Skip to main content

Open source, type-safe primitives for multi-modal AI. All capabilities, all providers, one interface

Project description

Celeste AI

Celeste Logo

The primitive layer for multi-modal AI

All capabilities. All providers. One interface.

Primitives, not frameworks.

Python License PyPI

Quick StartRequest Provider


🚀 Quick Start

from celeste import create_client, Capability, Provider

# Create client
client = create_client(
    capability=Capability.TEXT_GENERATION,
    provider=Provider.ANTHROPIC,
    api_key="your-api-key",  # Or loads automatically from environment
)

# Generate
response = await client.generate(prompt="Explain quantum computing")
print(response.content)

Install:

uv add "celeste-ai[text-generation]"  # Text only
uv add "celeste-ai[image-generation]" # Image generation
uv add "celeste-ai[all]"              # Everything

🎨 Multi-Modal Example

# Same API, different modalities
text_client = create_client(Capability.TEXT_GENERATION, Provider.ANTHROPIC)
image_client = create_client(Capability.IMAGE_GENERATION, Provider.OPENAI)
video_client = create_client(Capability.VIDEO_GENERATION, Provider.GOOGLE)

text = await text_client.generate(prompt="Write a haiku about AI")
image = await image_client.generate(prompt="A sunset over mountains")
video = await video_client.generate(prompt="Waves crashing on a beach")

No special cases. No separate libraries. One consistent interface.


Google Anthropic OpenAI Mistral Cohere xAI DeepSeek Groq Perplexity Ollama Hugging Face Replicate Stability AI Runway ElevenLabs

and many more

Missing a provider? Request it – ⚡ we ship fast.


🔧 Type-Safe by Design

# Full IDE autocomplete
response = await client.generate(
    prompt="Explain AI",
    temperature=0.7,    # ✅ Validated (0.0-2.0)
    max_tokens=100,     # ✅ Validated (int)
)

# Typed response
print(response.content)              # str (IDE knows the type)
print(response.usage.input_tokens)   # int
print(response.metadata["model"])     # str

Catch errors before production.


🤝 Contributing

We welcome contributions! See CONTRIBUTING.md.

Request a provider: GitHub Issues Report bugs: GitHub Issues


📄 License

Apache 2.0 license – see LICENSE for details.


Get StartedDocumentationGitHub

Made with ❤️ by developers tired of framework lock-in

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

celeste_ai-0.2.8.tar.gz (96.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

celeste_ai-0.2.8-py3-none-any.whl (25.1 kB view details)

Uploaded Python 3

File details

Details for the file celeste_ai-0.2.8.tar.gz.

File metadata

  • Download URL: celeste_ai-0.2.8.tar.gz
  • Upload date:
  • Size: 96.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for celeste_ai-0.2.8.tar.gz
Algorithm Hash digest
SHA256 2da27456c60614a74fb48eb4d04c8580cb43b71b70704a19e1fe434490612231
MD5 e8728173648ea8979480f3cc8f912e44
BLAKE2b-256 53796ccc9a00485a137a0acc5d02bdece36a28b510ec7135c5990e2aeae7f70c

See more details on using hashes here.

Provenance

The following attestation bundles were made for celeste_ai-0.2.8.tar.gz:

Publisher: publish.yml on withceleste/celeste-python

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file celeste_ai-0.2.8-py3-none-any.whl.

File metadata

  • Download URL: celeste_ai-0.2.8-py3-none-any.whl
  • Upload date:
  • Size: 25.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for celeste_ai-0.2.8-py3-none-any.whl
Algorithm Hash digest
SHA256 6f74de0719431b06d66aabbbbe4c9e6b587641f32bc700723fd0f89961d09d8d
MD5 4bb42fa5438f783d66991dbcb245277f
BLAKE2b-256 5bd4ad06d42578940eb54fe428767d0c25958dc3ba626c7082239827faef95e2

See more details on using hashes here.

Provenance

The following attestation bundles were made for celeste_ai-0.2.8-py3-none-any.whl:

Publisher: publish.yml on withceleste/celeste-python

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page