Skip to main content

Python SDK for Dialetica AI - Multi-agent conversational AI platform

Project description

Dialetica AI Python SDK

Official Python SDK for the Dialetica AI platform - a multi-agent conversational AI system.

Installation

pip install dialetica

Quick Start

from dialetica import Dialetica, AgentRequest, ContextRequest, MessageRequest

# Initialize the client
client = Dialetica(api_key="dai_your_api_key_here")
# Or use environment variable: DIALETICA_AI_API_KEY

# Create an agent
agent = client.agents.create(AgentRequest(
    name="Assistant",
    description="Helpful assistant",
    instructions=["Be helpful and concise"],
    model="gpt-4o"
))

# Create a context
context = client.contexts.create(ContextRequest(
    name="Support Chat",
    agents=[agent.id]
))

# Send a message
message = MessageRequest(
    role="user",
    sender_name="User",
    content="Hello!"
)

# Get response
responses = client.contexts.run(context, [message])
for response in responses:
    print(f"{response.sender_name}: {response.content}")

Features

  • Multi-Agent Conversations: Create contexts with multiple AI agents
  • Knowledge Management: Store and query knowledge using semantic search
  • Streaming Support: Real-time streaming responses with SSE
  • Type-Safe: Full Pydantic models for request/response validation
  • Simple API: Clean, intuitive interface following industry best practices

Building and Publishing

To build the package:

cd backend
python -m build

To publish to PyPI (test first with TestPyPI):

# Test on TestPyPI first
python -m twine upload --repository testpypi dist/*

# Then publish to PyPI
python -m twine upload dist/*

Documentation

For full documentation, visit https://docs.dialetica-ai.com

License

MIT License

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

dialetica-1.0.1.tar.gz (15.6 kB view details)

Uploaded Source

Built Distribution

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

dialetica-1.0.1-py3-none-any.whl (12.3 kB view details)

Uploaded Python 3

File details

Details for the file dialetica-1.0.1.tar.gz.

File metadata

  • Download URL: dialetica-1.0.1.tar.gz
  • Upload date:
  • Size: 15.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.7

File hashes

Hashes for dialetica-1.0.1.tar.gz
Algorithm Hash digest
SHA256 92d2a4d11c0e022b5704e022f94618069fe6127686abe56ec338ee0ba2a984c5
MD5 33b9777490c186b9232273c987aaa89e
BLAKE2b-256 2b12c85c3c08ba20ac758bd67ee471d0124d029bd7c8b7c3549b104c40e41853

See more details on using hashes here.

File details

Details for the file dialetica-1.0.1-py3-none-any.whl.

File metadata

  • Download URL: dialetica-1.0.1-py3-none-any.whl
  • Upload date:
  • Size: 12.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.7

File hashes

Hashes for dialetica-1.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 53c8f056c469051b239cfbfb0ebf2b1127fe66ba33f8a5996bdc33686bbf4565
MD5 1878292d9d90f29fcd24d7fc97248b8a
BLAKE2b-256 7bc6c60634e33a14f54814a9b4adb61ad860d7aecdf023a82e4189335a5f69f0

See more details on using hashes here.

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