Elsai Model v1.0.0

Unified interface to connect with OpenAI, Azure OpenAI, and AWS Bedrock.

INFO

v2.0 adds Gemini, LiteLLM, async connectors, and native Bedrock implementation. See v2.0 docs.

Installation

pip install --extra-index-url https://core-packages.elsai.ai/root/elsai-model/ elsai-model==1.0.0

---

OpenAIConnector

from elsai_model.openai import OpenAIConnector

llm = OpenAIConnector(
    openai_api_key="your_key",
    model_name="gpt-4o-mini",
    temperature=0.1,
)

response = llm.invoke(messages=[{"role": "user", "content": "Hello!"}])

Environment variables: OPENAI_API_KEY, OPENAI_MODEL_NAME, OPENAI_TEMPERATURE

---

AzureOpenAIConnector

from elsai_model.azure_openai import AzureOpenAIConnector

llm = AzureOpenAIConnector(
    azure_endpoint="https://your-resource.openai.azure.com/",
    openai_api_key="your-key",
    openai_api_version="2023-05-15",
    deployment_name="gpt-4o-mini",
    temperature=0.1,
)

response = llm.invoke(messages=[{"role": "user", "content": "Hello!"}])

---

BedrockConnector

LangChain-based implementation in v1.0.

from elsai_model.bedrock import BedrockConnector

llm = BedrockConnector(
    aws_access_key="your_key",
    aws_secret_key="your_secret",
    aws_region="us-east-1",
    model_id="anthropic.claude-3-5-sonnet-20241022-v2:0",
)

result = llm.invoke([{"role": "user", "content": "What is the capital of France?"}])

WARNING

BedrockConnector in v1.0 uses LangChain internally. v2.0 migrated to native boto3 for lower latency. Claude Sonnet 4 models require v2.0 (Messages API). Do not use claude-sonnet-4-* model IDs with v1.0.