Building AI with MongoDB: Putting Jina AI’s Breakthrough Open Source Embedding Model To Work

Mat Keep
February 14, 2024 | Updated: February 21, 2024
#genAI#Vector Search

Founded in 2020 and based in Berlin, Germany, Jina AI has swiftly risen as a leader in multimodal AI, focusing on prompt engineering and embedding models. With its commitment to open-source and open research, Jina AI is bridging the gap between advanced AI theory and the real world AI-powered applications being built by developers and data scientists. Over 400,000 users are registered to use the Jina AI platform.

Dr. Han Xiao, Founder and CEO at Jina AI, describes the company’s mission:

“We envision paving the way towards the future of AI as a multimodal reality. We recognize that the existing machine learning and software ecosystems face challenges in handling multimodal AI. As a response, we're committed to developing pioneering tools and platforms that assist businesses and developers in navigating these complexities. Our vision is to play a crucial role in helping the world harness the vast potential of multimodal AI and truly revolutionize the way we interpret and interact with information."

Jina AI’s work in embedding models has caught significant industry interest. As many developers now know, embeddings are essential to generative AI (gen AI). Embedding models are sophisticated algorithms that transform and embed data of any structure into multi-dimensional numerical encodings called vectors. These vectors give data semantic meaning by capturing its patterns and relationships. This means we can analyze and search for unstructured data in the same way we’ve always been able to with structured business data. Considering that over 80% of the data we create every day is unstructured, we start to appreciate how transformational embeddings — when combined with a powerful solution such as MongoDB Atlas Vector Search — are for gen AI.

Check out our AI resource page to learn more about building AI-powered apps with MongoDB.

Jina AI's jina-embeddings-v2 is the first open-source 8K text embedding model. Its 8K token length provides deeper context comprehension, significantly enhancing accuracy and relevance for tasks like retrieval-augmented generation (RAG) and semantic search. Jina AI’s embeddings offer enhanced data indexing and search capabilities, along with bilingual support. The embedding models are focused on singular languages and language pairs, ensuring state-of-the-art performance on language-specific benchmarks. Currently, Jina Embeddings v2 includes bilingual German-English and Chinese-English models, with other bilingual models in the works.

Jina AI’s embedding models excel in classification, reranking, retrieval, and summarization, making them suitable for diverse applications, especially those that are cross-lingual. Recent examples from multinational enterprise customers include the automation of sales sequences, skills matching in HR applications, and payment reconciliation with fraud detection.

Figure 1:  Jina AI’s world-class embedding models improve search and RAG systems.

In our recently published Jina Embeddings v2 and MongoDB Atlas article we show developers how to get started in bringing vector embeddings into their apps. The article covers:

  1. Creating a MongoDB Atlas instance and loading it with your data. (The article uses a sample Airbnb reviews data set.)

  2. Creating embeddings for the data set using the Jina Embeddings API.

  3. Storing and indexing the embeddings with Atlas Vector Search.

  4. Implementing semantic search using the embeddings.

Dr. Xiao says, “Our Embedding API is natively integrated with key technologies within the gen AI developer stack including MongoDB Atlas, LangChain, LlamaIndex, Dify, and Haystack. MongoDB Atlas unifies application data and vector embeddings in a single platform, keeping both fully synced. Atlas Triggers keeps embeddings fresh by calling our Embeddings API whenever data is inserted or updated in the database. This integrated approach makes developers more productive as they build new, cutting-edge AI-powered apps for the business.”

To get started with MongoDB and Jina AI, register for MongoDB Atlas and read the tutorial. If your team is building its AI apps, sign up for the AI Innovators Program. Successful companies get access to free Atlas credits and technical enablement, as well as connections into the broader AI ecosystem.

