AI / LLM Toolkit

== USE THE NEW FREE AND OPEN-SOURCE VERSION OF THIS PLUGIN (see marketplace) ==
The best way to build advanced AI/LLM apps!  With built-in response streaming, support for 100+ models, file uploads, web searches, vector storage, chat history management, and more!

Features:

🚫 NO More Waiting: Experience real-time streaming of responses, reminiscent of the official ChatGPT interface. Say goodbye to timeouts and prolonged waits!

💪 Support for 100+ Models: Including OpenAI, Anthropic/Claude, Llama, Mistral, Google Gemini, and more! Unlock unparalleled versatility and scalability for your applications!

🤖 Assistants API with Streaming: Create and use OpenAI Assistants in real-time by streaming your runs. Also supports all other functions of the API.

🧠 Enhanced Memory: Multi-turn conversations made easy with our intuitive message history. Perfect memory that just works.

🛠 Function Calling & API Execution: Supercharge your apps with custom ChatGPT plugins or integrate third-party data sources from APIs.

👁️‍🗨️ Multi-modal support (eg GPT-4o) Elevate your AI experience by integrating GPT-4o, enabling your applications to understand and interpret visual and auditory data alongside text, broadening the scope of interaction and functionality.

⏳ Token Monitoring: Keep an eye on your token consumption for every request you make.

✂ Automatic Truncation: Effortlessly manage messages without worrying about input length.

🛑 Stream Interruption: Regain control and steer the conversation when ChatGPT goes off-course.

🌐 Web Search Capabilities: Built-in web search enables you to extract relevant information from the web in real-time using Google search, or paste URLs/links directly for sites you are interested in.

📂 File Uploads: Seamlessly extract text from uploaded files (.pdf, .pptx, .docx, .csv, and many more types). It's easier than ever to add your own data sources to chats.

📌 Bubble-native Vector Storage & Search: Super-charge your app with "Retrieval Augmented Generation". Introducing Bubble-native embedding vector storage and search, so that you can search through your data without requiring Pinecone, Weaviate, or another third-party vector database service.

🔍 Enhanced Error Handling: With clearer and simpler mechanisms, we've made it easier to troubleshoot and navigate unexpected events.

📌 Custom Headers & bodies: For advanced users, you have full control over the payload and headers of your request.

⚙ Comprehensive API Parameters: Fine-tune your requests using all available parameters, including frequency penalty, presence penalty, and logit bias.

🏠 Custom endpoints Use Microsoft Azure deployments or other hosting providers.

🏠 Self-Hosting: Host your own backend server for complete control over your data.


===================================
   
💡 Endless Possibilities with ChatGPT:
Whether it's crafting chat UIs, answering questions, generating content, evaluating statements, or deep Chain-of-Thought reasoning, the potential uses for ChatGPT are vast and still being explored. Dive into this vast ocean and discover its limitless potentials!

===================================

EDITOR MODE - DEMO APP - RESOURCES

See the overiew page and features here:
🔗 https://chatgpt.launchable.ai/

Inspect sample setups and workflows here:
🔗 https://llm-toolkit-quickstart.bubbleapps.io/version-test

Find the complete documentation here:
🔗 https://launchable-ai.github.io/llm-toolkit-docs/

Watch video tutorials for more ideas and instructions:
🔗 https://chatgpt.launchable.ai/tutorials

Stay updated! For the latest news and updates, check out our discord server:
🔗 https://discord.com/invite/HfjhqcHfh3

To host your own server, head here:
🔗 https://github.com/Launchable-AI/llm-toolkit-backend


If you need help, please get in touch, at: https://launchable.ai/contact