Building an Interactive Manhattan Guide with Chatbot Demo Builder

Question: Know any good spots?

Response: Based on the context provided, I can recommend a few good pizza spots in Manhattan:

• Joe's Pizza (7 Carmine St) - This is described as "one of the most beloved slice joints in the city" with a "thin, crispy crust and always fresh" pizza, perfect for a quick bite.

• Prince Street Pizza (27 Prince St) - Known for its "thick, square pepperoni slice with those crispy-edged 'roni cups."

• $1 Pizza Slices - The context mentions that $1 pizza slices can still be found, especially around 6th Ave and 8th St in Greenwich Village. This is described as a "quintessential NYC food experience."

That's from a conversation with a chatbot we built in about 10 minutes. There was no coding, no database setup-just a PDF and the Chatbot Demo Builder tool. What made the experience so valuable wasn't just getting a good response, but seeing exactly what was happening behind the scenes after submitting our question.

Meet Chatbot Demo Builder

Chatbot Demo Builder is the newest addition to the Atlas Search Playground. This no-code tool gives users an intuitive way to explore MongoDB's vector search capabilities by building interactive Q&A bots with sample data or their own uploads. Powered by MongoDB Atlas Vector Search and Voyage AI, the Builder automatically handles index creation, query generation, and embedding, removing the common setup barriers that often slow down RAG (retrieval-augmented generation) experimentation.

What makes the tool particularly powerful is its accessibility. Like all tools in the Atlas Search Playground, it runs entirely in your browser without requiring a MongoDB Atlas account, cluster, or collection. This means you can test ideas, iterate quickly, and share prototypes with teammates and stakeholders, all without spinning up additional infrastructure.

With MongoDB.local NYC coming up on September 17, we thought it was the perfect time to put the Chatbot Demo Builder through its paces. So we decided to create something practical: a Q&A chatbot to help visitors explore Manhattan.

‍ Building in the browser

The entire process happened without leaving our browser. We started by uploading our Manhattan travel guide PDF to the Chatbot Demo Builder. Next, we configured how the chatbot would process our content using the Data Settings modal. For our chunking strategy, we chose recursive chunking with 500-token chunks and 50-token overlap. This preserves paragraph flow while ensuring important information isn't split awkwardly across boundaries. For the embedding model, we selected voyage-3-large, which excels at general knowledge retrieval tasks.

Once configured, we hit "Create Embeddings" and watched as the Builder processed our guide into a demo document collection containing metadata, chunked text, and vector embeddings.

Figure 1. Data Settings modal used for chunking configuration and embedding model selection.

Testing like tourists

With embeddings generated, we started asking questions like curious visitors:

• "Where can I find a public restroom near Central Park?"

• "What are some good day trip ideas?"

• "What are some fun facts about New York City?"

Each query highlighted the Builder's most powerful feature: complete transparency. When we asked about pizza, we could see the exact vector search query that ran, which chunks scored highest, and how the LLM prompt was constructed. This visibility turned experimentation from guesswork into informed iteration. We could understand not just what answers we got, but also why we got them and how to improve them.

Figure 2. Vector search query and scored document results for the pizza recommendation question.

Optimizing for better results

Fine-tuning our retrieval settings produced even better outputs. The Builder made these optimizations easily accessible and provided insight into exactly how they would affect results. We started by modifying numCandidates, which controls how many potential matches the system initially examines before selecting the best results. The recommended setting is at least 20 times higher than the limit value, allowing more potential matches to be evaluated before selecting the best ones; this trades a bit of latency for significantly better recall.

For even higher precision, the Builder offers an exact nearest neighbor (ENN) search, which calculates distances to all indexed embeddings. While computationally intensive, it guarantees finding the exact nearest neighbors when accuracy is key. Since our Manhattan guide only had 25 documents, we could afford to use ENN without worrying about performance impact.

Figure 3. Retrieval settings panel for adjusting search parameters and enabling exact nearest neighbor search.

Sharing and takeaways

Once we were happy with the responses, it was easy to share our work. The Builder generated a snapshot link that let the entire team test the chatbot for themselves without any additional setup.

In just a few steps, we transformed a static travel PDF into a conversational guide for exploring Manhattan. Along the way, we saw how decisions about chunking strategies, embeddings, and retrieval settings directly affect answer quality. We also gained visibility into what was happening behind the scenes, giving us the insights we needed to optimize these decisions.

Figure 4. Output panel tabs displaying data source, vector index, search query, and prompt details

By the end, we had a chatbot capable of providing helpful local insights about Manhattan, from day trip ideas to restaurant recommendations, all while giving us complete visibility into how it generated its answers.

Beyond the big apple

Chatbot Demo Builder makes it easy to explore RAG techniques. Whether you're prototyping a customer support bot, building an internal knowledge assistant, or creating an interactive travel guide, Chatbot Demo Builder allows you to gain a clearer understanding of what works best for your AI use case.