菜单
Use for DSPy reasoning modules including RLM, ProgramOfThought, CodeAct, Parallel, sandboxed execution, and long-context workflows.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use for DSPy adapter selection, JSONAdapter, XMLAdapter, ChatAdapter, native function calling, structured outputs, and multimodal inputs like dspy.Image or dspy.Audio.
Use for composing DSPy modules with Ensemble, MultiChainComparison, ensemble voting, sequential pipelines, and multi-program workflows.
Use for BetterTogether, prompt plus weight optimization, fine-tuning sequences, and strategy chains like p -> w -> p.
Use for BootstrapFewShot, bootstrapped demonstrations, teacher-model demos, and low-data DSPy prompt optimization.
Use for creating custom DSPy modules, extending dspy.Module, reusable components, stateful modules, serialization, and module testing.
Use for debugging DSPy programs, inspect_history, tracing LLM calls, custom callbacks, observability, monitoring, and cost tracking.
| name | dspy-reasoning-modules |
| version | 1.0.0 |
| dspy-compatibility | 3.2.1 |
| tags | ["reasoning"] |
| requires-extras | [] |
| description | Use for DSPy reasoning modules including RLM, ProgramOfThought, CodeAct, Parallel, sandboxed execution, and long-context workflows. |
| allowed-tools | ["Read","Write","Glob","Grep"] |
Choose the appropriate DSPy reasoning module for long-context exploration, code-assisted reasoning, or parallel execution.
| Module | Use it for | Important constraint |
|---|---|---|
dspy.RLM | Exploring very large contexts with iterative REPL code and recursive sub-LM calls | Experimental; requires Deno by default |
dspy.ProgramOfThought | Solving tasks by generating and executing Python | Requires Deno by default |
dspy.CodeAct | Combining generated Python with predefined tool functions | Functions only; requires Deno |
dspy.Parallel | Running (module, example) pairs concurrently | Tune threads and error handling |
RLM treats long inputs as external data in a sandbox rather than placing the full context in each LM prompt.
import dspy
dspy.configure(lm=dspy.LM("openai/gpt-4o"))
rlm = dspy.RLM(
"document, question -> answer",
max_iterations=12,
max_llm_calls=30,
sub_lm=dspy.LM("openai/gpt-4o-mini"),
)
result = rlm(
document=very_long_document,
question="What were the main revenue drivers?",
)
print(result.answer)
Use max_iterations, max_llm_calls, and max_output_chars as explicit cost and output bounds.
The default dspy.PythonInterpreter uses Deno and Pyodide. It denies host filesystem, environment, and network access unless explicitly enabled.
from pathlib import Path
import dspy
with dspy.PythonInterpreter(
enable_read_paths=[Path("./inputs")],
enable_network_access=["api.example.com"],
) as interpreter:
print(interpreter.execute("print('ready')"))
Grant only the minimum paths, environment variables, and network hosts needed by the task.
import dspy
dspy.configure(lm=dspy.LM("openai/gpt-4o-mini"))
math = dspy.ProgramOfThought("question -> answer")
print(math(question="What is the sum of the first 100 integers?").answer)
Use CodeAct when generated code also needs curated host-side tools:
def lookup_rate(currency: str) -> float:
"""Return a trusted exchange rate from the application service."""
return rates[currency]
agent = dspy.CodeAct("amount, currency -> converted", tools=[lookup_rate])
parallel = dspy.Parallel(num_threads=8, return_failed_examples=True)
results, failed_examples, exceptions = parallel(
[(program, {"question": question}) for question in questions]
)
Predict or ChainOfThought until code execution or long-context exploration is justified.RLM as experimental and load-test before production deployment.