1. AI-Horizon’s Pre-built Agents

Chat Agent: Cutting-edge chatbots featuring both short-term and long-term memory capabilities, RLHF (Reinforced Learning Human Feedback), a customizable system prompt, and smooth transitions between different Large Language Models (LLMs). Knowledge Search: Introduce perplexity-style document and data search to your organization with AI-Horizon. AI-Horizon's document search capability can efficiently manage over 100,000 documents, ensuring precise information retrieval on every occasion. Additionally, you receive source citations and the option to retrieve the source file. RAG Powered Apps: This is likely the most extensive RAG agent ever constructed. Simply by adjusting the parameters, you can select from up to 600 plus distinct RAG pipelines. Furthermore, you have the flexibility to integrate with any LLM, vector store, embedding model, reranker, or parser according to your preferences. Q&A Bot: A simplified edition of AI-Horizon Chatbot, serving as a precise question-answering agent for empowering your help and FAQs section. Q&A Bots are also ideally suited for managing one-way conversations such as employee handbook searches, legal reference inquiries, and more. Data Analysis: Develop a conversational analytics application for your data using AI_Horizon's Data Analysis agent in a Pythonic manner. The text query transforms into Python code, executing on a pandas dataframe and leveraging multiple ML libraries like Scikit-Learn, StatsModel, etc. This aids in conducting diverse analyses on your data, encompassing regression, correlation, clustering, time series, and much more. Text-to-SQL: Wish to conduct an exploratory analysis on your database? Utilize AI-Horizon's Text-to-SQL agent to translate your text queries into SQL code capable of managing intricate joins, extracting information, and crafting insights and recommendations.

2. AI-Horizon Automaton: Multi-Agent automation platform

AI-Horizon Automaton stands as an advanced multi-agent automation framework engineered for simplicity, emphasizing workflow efficiency and efficacy. It facilitates the generation of numerous agents assigned to distinct tasks. These agents and tasks operate autonomously, executing provided instructions until reaching a stable state.

How to Use

All it takes is a handful of lines of code to construct and deploy your agents. Let's check an example.

1. Install the AI-Horizon library and set the Open AI API key.

   npm install <<package_name>>
   export OPENAI_API_KEY="sk-"

2. Import the necessary agent module. Here we are choosing ChatBot module.

   from <<package_name>> import ChatBot

3. Enable the chatbot with only a single line of code. The RAG pipeline operates seamlessly in the background.

    my_chatbot = ChatBot.pdf_chat(input_files=["pdf_file_path"])

4. That’s it. Just query and start chatting with your chatbot.

    response = my_chatbot.chat("Your query here")