Common utilities for OpenRelik AI functionality.
# LLM providers are configured via environment variables
# export OLLAMA_SERVER_URL=http://localhost:11434
# export OLLAMA_DEFAULT_MODEL=gemma2:9b
from openrelik_ai_common.providers import manager
provider = manager.LLMManager().get_provider("ollama")
llm = provider(model_name="gemma2:9b", system_instructions="Your name is Foobar.")
# Single text generation
response = llm.generate(prompt="Hello, what is your name?")
print(response)
# Multiturn chat session
response = llm.chat("What is your name?")
print(response)
response = llm.chat("My name is John Doe")
print(response)
response = llm.chat("What is my name?")
print(response)
# Chat on the command line
while True:
message = input("Message: ")
response = llm.chat(message)
print(response)
Obligatory Fine Print
This is not an official Google product (experimental or otherwise), it is just code that happens to be owned by Google.
Metadata
Release files for openrelik-ai-common 0.6.1
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 | |
|---|---|---|---|---|
| openrelik_ai_common-0.6.1.tar.gz | 13.6 kB | With provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| openrelik_ai_common-0.6.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 36.4 kB
Release files / openrelik_ai_common-0.6.1.tar.gz
| Download URL | openrelik_ai_common-0.6.1.tar.gz |
|---|---|
| Size | 13.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
7cb8b90cfb98f02fd80feb08bb950fc89abfa90a4cb9326419f0652930fa7063
|
|
BLAKE2b-256 checksum How to use checksums |
883399601ef33937d584369580d9996be5538b71a7e36115e567cfb3346b029e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
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 May 29, 2026.
Transparency logRelease files / openrelik_ai_common-0.6.1-py3-none-any.whl
| Download URL | openrelik_ai_common-0.6.1-py3-none-any.whl |
|---|---|
| Size | 22.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
ba8977a11038287b5b00874cb3d086730785f074228a115ba2857d93aea2a9d9
|
|
BLAKE2b-256 checksum How to use checksums |
6ae0fca71f8c9158893abd5253111710728911157df21fb7587fcab1d4336e7a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
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 May 29, 2026.
Transparency logSecurity for openrelik-ai-common 0.6.1
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.
Full provenance
All 2 files in this release have been uploaded with provenance metadata.
Attestation for openrelik_ai_common-0.6.1.tar.gz
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 May 29, 2026.
Transparency logA 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.