sik-llms
- Easy llm interface; eliminates parsing json responses or building up json for functions/tools
- OpenAI and any OpenAI-compatible API
- Anthropic
- Sync and Async support
- Functions/Tools
- Structured Output
- Supports Anthropic models even though structured output is not natively supported in their models
- Reasoning mode in OpenAI and Anthropic
- ReasoningAgent that iteratively reasons and calls tool
See examples
from sik_llms import create_client, user_message, ResponseChunk
model = create_client(
model_name='gpt-4o-mini', # or e.g. 'claude-3-7-sonnet'
temperature=0.1,
)
messages = [
system_message("You are a helpful assistant."),
user_message("What is the capital of France?"),
]
# sync
response = model(messages=messages)
# async
response = await model.run_async(messages=messages)
# async streaming
responses = []
summary = None
async for response in model.stream(messages=messages):
if isinstance(response, TextChunkEvent):
print(response.content, end="")
responses.append(response)
else:
summary = response
print(summary)
Installation
uv install sik-llms or pip install sik-llms
1 maintainer
Metadata
1 maintainer
Release files for sik-llms 0.3.33
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 | |
|---|---|---|---|---|
| sik_llms-0.3.33.tar.gz | 168.0 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| sik_llms-0.3.33-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 212.7 kB
Release files / sik_llms-0.3.33.tar.gz
| Download URL | sik_llms-0.3.33.tar.gz |
|---|---|
| Size | 168.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
1aae51e26bed47d6e4bfaeb2ed87ad91305c69ba8f604a4874459721eea3c509
|
|
BLAKE2b-256 checksum How to use checksums |
a0e7fc5f2d9db79116f09440ddabce5c9c77837a102c3f6e53b8626833842953
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.7.5
|
Release files / sik_llms-0.3.33-py3-none-any.whl
| Download URL | sik_llms-0.3.33-py3-none-any.whl |
|---|---|
| Size | 44.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
806de12ed9e158d5b5c354bd7831bdcca055486836efd828f3319989c0552271
|
|
BLAKE2b-256 checksum How to use checksums |
11ebc70ff64fd7930c60dd48462e4ffd7fbdd4037b5d10db6cff74efe1fdde2c
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.7.5
|
Security for sik-llms 0.3.33
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.