← Previous

Safety Champion Builds the Future of Safety Management on MongoDB Atlas, with genAI in Sight

Safety Champion was born in Australia in 2015, out of an RMIT university project aiming to disrupt the safety management industry, still heavily reliant on paper-based processes and lagging in terms of digitisation, and bring it to the cloud. Most companies today need to comply with strict workplace safety policies. This is true for industries reliant on manual workers, such as manufacturing, transport and logistics, construction, and healthcare, but also for companies dealing with digital workers, both working in the office or remotely. To do this, organisations rely on safety management processes and systems that help them comply with government and industry-led regulations, as well as keep their employees safe. Whether it’s legal obligations about safety reporting, management of employees and contractors, or ways to implement company-wide safety programs, Safety Champion’s digital platform provides customers more visibility and tracking over safety programs, and a wealth of data to help make evidence-based safety decisions. "Data is core to our offering, as well as core to how next-generation safety programs are being designed and implemented. With paper-based processes, you simply can’t get access to rich data, connect data sets easily, or uncover organisation-wide insights and patterns that can help drive efficiencies and improve safety outcomes," explains Craig Salter, Founder of Safety Champion. MongoDB Atlas: Unlocking the power of data and analytics to improve safety outcomes for customers Safety Champion started using the self-managed version of MongoDB, and shortly after that in 2017 moved onto MongoDB Atlas which was more cost-effective, meant less overhead and not having to manage the day-to-day tasks required to keep a database up and running. The main challenge is that industry standards and policies around safety vary significantly for every company - the safety risks of an office-based business of digital workers are widely different from the risks workers on a manufacturing plant are exposed to, making data collection and itemisation for deeper insights very complex. MongoDB’s document model, its flexibility, and its ability to handle complex sets of data combined with Atlas’ ease of use for developers made it the perfect fit for Safety Champion. "It was very easy to get started on MongoDB, but also super easy and quick to get applications developed and brought to market," says Sid Jain, Solution Architect for Safety Champion. "The performance optimisation we saw using MongoDB Atlas was significant, and it freed up a lot of time from our developers so they could focus on what matters most to our business, instead of worrying about things like patching, setting up alerts, handling back-ups, and so on." The use of MongoDB Charts also gives Safety Champions’ customers access to important analytics that can be presented in visual forms, fitting very specific use cases and internal audiences. This helps organisations using Safety Champion improve decision-making by presenting very concrete data and graphs that can fuel evidence-based safety decisions. "MongoDB Atlas helps drive efficiencies for our clients, but it also helps safety and operations managers to have a voice in making important safety decisions because they are backed by strong data-led evidence. Connecting data sets means the ability to have a much deeper, richer view of what’s happening and what needs to be done," says Salter. Managing exponential growth: 2024, the year of scaling up, generative AI, Search, and much more Before 2020, Safety Champions was still a small start-up, with its platform managing about 5,000 documents a month - these include incident records, checklists, inspection reports, actionable tasks, task completion reports, and more. The COVID pandemic forced organisations to move their safety processes online and comply with a whole new set of safety measures and policies, which saw the company’s business explode: triple-digit annual growth between 2021 and 2023, a dev team that tripled in size, over 2,000 customers, and now up to 100,000 documents handled per month. "As our company kept growing, with some of our new customers handling tens of thousands of safety documents every month - we knew we needed to enable even more scale and future proof ourselves for the next years to come," explains Salter. "We also knew that if we wanted to take advantage of MongoDB’s capabilities in generative AI, search, multi-region, and more, which a lot of our customers were asking for, we needed to set some strong data foundations." Safety Champion is now in the process of upgrading to MongoDB 6.0, which will offer its clients more speed, especially when handling larger and more complex queries. MongoDB Search is now also available system-wide, allowing search queries to be performed across all the modules a client has added records for. "Since many modules allow linking records to each other, allowing a single search query to find and return records from multiple modules makes a world of difference. Developers no longer have to maintain other data systems and the extraction, transformation, and sync of data between MongoDB and search index happens seamlessly, greatly reducing the Ops burden on dev teams," explains Jain. The use of multi-region functionalities within MongoDB Atlas means customers, especially global ones operating in multiple geographic regions, will be able to segregate data and ensure they meet regulatory requirements around data hosting and security. Lastly, Safety Champion is exploring the potential of generative AI with plans to start using MongoDB Vector Search , later in 2024. Some of the use cases the company is already investigating include semantic insights, understanding textual data that employees enter in forms, applying LLMs to that data, and extracting helpful information from it. "Every client wants more analytics, more insights, and more high-level meaning out of data. It’s not just about making it easier to enter data and seeing safety incidents, it’s about what it means and decisions that can be made from a safety perspective," says Salter. "The new version of the Safety Champion platform powered by MongoDB Atlas means we are fully ready to dive into the next phase of our evolution as a business and offer features such as generative AI which will take both Safety Champions and our customers to the next era of safety management."

