Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

fix: update the model name #1699

Merged
merged 4 commits into from
Feb 5, 2025
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions gemini/sample-apps/gemini-quart-cloudrun/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ This application demonstrates a non-blocking communication with [Quart](https://

## Application screenshot

![Demo animation](https://storage.googleapis.com/github-repo/generative-ai/sample-apps/gemini-quart-cloudrun/demo_anim.gif)
![Demo animation](https://storage.googleapis.com/github-repo/generative-ai/sample-apps/gemini-quart-cloudrun/demo_anim.png)

Interruption example with the demo chat app

Expand All @@ -27,7 +27,7 @@ Interruption example with the demo chat app

**Key Benefits building Gen AI app with Quart + Gemini Live API:**

- **Responsiveness and Natural Conversation:** Quart supports non-blocking, full-duplex WebSocket communication natively, crucial for a truly interactive Gen AI experience. It doesn't halt while waiting for Gemini, ensuring quick replies and a smooth conversation flow, especially when the app supports multimodal interaction using audio and images and is network-latency sensitive. Users can send text or voice messages in quick succession, and Quart handles them and interrupts with less delays (as shown in the demo animation above).
- **Responsiveness and Natural Conversation:** Quart supports non-blocking, full-duplex WebSocket communication natively, crucial for a truly interactive Gen AI experience. It doesn't halt while waiting for Gemini, ensuring quick replies and a smooth conversation flow, especially when the app supports multimodal interaction using audio and images and is network-latency sensitive. Users can send text or voice messages in quick succession, and Quart handles them and interrupts with less delays.
- **Concurrency and Scalability:** Handles many users and their messages simultaneously. Quart can process multiple requests and replies with Gemini concurrently, making the gen AI app faster and more efficient. Quart makes better use of server resources with the single thread event-loop design, leading to lower operational costs and better scalability.

### Flask (blocking) v. Quart (non-blocking)
Expand Down
2 changes: 1 addition & 1 deletion gemini/sample-apps/gemini-quart-cloudrun/app/app.py
Original file line number Diff line number Diff line change
Expand Up @@ -38,7 +38,7 @@
GEMINI_API_KEY: str = os.environ.get("GEMINI_API_KEY", "")
QUART_DEBUG_MODE: bool = os.environ.get("QUART_DEBUG_MODE") == "True"

GEMINI_MODEL: str = "gemini-2.0-flash-exp"
GEMINI_MODEL: str = "gemini-2.0-flash-001"

# Gemini API Client: Use either one of the following APIs
gemini_client: Client = (
Expand Down
Loading