Obiguard Python SDK
Security Control Panel for AI Apps
pip install obiguard
Features
The Obiguard SDK is built on top of the OpenAI SDK, allowing you to seamlessly integrate Obiguard's advanced features while retaining full compatibility with OpenAI methods. With Obiguard, you can enhance your interactions with OpenAI or any other OpenAI-like provider by leveraging robust monitoring, reliability, prompt management, and more features - without modifying much of your existing code.
Obiguard AI Gateway
| Unified API Signature If you've used OpenAI, you already know how to use Obiguard with any other provider. |
Interoperability Write once, run with any provider. Switch between any model from_any provider seamlessly. |
| Automated Fallbacks & Retries Ensure your application remains functional even if a primary service fails. |
Load Balancing Efficiently distribute incoming requests among multiple models. |
| Semantic Caching Reduce costs and latency by intelligently caching results. |
Virtual Keys Secure your LLM API keys by storing them in Obiguard vault and using disposable virtual keys. |
Observability
| Logging Keep track of all requests for monitoring and debugging. |
Requests Tracing Understand the journey of each request for optimization. |
| Custom Metadata Segment and categorize requests for better insights. | Feedbacks Coming soon - Collect and analyse weighted feedback on requests from users. |
| Analytics Track your app & LLM's performance with 40+ production-critical metrics in a single place. |
Usage
Prerequisites
- Sign up on Obiguard and grab your Obiguard API Key
- Add your OpenAI key to Obiguard's Virtual Keys page and keep it handy
# Installing the SDK
$ pip install obiguard
$ export OBIGUARD_API_KEY=<OBIGUARD API OR VIRTUAL KEY>
Making a Request to OpenAI
- Obiguard fully adheres to the OpenAI SDK signature. You can instantly switch to Obiguard and start using our production features right out of the box.
- Just replace
from openai import OpenAIwithfrom obiguard_ai import Obiguard:
from obiguard import Obiguard
obiguard = Obiguard(
obiguard_api_key="OBIGUARD API OR VIRTUAL KEY"
)
chat_completion = obiguard.chat.completions.create(
messages=[{"role": 'user', "content": 'Say this is a test'}],
model='gpt-4'
)
print(chat_completion)
Async Usage
- Use
AsyncObiguardinstead ofObiguardwithawait:
import asyncio
from obiguard import AsyncObiguard
obiguard = AsyncObiguard(
obiguard_api_key="OBIGUARD API OR VIRTUAL KEY",
)
async def main():
chat_completion = await obiguard.chat.completions.create(
messages=[{'role': 'user', 'content': 'Say this is a test'}],
model='gpt-4'
)
print(chat_completion)
asyncio.run(main())
Compatibility with OpenAI SDK
Obiguard currently supports all the OpenAI methods, including the legacy ones.
| Methods | OpenAI V1.26.0 |
Obiguard V1.0.0 |
|---|---|---|
| Audio | ✅ | ✅ |
| Chat | ✅ | ✅ |
| Embeddings | ✅ | ✅ |
| Images | ✅ | ✅ |
| Fine-tuning | ✅ | ✅ |
| Batch | ✅ | ✅ |
| Files | ✅ | ✅ |
| Models | ✅ | ✅ |
| Moderations | ✅ | ✅ |
| Assistants | ✅ | ✅ |
| Threads | ✅ | ✅ |
| Thread - Messages | ✅ | ✅ |
| Thread - Runs | ✅ | ✅ |
| Thread - Run - Steps | ✅ | ✅ |
| Vector Store | ✅ | ✅ |
| Vector Store - Files | ✅ | ✅ |
| Vector Store - Files Batches | ✅ | ✅ |
| Generations | ❌ (Deprecated) | ✅ |
| Completions | ❌ (Deprecated) | ✅ |
Obiguard-Specific Methods (Coming Soon)
| Methods | Obiguard 1.0.X |
|---|---|
| Feedback | Obiguard |
| Prompts | Obiguard |
Check out Obiguard docs for the full list of supported providers
Contributing
Get started by checking out Github issues. Email us at support@obiguard.com.
Metadata
Release files for obiguard 1.0.19
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| obiguard-1.0.19.tar.gz | 365.8 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| obiguard-1.0.19-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 1.1 MB
Release files / obiguard-1.0.19.tar.gz
| Download URL | obiguard-1.0.19.tar.gz |
|---|---|
| Size | 365.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
4aa101fee3a6d8caac71f93ff385e77460b66d6329e38e73adf0039eca6b1fdf
|
|
BLAKE2b-256 checksum How to use checksums |
b56ff61e2798c837ba6b5df031b33977519a429576b59cb7f4be6dffec4f8acf
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.12.9
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Aug 7, 2025.
Transparency logRelease files / obiguard-1.0.19-py3-none-any.whl
| Download URL | obiguard-1.0.19-py3-none-any.whl |
|---|---|
| Size | 708.3 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
657ac13d87ab480035edd022e973e5c2cd706802e8103e910c0cba22f038262c
|
|
BLAKE2b-256 checksum How to use checksums |
3416a3282a10ddbde65330846c2874ddf24f648d5a6d456757f3d805b599dd36
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.12.9
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Aug 7, 2025.
Transparency log