Call with the Anthropic SDK¶
This page assumes that your application already uses the Anthropic Python SDK. After completing it, the application receives one text response through the Genesis Messages shape.
For full integration details and usage boundaries, see Genesis SDK.
How the call progresses¶
The Anthropic client uses the Genesis origin/root as its service address and appends the Messages version path itself. A successful response keeps the Messages content-block shape. Read text from a content block rather than using the Chat Completions response shape.
Prepare the call¶
Prepare the following:
Required item |
How to obtain it |
Purpose on this page |
|---|---|---|
Existing Anthropic Python SDK |
Use the dependency already used by the application; this page does not install or select a version |
Creates the client |
Genesis origin/root |
Obtain it from the Genesis connection information for the current environment |
Client service address |
Genesis personal access token |
Obtain it from the Genesis connection information for the current environment |
Client credential |
Messages-capable model ID |
Select one from the model information for the current environment or list models |
Selects the model for this call |
This client uses the personal-access-token authentication shape. A service-account API Key uses a different authentication header; use the HTTP instructions in Messages (Anthropic) when calling with a service account.
Send a Messages request¶
The following example creates a client and submits one user message. It reads the text result from the first content block.
import os
from anthropic import Anthropic
client = Anthropic(
base_url=os.environ["GENESIS_ORIGIN"],
api_key=os.environ["GENESIS_PERSONAL_ACCESS_TOKEN"],
)
message = client.messages.create(
model=os.environ["GENESIS_MODEL_ID"],
max_tokens=1024,
messages=[
{"role": "user", "content": "Explain data lineage in one sentence."},
],
)
print(message.content[0].text)
Printed text means that this Messages call returned. The model must support Messages. Streaming, image input, and tool calling depend on the selected model and current service configuration.
Next steps¶
For complete request, response, authentication, and error details, see Messages (Anthropic).