Projects

Dynamic agent which modifies the plan of execution on the fly. Inspired by BabyAGI and Plan-and-Execute agents. What is it? Based on Plan-and-execute type agents, but capable of more complex tasks as it can think and update the plan based on new information after performing an action. It is built from scratch to have better control and expandability over the implementation. The key added capability is iterative thinking and replanning after each action, facilitates longer execution sequences and potentially hierarchical tasks where sequential processing fails as the main task is split into multiple sub-tasks which should be processed before reaching the next step....

Built an end-to-end web application using, ChromaDB Langchain Streamlit Transformers AWS S3 Summary It can handle multiple input types, use various large language models (LLMs) locally or via an API, supports multiple speech-to-text models, etc. It has three main components built with Python, the UI, the Middleware service and the LLM Service. The Middleware service is responsible for interacting with 3rd party services like Deepgram, AWS, etc., and passes relevant data to the LLM service....

Easy to use, configurable CLI application to test connectivity, view data/configuration in Redis built with Go. Features: -data: Prints all the existing data on Redis. -config: Prints all the current Redis config. -configWithPattern: Prints the config which matches the specified pattern. -testReadWrite: Tests the Redis connection by setting and deleting sample data based on the -count flag. -insertSampleData: Inserts sample data into Redis based on the -count flag. -deleteAllData: Deletes all existing data in the Redis instance....

MonkeyLang is a programming language specification that can be implemented in any language such as Go, Java or Rust. It has features like, C-based syntax, datatypes, built-in functions, closures, etc. Here is what Monkey looks like: // Integers & arithmetic expressions... let version = 1 + (50 / 2) - (8 * 3); // ... and strings let name = "The Monkey programming language"; // ... booleans let isMonkeyFastNow = true; // ....

Built a Chatbot framework with, Google’s DialogFlow (NLU) Telegram Bot API (Frontend) Go/go-fiber (API middleware) Firebase Firestore (Database and logging) Developed based on Hexagonal Architectural Pattern also known as, the ports and adapters architecture. Implemented features like, quick replies that can be configured in the DialogFlow response itself. Your browser does not support the video tag. Source repository: snehalyelmati/chatbot-framework-golang