JeCabrera commited on
Commit
61b28b6
·
verified ·
1 Parent(s): 7127bf5

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -45
README.md CHANGED
@@ -1,45 +1,7 @@
1
- # Gemini Playground 💬
2
-
3
- ## Overview
4
-
5
- Gemini Playground is an interactive Python application that leverages Google Generative AI and Gradio to provide a platform for experimenting with Gemini Pro and Gemini Pro Vision models. Users can engage in dynamic conversations with the chatbot, utilizing text and image prompts to generate creative and context-aware responses.
6
-
7
- ![img](https://github.com/arham-kk/gemini-demo/assets/108623726/d88a8c82-4fcc-45fd-aea3-4a6a88787200)
8
-
9
- ## Prerequisites
10
-
11
- Before running the code, ensure you have the necessary dependencies installed. You can install them using the following command:
12
-
13
- ```bash
14
- pip install -r requirements.txt
15
- ```
16
-
17
- Make sure to obtain your own Google API key by visiting [GOOGLE API KEY](https://makersuite.google.com/app/apikey) and follow the instructions.
18
-
19
- ## Usage
20
-
21
- 1. Set up your Google API key by entering it in the `GOOGLE API KEY` textbox.
22
- 2. Optionally provide an image prompt to explore the capabilities of Gemini Pro Vision.
23
- 3. Input your text prompt in the `Ask me anything and press Enter` textbox.
24
- 4. Adjust various parameters such as temperature, token limit, stop sequences, top-K, and top-P to tailor the model's behavior.
25
- 5. Click the "Run" button to initiate the conversation.
26
-
27
- ## Features
28
-
29
- - **Gemini Pro and Gemini Pro Vision**: Choose between text-only (Gemini Pro) or text and image prompts (Gemini Pro Vision).
30
- - **Interactive Chat Interface**: Engage in dynamic conversations with the chatbot using Gradio's intuitive chat interface.
31
- - **Flexible Parameter Adjustment**: Fine-tune model behavior with adjustable parameters like temperature, token limit, and more.
32
-
33
- ## Parameters
34
-
35
- - **GOOGLE API KEY**: Your personal Google API key for accessing the Generative AI models.
36
- - **Image**: Optional image prompt for Gemini Pro Vision.
37
- - **Temperature**: Controls the randomness of the generated content. Higher values lead to more creative responses.
38
- - **Token Limit**: Limit the length of the generated content in tokens.
39
- - **Stop Sequences**: Specify stop sequences to control the generation process.
40
- - **Top-K**: Control the diversity of the output by selecting from the top-K most likely tokens.
41
- - **Top-P**: Control the diversity of the output by selecting tokens with cumulative probabilities up to the top-P threshold.
42
-
43
- ## Important Note
44
-
45
- Ensure you a valid Google API key to use the Gemini Pro and Gemini Pro Vision models.
 
1
+ colorFrom: yellow
2
+ colorTo: purple
3
+ sdk: gradio
4
+ sdk_version: 5.12.0
5
+ app_file: app.py
6
+ pinned: false
7
+ license: apache-2.0