This release is a pre-release and may not be stable for production use.
Humanloop Python Library
The Humanloop Python library provides convenient access to the Humanloop API from Python.
Installation
pip install humanloop
Usage
Instantiate and use the client with the following:
from humanloop import ChatMessage, PromptKernelRequest
from humanloop.client import Humanloop
client = Humanloop(
api_key="YOUR_API_KEY",
)
client.prompts.log(
path="persona",
prompt=PromptKernelRequest(
model="gpt-4",
template=[
ChatMessage(
role="system",
content="You are {{person}}. Answer questions as this person. Do not break character.",
)
],
),
messages=[
ChatMessage(
role="user",
content="What really happened at Roswell?",
)
],
inputs={"person": "Trump"},
)
Async Client
The SDK also exports an async client so that you can make non-blocking calls to our API.
from humanloop import ChatMessage, PromptKernelRequest
from humanloop.client import AsyncHumanloop
client = AsyncHumanloop(
api_key="YOUR_API_KEY",
)
await client.prompts.log(
path="persona",
prompt=PromptKernelRequest(
model="gpt-4",
template=[
ChatMessage(
role="system",
content="You are {{person}}. Answer questions as this person. Do not break character.",
)
],
),
messages=[
ChatMessage(
role="user",
content="What really happened at Roswell?",
)
],
inputs={"person": "Trump"},
)
Exception Handling
All errors thrown by the SDK will be subclasses of ApiError.
import humanloop
try:
client.prompts.call(...)
except humanloop.core.ApiError as e: # Handle all errors
print(e.status_code)
print(e.body)
Advanced
Timeouts
By default, requests time out after 60 seconds. You can configure this with a timeout option at the client or request level.
from humanloop.client import Humanloop
client = Humanloop(
...,
# All timeouts are 20 seconds
timeout=20.0,
)
# Override timeout for a specific method
client.prompts.call(..., {
timeout_in_seconds=20.0
})
Retries
The SDK is instrumented with automatic retries with exponential backoff. A request will be retried as long as the request is deemed retriable and the number of retry attempts has not grown larger than the configured retry limit (default: 2).
A request is deemed retriable when any of the following HTTP status codes is returned:
Use the max_retries request option to configure this behavior.
client.prompts.call(..., {
max_retries=1
})
Custom HTTP client
You can override the httpx client to customize it for your use-case. Some common use-cases include support for proxies and transports.
import httpx
from humanloop.client import Humanloop
client = Humanloop(...,
http_client=httpx.Client(
proxies="http://my.test.proxy.example.com",
transport=httpx.HTTPTransport(local_address="0.0.0.0"),
),
)
Pagination
Paginated requests will return a SyncPager or AsyncPager, which can be used as generators for the underlying object.
from humanloop.client import Humanloop
client = Humanloop(
api_key="YOUR_API_KEY",
)
response = client.prompts.list(
size=1,
)
for item in response:
yield item
# alternatively, you can paginate page-by-page
for page in response.iter_pages():
yield page
Contributing
While we value open-source contributions to this SDK, this library is generated programmatically. Additions made directly to this library would have to be moved over to our generation code, otherwise they would be overwritten upon the next generated release. Feel free to open a PR as a proof of concept, but know that we will not be able to merge it as-is. We suggest opening an issue first to discuss with us!
On the other hand, contributions to the README are always very welcome!
1 maintainer
Metadata
1 maintainer
Release files for humanloop 0.8.0b5
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| humanloop-0.8.0b5.tar.gz | 75.8 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| humanloop-0.8.0b5-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 247.4 kB
Release files / humanloop-0.8.0b5.tar.gz
| Download URL | humanloop-0.8.0b5.tar.gz |
|---|---|
| Size | 75.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
e5c3f933ab5ba2e4c03ced30b934bb362e431ec98f6512e09dd73e12b4f85480
|
|
BLAKE2b-256 checksum How to use checksums |
8b78bda337a33324a7688a5bcbeefb244397ae2e057208412044d963924a2af0
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/1.5.1 CPython/3.8.18 Linux/5.15.0-1067-azure
|
Release files / humanloop-0.8.0b5-py3-none-any.whl
| Download URL | humanloop-0.8.0b5-py3-none-any.whl |
|---|---|
| Size | 171.6 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
8012c86c6fbd52a65efce3ac87dde19e29854ddace4b45d277be9ef17df549ae
|
|
BLAKE2b-256 checksum How to use checksums |
aa470964089d12e65bb37e39ffbec2225cd4d3b61de4f222ab2ddd698dae7e4a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/1.5.1 CPython/3.8.18 Linux/5.15.0-1067-azure
|
Security for humanloop 0.8.0b5
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
