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-0.2.10.tar.gz (96.8 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-0.2.10-py3-none-any.whl (25.1 kB view details)

Uploaded Python 3

File details

Details for the file celeste_ai-0.2.10.tar.gz.

File metadata

  • Download URL: celeste_ai-0.2.10.tar.gz
  • Upload date:
  • Size: 96.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for celeste_ai-0.2.10.tar.gz
Algorithm Hash digest
SHA256 162457e1e8cf70da2cd4525d11e3cb3347a337a13dfaa417b5faeb2f5d524e25
MD5 c06b6630a398b475bf9f4d17d6e91ffd
BLAKE2b-256 1d5426e15a0f8d2acc6515783c9cb5e4d3e4f4ac52f5183365009a1fb54443a1

See more details on using hashes here.

Provenance

The following attestation bundles were made for celeste_ai-0.2.10.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-0.2.10-py3-none-any.whl.

File metadata

  • Download URL: celeste_ai-0.2.10-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-0.2.10-py3-none-any.whl
Algorithm Hash digest
SHA256 53b9059b4e24d0c453be7e74b441e87d5addeedec2cd1ca98489c64fe830b852
MD5 1f4bd40e745fdc189769bf2ec5eeff56
BLAKE2b-256 439ee7311da323cee761a6e8f67ef1f93f5dc2ea8d8b49eb8f3516143e35e8f0

See more details on using hashes here.

Provenance

The following attestation bundles were made for celeste_ai-0.2.10-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