# Google AI Studio
A collection of AI tools built on Google Vertex AI APIs. It works even in EU / UK.
At the time of writing, web-based Google AI Studio is not accessible in [EU / UK / some other regions](https://ai.google.dev/available_regions#available_regions). As this python package is based on Google Vertex AI APIs, there is no such restriction.
Current available features:
geminipro - a multiturn chat bot built on Google [Gemini Pro & Gemini Pro Vision](https://cloud.google.com/vertex-ai/docs/generative-ai/multimodal/overview) (LLM: Gemini Pro)
palm2 - a multiturn chat bot built on Google [PaLM 2](https://cloud.google.com/vertex-ai/docs/generative-ai/language-model-overview) (LLM: chat-bison-32k)
codey - a multiturn chat bot built on [Codey](https://cloud.google.com/vertex-ai/docs/generative-ai/code/code-models-overview) (LLM: codechat-bison-32k)
These are part of integrated tools, developed in our [LetMeDoIt AI project](https://github.com/eliranwong/letmedoit).
# Screenshot
<img width=”1440” alt=”geminipro_palm2” src=”https://github.com/eliranwong/letmedoit/assets/25262722/dc6f874e-ae11-4514-9ed0-3d22f2b1985c”>
# Install or Upgrade
> pip install –upgrade googleaistudio
# Google API Setup
Save a copy of your API key JSON file as “~/googleaistudio/credentials_googleaistudio.json”, where “~” denotes your home directory.
Read https://github.com/eliranwong/letmedoit/wiki/Google-API-Setup for setting up Google API.
# Usage
Run in terminal:
> geminipro
> geminiprovision
> palm2
> codey
# CLI options
> geminipro -h
> geminipro -t 0.5 -o 1024 “Hello!”
> geminiprovision -h
> geminiprovision -f image.png -t 0.5 -o 1024 “Describe this image file”
> palm2 -h
> palm2 -m “chat-bison” -t 0.5 -o 1024 “Hello!”
> codey -h
> codey -m “codechat-bison” -t 0.5 -o 1024 “How to use decorators in python?”
# Integration in LetMeDoIt AI project
https://github.com/eliranwong/letmedoit/wiki/Integration-with-Google-AI-Tools
# Documentation for Developers
https://cloud.google.com/vertex-ai/docs/generative-ai/learn/overview
https://cloud.google.com/vertex-ai/docs/generative-ai/learn/models
https://cloud.google.com/vertex-ai/docs/generative-ai/model-reference/overview
https://cloud.google.com/vertex-ai/docs/generative-ai/sdk-for-llm/llm-sdk-overview
https://cloud.google.com/vertex-ai/docs/generative-ai/multimodal/function-calling
1 maintainer
Metadata
1 maintainer
Release files for googleaistudio 0.0.22
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 | |
|---|---|---|---|---|
| googleaistudio-0.0.22.tar.gz | 21.1 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| googleaistudio-0.0.22-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 50.4 kB
Release files / googleaistudio-0.0.22.tar.gz
| Download URL | googleaistudio-0.0.22.tar.gz |
|---|---|
| Size | 21.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
2691504073f588b6cd2d3cbe6a7c1885e566ce86f3574afe917d062a5af0f4da
|
|
BLAKE2b-256 checksum How to use checksums |
257e84d99d19b3b2ea421bf22e1e73bc69f03ca40a6f7bcb23fe2da5ab088bc1
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.10.7
|
Release files / googleaistudio-0.0.22-py3-none-any.whl
| Download URL | googleaistudio-0.0.22-py3-none-any.whl |
|---|---|
| Size | 29.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
27257fc04674856b72606122fee120e903d14330f21b3870c802d391f5df2926
|
|
BLAKE2b-256 checksum How to use checksums |
3d2a48f32dc078db15119b40feb5b2e0656817490505c5338b02704cd5731d14
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.10.7
|
Security for googleaistudio 0.0.22
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.
