Client library for the anthropic-bedrock API
Project description
Anthropic Bedrock Python API library
The Anthropic Bedrock Python library provides convenient access to the Anthropic Bedrock REST API from any Python 3.7+ application. It includes type definitions for all request params and response fields, and offers both synchronous and asynchronous clients powered by httpx.
For the non-Bedrock Anthropic API at api.anthropic.com, see anthropic-python
.
Documentation
The API documentation can be found here.
Installation
pip install anthropic-bedrock
Usage
The full API of this library can be found in api.md.
import anthropic_bedrock
from anthropic_bedrock import AnthropicBedrock
client = AnthropicBedrock(
# Authenticate by either providing the keys below or use the default AWS credential providers, such as
# using ~/.aws/credentials or the "AWS_SECRET_ACCESS_KEY" and "AWS_ACCESS_KEY_ID" environment variables.
aws_access_key="<access key>",
aws_secret_key="<secret key>",
# Temporary credentials can be used with aws_session_token.
# Read more at https://docs.aws.amazon.com/IAM/latest/UserGuide/id_credentials_temp.html.
aws_session_token="<session_token>",
# aws_region changes the aws region to which the request is made. By default, we read AWS_REGION,
# and if that's not present, we default to us-east-1. Note that we do not read ~/.aws/config for the region.
aws_region="us-east-2",
)
completion = client.completions.create(
model="anthropic.claude-v2",
max_tokens_to_sample=256,
prompt=f"{anthropic_bedrock.HUMAN_PROMPT} how does a court case get to the Supreme Court? {anthropic_bedrock.AI_PROMPT}",
)
print(completion.completion)
This library uses botocore internally for authentication; you can read more about the default providers here.
Async usage
Simply import AsyncAnthropicBedrock
instead of AnthropicBedrock
and use await
with each API call:
import anthropic_bedrock
from anthropic_bedrock import AsyncAnthropicBedrock
client = AsyncAnthropicBedrock()
async def main():
completion = await client.completions.create(
model="anthropic.claude-v2",
max_tokens_to_sample=256,
prompt=f"{anthropic_bedrock.HUMAN_PROMPT} how does a court case get to the Supreme Court? {anthropic_bedrock.AI_PROMPT}",
)
print(completion.completion)
asyncio.run(main())
Functionality between the synchronous and asynchronous clients is otherwise identical.
Streaming Responses
We provide support for streaming responses using Server Side Events (SSE).
from anthropic_bedrock import AnthropicBedrock, HUMAN_PROMPT, AI_PROMPT
client = AnthropicBedrock()
stream = client.completions.create(
prompt=f"{HUMAN_PROMPT} Your prompt here{AI_PROMPT}",
max_tokens_to_sample=300,
model="anthropic.claude-v2",
stream=True,
)
for completion in stream:
print(completion.completion, end="", flush=True)
The async client uses the exact same interface.
from anthropic_bedrock import AsyncAnthropicBedrock, HUMAN_PROMPT, AI_PROMPT
client = AsyncAnthropicBedrock()
stream = await client.completions.create(
prompt=f"{HUMAN_PROMPT} Your prompt here{AI_PROMPT}",
max_tokens_to_sample=300,
model="anthropic.claude-v2",
stream=True,
)
async for completion in stream:
print(completion.completion, end="", flush=True)
Using types
Nested request parameters are TypedDicts. Responses are Pydantic models, which provide helper methods for things like serializing back into JSON (v1, v2). To get a dictionary, call dict(model)
.
Typed requests and responses provide autocomplete and documentation within your editor. If you would like to see type errors in VS Code to help catch bugs earlier, set python.analysis.typeCheckingMode
to basic
.
Token counting
You can estimate billing for a given request with the client.count_tokens()
method, eg:
client = AnthropicBedrock()
client.count_tokens('Hello world!') # 3
Handling errors
When the library is unable to connect to the API (for example, due to network connection problems or a timeout), a subclass of anthropic_bedrock.APIConnectionError
is raised.
When the API returns a non-success status code (that is, 4xx or 5xx
response), a subclass of anthropic_bedrock.APIStatusError
is raised, containing status_code
and response
properties.