February 14, 2024
Next →

Hanabi Technologies Uses MongoDB to Power AI Assistant, Hana

For all the hype surrounding generative AI, cynics tend to view the few real-world implementations as little more than “fancy chatbots.” But for Abhinav Aggarwal, CEO of Hanabi Technologies, the idea of a generative AI-powered bot that is more than just an assistant was intriguing. “I’d been using ChatGPT since it launched,” said Aggarwal. “That got me thinking: How could we make a chatbot that was like a team member?” And with that concept, Hana was born. The problem with bots “Most generative AI chatbots do not act like people; they wait for a command and give a response,” said Aggarwal. “We wanted to create a human-like chatbot that would proactively help people based on what they wanted—automating reminders, for example, or fetching time zones from your calendar to correctly schedule meetings.” Hanabi’s flagship product, Hana, is an AI assistant designed to enhance team collaboration within Google Chat, working in concert with Google Workspace and its suite of products. “Our target customers are smaller companies of between 10 and 50 people. At this size you’re not going to build your own agent from scratch,” he said. Hana integrates with Google APIs to deliver a human-like assistant that chimes in with helpful interventions, such as automatically setting reminders and making sure meetings are booked in the right time zone for each participant. “Hana is designed to bring AI to smaller companies and help them collaborate in a space where they are already working—Google Workspace,” Aggarwal explained. The MongoDB Atlas solution For Hana to act like a member of the team, Hanabi needed to process massive amounts of data to support advanced features like retrieval-augmented generation (RAG) for better information retrieval across Google Docs and many other sources. And with a rapidly growing user base of over 600 organizations and 17,000+ installs, Hanabi also required a secure, scalable, and high-performing data storage solution. MongoDB Atlas provided a flexible document model, built-in vector database, and scalable cloud-based infrastructure, freeing Hanabi engineers to build new features for Hana rather than focusing on rote tasks like data extract, transform, and load processes or manual scaling and provisioning. Now, MongoDB Atlas handles a variety of responsibilities: Scalability and security: MongoDB Atlas’s auto-scaling and automatic backup features have enabled Hanabi to seamlessly grow its user base without the need for manual database management. RAG: MongoDB Atlas plays a critical role in Hana’s RAG functionality. The platform enables Hanabi to split Google Docs into small sections, create embeddings, and store these sections in Atlas’s vector database. Development Processes: According to Aggarwal, MongoDB’s flexibility in managing changing schemas has been essential to the company’s fast-paced development cycle. Data Visualization: Using MongoDB Atlas Charts has enabled Hanabi to create comprehensive dashboards for real-time data visualization. This has helped the team track usage, set reminders, and optimize performance without needing to build a manual dashboard. Impact and results With MongoDB Atlas, Hanabi can successfully scale Hana to meet the demands of its rapidly expanding user base. The integration is also enabling Hana to offer powerful features like automatic interactions with customers, advanced information retrieval from Google Docs, and manually added memory snippets, making it an essential tool for teams around the world. Next steps Hanabi plans to continue integrating more tools into Hana while expanding its reach to personal Gmail users. The company is also rolling out a new automatic-interaction feature, further enhancing Hana’s ability to proactively assist users without direct commands. MongoDB Atlas remains a key component of Hanabi’s stack, alongside Google Kubernetes Engine, NestJS, and LangChain, enabling Hanabi to focus on innovating to improve the customer experience. Tech Stack MongoDB Atlas Google Kubernetes Engine NestJS LangChain Are you building AI apps? Join the MongoDB AI Innovators Program today! Successful participants gain access to free MongoDB Atlas credits, technical enablement, and invaluable connections within the broader AI ecosystem. If your company is interested in being featured, we’d love to hear from you. Connect with us at ai_adopters@mongodb.com.

November 21, 2024