Aman Chadha’s Post

Accelerate MongoDB Apps to Drive 100x Faster Analytics and AI https://lnkd.in/g2jSC-TP Hands-on workshop for developers and AI professionals, on state-of-the-art technology. Recording and GitHub material will be available to registrants who cannot attend the free 60-min session. Includes demo on how to utilize both SQL & NoSQL to power fast analytics for your MongoDB applications, with native support for vector functions and fast semantic search on JSON using simple SQL queries. Also very fast in real-time. #vectorDB #mongoDB #semanticsearch

LLMs are trained to a past date. They are unaware of the enterprise's internal data, documents, current affairs etc. LLMs also hallucinate (make up believable answers that are not facts). Does that mean LLMs are not useful to enterprise use cases? Fortunately, the RAG (Retrieval-Augmented Generation) framework enables you to retrieve the relevant data for a given prompt from your dataset, augment that as a context in your prompt to LLM and finally generate responses that are more accurate, less prone to hallucination and relevant to enterprise use cases. Langchain is one such popular framework to quickly set up RAG for your use case. I have personally tried and found it very easy to create an RAG application with very nominal effort. For retrieval, you would need to clean, split your data/documents and then embed using an embedding model (I tried OpenAI and llama2) and finally index your data in a vector database of your choice (I tried FAISS and Weaviate). These vector databases give functionality to find semantically matching chunks for a given embedded query. Given the increasing popularity of vector databases, legacy popular databases like Mongo and Postgres (with a plugin) have also started supporting vector search. Interestingly a lot of new companies started offering new Vector DB solutions. This reminds me of the quote "During a gold rush, sell shovels" 😊 #AI #LLM #RAG #Langchain #VectorDB #MongoDB #Postgres #OpenAI #llama2

🚀 PostgreSQL: The Future of Databases! 🚀 PostgreSQL has always been a powerhouse for handling relational data, but its capabilities have reached new heights with cutting-edge extensions like Apache AGE and pgvector. 🌐✨ Imagine this: a single database platform that seamlessly integrates both graph-based queries AND vector embeddings for AI and machine learning applications. The possibilities are endless! Here's what you can do with this dynamic duo: 1️⃣ Apache AGE transforms PostgreSQL into a graph database, making it perfect for handling complex relationships and networks, like: Social networks 🧑🤝🧑 Supply chain management 📦 Fraud detection 🔍 2️⃣ pgvector brings AI into the mix by enabling vector similarity searches directly inside PostgreSQL. This is a game-changer for: Semantic search: retrieving the most contextually relevant content Recommendation systems: using embeddings to suggest the best matches Image and document retrieval: finding similar content using deep learning models 📸📄 💡 When you combine graph capabilities from Apache AGE with the power of pgvector, you're looking at a robust system that can handle AI-driven insights and complex data relationships—all within PostgreSQL! No need to jump between multiple platforms. PostgreSQL has become a one-stop shop for modern applications, with the scalability and flexibility to drive AI innovations. 🚀 Are you ready to supercharge your data and AI workflows? PostgreSQL with Apache AGE and pgvector could be the key to unlocking your next breakthrough! 🔓✨ #PostgreSQL #ApacheAGE #pgvector #AI #MachineLearning #GraphDatabase #Innovation #DataScience #TechTrends #AIRevolution #DataInnovation

PostgreSQL developers can seamlessly integrate Anthropic's Claude models, including the powerful Sonnet 3.5, directly into their databases using pgai. This open-source extension simplifies tasks like embeddings and data reasoning within PostgreSQL, offering access to a range of Claude models to suit different AI needs. With Claude’s contextual understanding, speed, and cost-effectiveness, developers can enhance their AI workflows without external infrastructure. Learn more 👉 https://lnkd.in/gAkV5A5m Ready to get started? Head over to the pgai GitHub repo 👉 https://lnkd.in/gijeVw8T 👉 #AI #PostgreSQL #pgAI #Anthropic

MongoDB Atlas Vector Search MongoDB Atlas Vector Search allows you to perform semantic similarity searches on your data, which can be integrated with LLMs to build AI-powered applications. Data from various sources and in different formats can be represented numerically as vector embeddings. Atlas Vector Search allows you to store vector embeddings alongside your source data and metadata, leveraging the power of the document model. These vector embeddings can then be queried using an aggregation pipeline to perform fast semantic similarity search on the data, using an approximate nearest neighbors algorithm. With the help of MongoDB Atlas Search’s Vector Search feature, developers can store dense vectors that are organised according to certain algorithms (like KNN) and use an engine to calculate related vectors (like euclidean distance) to determine relevance scores.

