: api/primitives/Tool.md
- ToolCalls: api/primitives/ToolCalls.md
- Signatures:
- InputField: api/signatures/InputField.md
- OutputField: api/signatures/OutputField.md
- Signature: api/signatures/Signature.md
- Tools:
- ColBERTv2: api/tools/ColBERTv2.md
- Embeddings: api/tools/Embeddings.md
- PythonInterpreter: api/tools/PythonInterpreter.md
- Utils:
- StatusMessage: api/utils/StatusMessage.md
- StatusMessageProvider: api/utils/StatusMessageProvider.md
- StreamListener: api/utils/StreamListener.md
- asyncify: api/utils/asyncify.md
- configure_cache: api/utils/configure_cache.md
- disable_litellm_logging: api/utils/disable_litellm_logging.md
- disable_logging: api/utils/disable_logging.md
- enable_litellm_logging: api/utils/enable_litellm_logging.md
- enable_logging: api/utils/enable_logging.md
- inspect_history: api/utils/inspect_history.md
- load: api/utils/load.md
- streamify: api/utils/streamify.md
theme:
name: material
custom_dir: overrides
features:
- navigation.tabs
- navigation.path
- navigation.indexes
- navigation.expand
- toc.follow
- toc.integrate
- navigation.top
- search.suggest
- search.highlight
- content.tabs.link
- content.code.annotation
- content.code.copy
- navigation.footer
- content.action.edit
language: en
palette:
- scheme: default
toggle:
icon: material/weather-night
name: Switch to dark mode
primary: white
accent: black
- scheme: slate
toggle:
icon: material/weather-sunny
name: Switch to light mode
primary: black
accent: lime
icon:
repo: fontawesome/brands/git-alt
edit: material/pencil
view: material/eye
logo: static/img/dspy_logo.png
favicon: static/img/logo.png
extra_css:
- stylesheets/extra.css
plugins:
- social
- search:
lang: en
separator: '[\s-.]+'
- mkdocstrings:
handlers:
python:
options:
docstring_style: google
show_source: true
show_root_heading: true
heading_level: 3
members_order: source
separate_signature: false
show_category_heading: true
show_symbol_type_heading: true
show_docstring_parameters: true
show_if_no_docstring: true
show_signature_annotations: true
unwrap_annotated: true
annotations_path: brief
docstring_section_style: table
merge_init_into_class: true
rendering:
show_if_no_docstring: true
show_warnings: false
html_meta: false
- mkdocs-jupyter:
ignore_h1_titles: true
- redirects:
redirect_maps:
# Redirect /intro/ to the main page
"intro/index.md": "index.md"
"intro.md": "index.md"
"deep-dive/optimizers/bootstrap-fewshot.md": "api/optimizers/BootstrapFewShot.md"
"deep-dive/optimizers/bfrs.md": "api/optimizers/BootstrapFewShotWithRandomSearch.md"
"deep-dive/optimizers/BootstrapFinetune.md": "api/optimizers/BootstrapFinetune.md"
"deep-dive/optimizers/copro.md": "api/optimizers/COPRO.md"
"deep-dive/optimizers/Ensemble.md": "api/optimizers/Ensemble.md"
"deep-dive/optimizers/LabeledFewShot.md": "api/optimizers/LabeledFewShot.md"
"deep-dive/optimizers/miprov2.md": "api/optimizers/MIPROv2.md"
"api/optimizers/GEPA/index.md": "api/optimizers/GEPA/overview.md"
"docs/quick-start/getting-started-01.md": "tutorials/rag/index.ipynb"
"docs/quick-start/getting-started-02.md": "tutorials/rag/index.ipynb"
"quick-start/getting-started-01.md": "tutorials/rag/index.ipynb"
"quick-start/getting-started-02.md": "tutorials/rag/index.ipynb"
- llmstxt:
markdown_description: >
DSPy is the framework for programming—rather than prompting—language models.
DSPy unifies techniques for prompting, fine-tuning, reasoning, tool use, and evaluation of LMs.
It provides a systematic approach to building AI applications through composable modules,
optimization techniques, and evaluation frameworks.
sections:
Get Started:
- index.md: DSPy overview and quick start guide
Learn DSPy - Learning DSPy:
- learn/index.md: Three stages of building AI systems - programming, evaluation, and optimization
Learn DSPy - DSPy Programming:
- learn/programming/**.md
Learn DSPy - DSPy Evaluation:
- learn/evaluation/**.md
Learn DSPy - DSPy Optimization:
- learn/optimization/**.md
# Since we don't have a learn/**.md, future sections within learn/ should be added here
# to ensure they show up in the llms.txt navigation
Tutorials - Docs:
- tutorials/**.md
Tutorials - Notebooks:
- tutorials/**.ipynb
Community:
- community/**.md
FAQ:
- faqs.md: Common questions on DSPy usage, comparisons, optimization, and debugging
- cheatsheet.md: DSPy cheatsheet for quick reference
API Reference:
- api/**.md
extra:
social:
- icon: fontawesome/brands/github
link: https://github.com/stanfordnlp/dspy
- icon: fontawesome/brands/discord
link: https://discord.gg/XCGy2WDCQB
extra_javascript:
- "js/runllm-widget.js"
- "js/tutorial-nav.js"
- "js/copy-as-markdown.js"
markdown_extensions:
- toc:
permalink: true
toc_depth: 3
- pymdownx.tabbed:
alternate_style: true
- pymdownx.highlight:
anchor_linenums: true
- pymdownx.inlinehilite
- pymdownx.snippets
- admonition
- pymdownx.arithmatex:
generic: true
- footnotes
- pymdownx.details
- pymdownx.superfences
- pymdownx.mark
- attr_list
- md_in_html
- pymdownx.emoji:
emoji_index: !!python/name:material.extensions.emoji.twemoji
emoji_generator: !!python/name:material.extensions.emoji.to_svg
copyright: |
© 2025 DSPy