SkillsAdd

omidzamani/dspy-skills

dspy-adapters-multimodal

Use for DSPy adapter selection, JSONAdapter, XMLAdapter, ChatAdapter, native function calling, structured outputs, and multimodal inputs like dspy.Image or dspy.Audio.

First seen Jun 12, 2026

Installation

$ npx skills add omidzamani/dspy-skills --skill dspy-adapters-multimodal
View on skills.sh ↗ GitHub repository ↗

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

linkfox-multimodal-recognize-image Similar name
linkfox-ai/linkfox-skills

基于多模态AI的图片识别与分析。当用户想分析、描述、从图片URL中提取信息、image recognition, image…

1.2K installs
mmx-cli Similar name
minimax-ai/skills

Use mmx to generate text, images, video, speech, and music via the MiniMax AI platform. Use whe…

638 installs
vision-multimodal Similar name
thelobbi/claude

Vision and multimodal capabilities for Claude including image analysis, PDF processing, and doc…

553 installs
ai-multimodal Similar name
mrgoonie/claudekit-skills

Process and generate multimedia content using Google Gemini API. Capabilities include analyze a…

515 installs
linkfox-multimodal-extract-attributes Similar name
linkfox-ai/linkfox-skills

利用多模态AI分析商品主图，提取视觉特征和提示词。当用户提到分析产品图片、从商品图中提取视觉属性…

368 installs
linkfox-multimodal-generate-image Similar name
linkfox-ai/linkfox-skills

AI驱动的图片生成与编辑工?

365 installs

Also in this package

Other skills from omidzamani/dspy-skills · top by installs.

npx skills add omidzamani/dspy-skills
dspy-gepa-reflective 42 dspy-evaluation-suite 39 dspy-debugging-observability 33 dspy-react-agent-builder 33 dspy-rag-pipeline 32 dspy-signature-designer 32 dspy-custom-module-design 31 dspy-output-refinement-constraints 31 dspy-advanced-module-composition 31 dspy-miprov2-optimizer 30

Browse all from omidzamani/dspy-skills

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

Stars 121
License LICENSE
Default branch master
Open issues 1
Status Active

Skill metadata

Parsed from SKILL.md frontmatter.

Version1.0.0
Allowed toolsRead, Write, Glob, Grep

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 3,456 B
  • docs SUMMARY.md 199 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 7 installs

SKILL.md

DSPy Adapters and Multimodal I/O

Goal

Choose an adapter deliberately and model image, audio, and file inputs with DSPy's typed primitives.

Adapter Selection

Adapter Use it for
dspy.ChatAdapter() Default, human-readable field markers, broad model compatibility
dspy.JSONAdapter() Structured JSON output and native function calling where supported
dspy.XMLAdapter() XML-tagged fields when XML is easier for the target LM to follow
dspy.TwoStepAdapter() A separate extraction pass when parsing needs extra help

Configure globally or for a limited scope:

import dspy

dspy.configure(
    lm=dspy.LM("openai/gpt-4o-mini"),
    adapter=dspy.JSONAdapter(),
)

with dspy.context(adapter=dspy.XMLAdapter()):
    result = dspy.Predict("question -> answer")(question="What is DSPy?")

Native Function Calling

JSONAdapter enables native function calling by default. ChatAdapter keeps text parsing by default. Override either behavior explicitly:

chat_native = dspy.ChatAdapter(use_native_function_calling=True)
json_manual = dspy.JSONAdapter(use_native_function_calling=False)

DSPy falls back to manual parsing when the configured LM does not support native function calling.

Image Inputs

class DescribeImage(dspy.Signature):
    image: dspy.Image = dspy.InputField()
    description: str = dspy.OutputField()

describe = dspy.Predict(DescribeImage)
result = describe(image=dspy.Image("./diagram.png"))

Pass a local path, HTTP URL, bytes, PIL image, or existing data URI directly to dspy.Image(...).

Audio and File Inputs

class SummarizeAudio(dspy.Signature):
    audio: dspy.Audio = dspy.InputField()
    summary: str = dspy.OutputField()

audio = dspy.Audio.from_file("./meeting.wav")
summary = dspy.Predict(SummarizeAudio)(audio=audio)
class SummarizeFile(dspy.Signature):
    file: dspy.File = dspy.InputField()
    summary: str = dspy.OutputField()

document = dspy.File.from_path("./research.pdf")
summary = dspy.Predict(SummarizeFile)(file=document)

Provider capabilities vary. Verify that the selected model accepts the media type before deployment.

Best Practices

  1. Start with ChatAdapter; switch only for a measured reason.
  2. Use typed signatures for structured output.
  3. Test adapter behavior against the exact production model.
  4. Avoid deprecated Image.fromfile() and Image.fromurl() helpers; call dspy.Image(...).
  5. Keep local file handling and uploaded file IDs within provider policy.

Related Skills

  • Design signatures: [dspy-signature-designer](../dspy-signature-designer/SKILL.md)
  • Build tool agents: [dspy-react-agent-builder](../dspy-react-agent-builder/SKILL.md)

Official Documentation