#DailyLearning-November [Day 4/20]#20DaysOfLearningChallenge 🗓 **Today's Focus:** Sliding Window Problems & MongoDB Aggregations  💡 **What I Learned Today:**   1. **Sliding Window Technique**:     I solved five problems using the sliding window technique, focusing on optimizing subarray operations and string manipulation:     - [Longest K Unique Characters Substring](https://lnkd.in/gj8yUacW)     - [Minimum Window Substring](https://lnkd.in/g-EYU544)     - [Fruit Into Baskets](https://lnkd.in/g7xBPuuq)     - [Longest Substring Without Repeating Characters](https://lnkd.in/gYpbRtP4)     - [Substrings of Size Three With Distinct Characters](https://lnkd.in/gxsVs6RK)  2. **MongoDB Aggregations**:     Explored aggregation concepts using **Masai Prepleaf** resources.     - **Aggregation - 1**: Basics of grouping, filtering, and projecting data.     - **Aggregation - 2**: Advanced operations like `$group`, `$lookup`, and `$unwind`, enhancing my ability to query and analyze complex datasets efficiently.  🚀 **How I Applied It:**   - Practiced solving problems requiring efficient window management and string operations to improve my algorithmic thinking.   - Worked on MongoDB aggregation pipelines, applying what I learned to analyse structured and unstructured data.  📈 **Next Steps:**   Tomorrow, I’ll dive deeper into MongoDB queries and explore advanced Express concepts like middleware chaining.  🔗 **Resources Used:**   - [Masai Prepleaf](https://www.prepleaf.com)   - GeeksforGeeks   - LeetCode  🔗 You can check my work at : https://lnkd.in/dTx6v-6a https://lnkd.in/gBi4h7CE #Masai #Prepleaf #DailyLearning #SlidingWindow #MongoDB #ProblemSolving #CodingSkills #WebDevelopment  Masai Prepleaf by Masai

🟢 Do you work with large datasets and complex queries involving similarity searches for your PostgreSQL database? pgvector might be the missing link required for enhancing your application’s capabilities with AI. Join Semab Tariq, our in-house PostgreSQL Database Developer, on 8 May 2024 for an information-packed session on “pgvector: How to transform your search capabilities with AI”. We will share everything you need to maximize the performance of your queries and lots more. 📅 May 8, 2024 | 3:00 PM GMT ▶ Make sure you have saved your spot: https://hubs.ly/Q02tTz790 ... #PostgreSQL #OpenSource #Database #pgvector #AI #artificialintelligence

Exciting news! Just wrapped up an immersive Session with Learnbay , mastering the art of SQL and MongoDB. Here are some key takeaways from each module: SQL: Mastered the art of structured querying, enabling me to retrieve and analyze data efficiently. From basic commands to complex queries, I'm now adept at navigating and extracting insights from databases seamlessly. MongoDB: Explored the dynamic realm of NoSQL databases, gaining proficiency in managing unstructured data. The flexibility and scalability of MongoDB have opened up new possibilities for handling diverse data types and structures with finesse. #Learnbay #DataScience #AI

𝗪𝗵𝗮𝘁 𝗸𝗶𝗻𝗱 𝗼𝗳 𝗔𝗜 𝗮𝗽𝗽𝘀 𝗰𝗮𝗻 𝘆𝗼𝘂 𝗯𝘂𝗶𝗹𝗱 𝘄𝗶𝘁𝗵 𝗣𝗼𝘀𝘁𝗴𝗿𝗲𝗦𝗤𝗟? 🐘 🤖 Now everyday application developers with no specialized AI/ML background can build AI apps with PostgreSQL. Thanks to its robust relational foundation and ecosystem of extensions like pgvector, pgvectorscale, and pgai, PostgreSQL is all you need to build a state of the art AI application. Just like the timescaledb extension turned Postgres into a time series database, now the pgvectorscale and pgai extensions have turned Postgres into a vector database. Here are some AI systems you can build using PostgreSQL, with resources to learn more: ➡️ RAG: https://lnkd.in/gg-T6MQ7 ➡️ Search: https://lnkd.in/gY5KYnaY ➡️ Agents: https://lnkd.in/g6nGsY9n ➡️ Text to SQL: https://lnkd.in/grJtr_9c ➡️ Recommendation Systems: https://lnkd.in/gvpN_dzc No wonder PostgreSQL is catching fire as the default database choice for AI applications! That’s something covered in detail in our recent webinar: https://lu.ma/0v7nwfxd #PostgreSQL #Timescale #ArtificialIntelligence #AI #Vectors #LLM #RAG #SQL #Postgres #SQL 

How to Choose the Right Chunking Strategy for Your LLM Application by Apoorva Joshi MongoDB In Part 1 (https://lnkd.in/eQdfZu8Y) of this series on Retrieval Augmented Generation (RAG), we looked into choosing the right embedding model for your RAG application. While the choice of embedding model is an important consideration to ensure good quality retrieval for RAG, there is one key decision to be made before the embedding stage that can have a significant downstream impact — choosing the right chunking strategy for your data. In this tutorial, we will cover the following: What is chunking and why is it important for RAG? Choosing the right chunking strategy for your RAG application Evaluating different chunking methodologies on a dataset