🌍 The Solution uses a multilingual semantic model from COhere to 🚀 revolutionize the media and news industry in multilingual markets like India(We have used telugu , hindi ,bengali,English news dataset for this use case), allowing anyone to track 📰 regional news in real-time without the need for translation or understanding of other regional languages. 🙌

Semantic Search AI Hackathon

team phoeniks

Cohere

Indic News search engine

## Problem  1. AI coding assistants (Copilot, Cursor, Aider.chat) accelerate software development. 2. People typically code not by reading documentation but by asking Llama, ChatGPT, Claude, or other LLMs. 3. LLMs struggle to understand documentation as it requires reasoning. 4. New projects or updated documentation often get overshadowed by legacy code.  ## Solution  - To help LLMs comprehend new documentation, we need to generate a large number of usage examples.  ## How we do it  1. Download the documentation from the URL and clean it by removing menus, headers, footers, tables of contents, and other boilerplate. 2. Analyze the documentation to extract main ideas, tools, use cases, and target audiences. 3. Brainstorm relevant use cases. 4. Refine each use case. 5. Conduct a human review of the code. 6. Organize the validated use cases into a dataset or RAG system.  ## Tools we used  https://github.com/kirilligum/synth-dev  - **Restack**: To run, debug, log, and restart all steps of the pipeline. - **TogetherAI**: For LLM API and example usage. See: https://github.com/kirilligum/synth-dev/blob/main/streamlit_fastapi_togetherai_llama/src/functions/function.py - **Llama**: We used Llama 3.2 3b, breaking the pipeline into smaller steps to leverage a more cost-effective model. Scientific research shows that creating more data with smaller models is more efficient than using larger models. See: https://github.com/kirilligum/synth-dev/blob/main/streamlit_fastapi_togetherai_llama/src/functions/function.py - **LlamaIndex**: For LLM calls, prototyping, initial web crawling, and RAG. See: https://github.com/kirilligum/synth-dev/blob/main/streamlit_fastapi_togetherai_llama/src/functions/function.py

Helping LLMs understand developer documentation by creating hundreds of diversified use case coding examples for pre-training and RAG.

Synth Dev

Restack's Autonomous Intelligence Framework empowers teams to build, deploy, and scale AI systems, offering orchestration, real-time workflows, and adaptive capabilities.

Restack

LlamaIndex connects data sources to large language models, providing tools to ingest, index, and query data for building powerful AI apps augmented by your knowledge.

LlamaIndex

Discover the power of Together AI and empower AI innovation together!

Together AI

Llama 3.2 is Meta’s open-source AI model, optimized for edge devices with multimodal capabilities, enabling text and image processing for broader AI applications across platforms.

Llama 3.2

Meta is a US technology company that owns the social networks Facebook and Instagram, the instant messaging apps WhatsApp and Messenger, and the virtual reality device brand Meta Quest.

Code Crusiade

Cutting-edge AI language model with unparalleled performance and innovative features.

Llama 3

Clear Bureau - AI for Accessible Government

Just like computers store data to process, our brains work by storing memories. As humans, everything that we see, feel, sense, everything that happens - gets stored as memories. We might get attached to some memories more than others, that might be good, bad or affecting us in some ways. We have created Revisit - which is a personal therapy app that helps to heals memories using text, images, audio, video and is personalized assistant to users. We have used Llama, Open AI, Aria and Allegro to integrate features that help users to type their memory as text inputs and help them to heal their memories.

Just like computers store data to process, our brains work by storing memories. As humans, everything that we see, feel, sense, everything that happens - gets stored as memories. 

Revisit

OpenAI is an AI research and deployment company

OpenAI

Rhymes.ai is a multimodal AI platform that integrates text, images, and video into seamless outputs. With innovations like Aria and Allegro, it empowers users to build advanced, efficient AI applications.

Rhymes.ai

Revisit - Personal Therapy App

Creating a custom RAG (Retrieve and Generate) pipeline without any coding is now accessible to users and beginners through intuitive no-code platforms. Start by selecting a user-friendly tool like Microsoft Power Automate, Zapier, or specialized AI platforms such as LangChain’s no-code solutions. These platforms offer drag-and-drop interfaces where you can easily configure data sources for retrieval, such as databases, APIs, or cloud storage. Next, integrate AI models for the generation phase by selecting from pre-built templates or connecting to services like OpenAI. Customize the workflow by setting parameters, defining triggers, and establishing how retrieved information is used to generate responses. Additionally, leverage built-in analytics and testing features to refine your pipeline. No-code RAG pipelines empower users to efficiently build robust, tailored solutions for tasks like customer support, content creation, and data analysis without needing programming expertise. This approach accelerates deployment, reduces errors, and allows for easy adjustments, making advanced AI capabilities accessible to everyone.








Helps user and beginner to generate custom rag pipline without any code

Medworks

Llama 3.1 is an open-source, state-of-the-art large language model (LLM) by Meta AI. It’s optimized for advanced NLP tasks, offering various model sizes, and focuses on transparency, safety, and accessibility.

Llama 3.1

Snowflake is a top cloud data platform, enabling seamless data storage, analysis, and sharing across clouds, serving diverse sectors with real-time insights.

Snowflake

Rag Custom Pipiline Generator

AlphaBeam is a multilingual platform for Conversational Business intelligence, that redefines data interaction by seamlessly helping business users to explore their data without having to rely on their tech teams every time. While traditional BI tools have empowered data exploration through dashboards and reports, they often cater to a specialized audience, requiring technical expertise and leaving out crucial stakeholders. This results in missed insights, delayed decisions, and a limited understanding of their data's true potential.

To address this shortcoming in fostering a truly interactive and user-centric experience for non-technical users, AlphaBeam seamlessly blends conversational capabilities with advanced analytics, creating a symbiotic relationship between business users and their data. It also fosters business interaction in local African languages, to capture cultural contexts.

At a glance, AlphaBeam is a data-agnostic solution to ingest data from different sources, a semantic layer which translates raw data into business vocabularies and user queries into precise metrics and visualisations, a conversational interface for ad-hoc analysis and AI-powered insights through Llama 3.2 in 50+ African languages, and a visualisation layer which transforms the retrieved data into compelling dashboards. These capabilities empower users to carry out the following:

- Conversational Inquiries: Business users can ask questions about already existing dashboards in English or 50+ African languages, just as they would converse with a colleague. They could dig deeper into the data behind the visualisations, gaining a comprehensive understanding of the data.

- Comprehensive Metric Exploration: Engage in a conversational dialogue to uncover insights about any metric or data point. 

- Decision Making at the Speed of Data: Through conversational querying, AlphaBeam empowers users to make informed decisions very quickly based on readily available insights.

Multilingual conversational business intelligence in 50+ African languages

AlphaBeam

Chroma is an AI-native open-source embedding database. The fastest way to build Python or JavaScript LLM apps with memory

Chroma

Unleash the potential of Streamlit for rapid deployment of data applications.