dsdanielpark/Bard-APIArchived
Bard API
Bard-API is an asynchronous Python wrapper and client for interacting with Google Gemini. It functions as a stateful conversation manager and multimodal interface, allowing users to send text and image prompts to a language model and retrieve responses.
The library utilizes a cookie-based authentication system that extracts session tokens from local browser storage to authorize requests. To manage access and connectivity, it includes proxy-based request routing to bypass regional restrictions and avoid IP blocks.
The project covers capabilities for multimodal AI analysis and the maintenance of session history to enable continuous multi-turn dialogues. It also provides utilities for extracting image links from responses, converting text to speech, and automatically executing generated code snippets within a local environment.
Features
- Gemini Integrations - Provides a Python wrapper for programmatically interacting with Google Gemini and Bard.
- Asynchronous Clients - Provides a non-blocking asynchronous Python interface for sending prompts to large language models and retrieving responses.
- Multimodal Input Processing - Processes combined text and image prompts to perform visual analysis through generative AI.
- Conversation State Management - Maintains session history and context to enable continuous, stateful multi-turn dialogues with the AI model.
- Conversation State Persistence - Maintains session objects and conversation history to support continuous multi-turn dialogues.
- Session-Cookie Wrappers - Uses a wrapper to extract browser session cookies for authenticating AI service requests without official API keys.
- Multimodal Analysis Tools - Provides utilities for analyzing combined text and image inputs to generate detailed descriptions of visual content.
- Visual Content Analysis - Analyzes images via text prompts to generate detailed descriptions of visual content.
- Stateful Session Management - Maintains conversation history and context within persistent objects to enable continuous dialogue.
- AI Prompt Sending APIs - Provides programmatic APIs to send text prompts to language models and retrieve structured responses.
- Browser Session Authentication - Uses extracted browser cookies to authenticate requests to AI services without official API keys.
- Browser Cookie Imports - Automatically retrieves session cookies from local browser storage to authorize API requests.
- Session Token Injection - Authenticates requests by extracting and using session tokens from local browser storage.
- API Wrapping - Wraps internal web service endpoints into a Python library to programmatically retrieve model responses.
- AI Content Workflow Automation - Integrates LLMs into scripts to automate code execution and text-to-speech synthesis.
- Code Execution Environments - Provides a mechanism to execute AI-generated code snippets within the local environment to produce results.
- Conversational Bot Development - Facilitates building chatbots that maintain stateful session history and context for multi-turn dialogues.
- Multimodal AI Toolkits - Ships a toolkit for performing integrated analysis of text and image data via generative AI services.
- Code Snippet Execution - Automatically runs code snippets received in AI responses within the local environment.
- Proxy Routing - Implements logic to route API requests through external proxy servers to bypass regional restrictions and IP blocks.
- External Proxy Forwarding - Forwards network traffic through external proxy servers to bypass regional restrictions and IP blocks.
- Asynchronous Request Execution - Implements a non-blocking asynchronous execution model for handling multiple network requests.
Star history
How this analysis was created: This summary and feature list were written by an AI model that read the project's README and public documentation pages. Each feature links to the documentation it came from; stars, license and language come straight from the GitHub API. The model does not read the source code, and the analysis is refreshed when the project is re-analysed. Learn more on our About page.