All errors inherit from anthropic_bedrock.APIError
.
import anthropic_bedrock
from anthropic_bedrock import AnthropicBedrock
client = AnthropicBedrock()
try:
client.completions.create(
prompt=f"{anthropic_bedrock.HUMAN_PROMPT} Your prompt here {anthropic_bedrock.AI_PROMPT}",
max_tokens_to_sample=256,
model="anthropic.claude-v2",
)
except anthropic_bedrock.APIConnectionError as e:
print("The server could not be reached")
print(e.__cause__) # an underlying Exception, likely raised within httpx.
except anthropic_bedrock.RateLimitError as e:
print("A 429 status code was received; we should back off a bit.")
except anthropic_bedrock.APIStatusError as e:
print("Another non-200-range status code was received")
print(e.status_code)
print(e.response)
Error codes are as followed:
Status Code | Error Type |
---|---|
400 | BadRequestError |
401 | AuthenticationError |
403 | PermissionDeniedError |
404 | NotFoundError |
422 | UnprocessableEntityError |
429 | RateLimitError |
>=500 | InternalServerError |
N/A | APIConnectionError |
Retries
Certain errors are automatically retried 2 times by default, with a short exponential backoff. Connection errors (for example, due to a network connectivity problem), 408 Request Timeout, 409 Conflict, 429 Rate Limit, and >=500 Internal errors are all retried by default.
You can use the max_retries
option to configure or disable retry settings:
from anthropic_bedrock import AnthropicBedrock, HUMAN_PROMPT, AI_PROMPT
# Configure the default for all requests:
client = AnthropicBedrock(
# default is 2
max_retries=0,
)
# Or, configure per-request:
client.with_options(max_retries=5).completions.create(
prompt=f"{HUMAN_PROMPT} Can you help me effectively ask for a raise at work?{AI_PROMPT}",
max_tokens_to_sample=300,
model="anthropic.claude-v2",
)
Timeouts
By default requests time out after 1 minute. You can configure this with a timeout
option,
which accepts a float or an httpx.Timeout
object:
from anthropic_bedrock import AnthropicBedrock, HUMAN_PROMPT, AI_PROMPT
# Configure the default for all requests:
client = AnthropicBedrock(
# default is 10 minutes
timeout=20.0,
)
# More granular control:
client = AnthropicBedrock(
timeout=httpx.Timeout(60.0, read=5.0, write=10.0, connect=2.0),
)
# Override per-request:
client.with_options(timeout=5 * 1000).completions.create(
prompt=f"{HUMAN_PROMPT} Where can I get a good coffee in my neighbourhood?{AI_PROMPT}",
max_tokens_to_sample=300,
model="anthropic.claude-v2",
)
On timeout, an APITimeoutError
is thrown.
Note that requests that time out are retried twice by default.
Advanced
Logging
We use the standard library logging
module.
You can enable logging by setting the environment variable ANTHROPIC_BEDROCK_LOG
to debug
.
$ export ANTHROPIC_BEDROCK_LOG=debug
How to tell whether None
means null
or missing
In an API response, a field may be explicitly null
, or missing entirely; in either case, its value is None
in this library. You can differentiate the two cases with .model_fields_set
:
if response.my_field is None:
if 'my_field' not in response.model_fields_set:
print('Got json like {}, without a "my_field" key present at all.')
else:
print('Got json like {"my_field": null}.')
Configuring the HTTP client
You can directly override the httpx client to customize it for your use case, including:
- Support for proxies
- Custom transports
- Additional advanced functionality
import httpx
from anthropic_bedrock import AnthropicBedrock
client = AnthropicBedrock(
base_url="http://my.test.server.example.com:8083",
http_client=httpx.Client(
proxies="http://my.test.proxy.example.com",
transport=httpx.HTTPTransport(local_address="0.0.0.0"),
),
aws_secret_key="<secret key>",
aws_access_key="<access key>",
aws_region="us-east-2",
)
Managing HTTP resources
By default the library closes underlying HTTP connections whenever the client is garbage collected. You can manually close the client using the .close()
method if desired, or with a context manager that closes when exiting.
Versioning
This package generally follows SemVer conventions, though certain backwards-incompatible changes may be released as minor versions:
- Changes that only affect static types, without breaking runtime behavior.
- Changes to library internals which are technically public but not intended or documented for external use. (Please open a GitHub issue to let us know if you are relying on such internals).
- Changes that we do not expect to impact the vast majority of users in practice.
We take backwards-compatibility seriously and work hard to ensure you can rely on a smooth upgrade experience.
We are keen for your feedback; please open an issue with questions, bugs, or suggestions.
Requirements
Python 3.7 or higher.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for anthropic_bedrock-0.1.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | e0109bf8604d1466e68dd880cd8b815d9d30c982c0eee0b4b0d3fd11267e0c4b |
|
MD5 | 18d27c66c7fcaa78df2d9545c8f760f4 |
|
BLAKE2b-256 | e849bfa22db5cae480869e0d59fca07f38cfd204a8d51a5a9d72368a9ad2e5d9 |