AI has long since stopped being just about chatting. The real power emerges when an AI model understands and can retrieve your own knowledge, documents, manuals, emails, or project information. That's where embeddings come in.

Gemini Embedding 2: Give Your FileMaker Solution an AI Memory

AI is no longer just about chatting. The real power emerges when an AI model understands and can retrieve your own knowledge, documents, manuals, emails, or project information. That's where embeddings come in.

With the introduction of Gemini Embedding 2, Google has made one of the most powerful embedding models available today. But what exactly are embeddings, why are they important, and how can you use them within a FileMaker solution?

What are embeddings?

An embedding can be thought of as a numerical representation of text.

When you run a document, manual, or email through an embedding model, it gets converted into a long list of numbers (a vector). Those numbers don't represent the exact words, but rather the meaning of the text.

This allows two texts with the same meaning to be positioned close to each other in what's called vector space, even if completely different words are used.

Example

Document

How do I create an invoice in FileMaker?

User question

In what way can I generate a new bill?

To a traditional search engine, these look like two different texts. To an embedding model, they're virtually identical.

That makes semantic search possible.

Why Gemini Embedding 2?

Google developed Gemini Embedding 2 as the successor to earlier embedding models.

Key advantages include:

Higher accuracy in semantic search
Strong performance on business documents
Support for multiple languages
Suitable for large knowledge bases
Lower costs than repeatedly sending complete documents to a Large Language Model
Fast processing of large amounts of data

For organizations wanting to combine AI with their own knowledge, this is an important building block.

How does it work?

The process consists of four steps.

Step 1: Gather your knowledge

Think about:

Manuals
Procedures
Project documentation
Customer files
Support tickets
Contracts
Product information
Safety documentation

Step 2: Create embeddings

Every piece of text is sent to Gemini Embedding 2.

The model returns a vector like:

json [ 0.0245, -0.8121, 0.4431, ... ]

This vector is stored in a vector database.

Step 3: User asks a question

For example:

How do I add a user to the system?

This question is also converted into an embedding.

Step 4: Search for similar knowledge

Vector search finds which documents are closest to the question.

The found documents are then sent to a Large Language Model such as Gemini, Claude, or ChatGPT.

We call this process:

Retrieval Augmented Generation (RAG)

With RAG, an AI model can provide answers based on your own knowledge instead of only its training data.

Why is this interesting for FileMaker?

Many organizations have their business knowledge stored in FileMaker.

Think about:

CRM data
Tickets
Project files
Knowledge bases
Product documentation
Safety procedures
Contract information
Internal manuals

Traditionally, an employee must search using keywords.

With embeddings, a user can simply ask a question:

What procedure applies when an employee reports a near miss?

The AI then automatically searches for the most relevant documents and generates an answer based on the information found.

Practical example: HSE platform

Suppose you manage an HSE platform with:

Toolbox meetings
Safety instructions
Risk analyses
Incident reports
Procedures
Work permits

By embedding all documents, an intelligent knowledge assistant is created.

Users can ask questions such as:

What should I do in case of a fall incident?
Which PPE is mandatory for working at height?
What does our procedure say about reporting a near miss?
What training is required for this type of work?

The AI searches directly through all available documentation and presents an answer including source attribution.

Combining Gemini Embedding 2 with FileMaker

A possible architecture looks like this:

text FileMaker │ ├── Documents ├── Tickets ├── Procedures └── CRM data │ ▼ Gemini Embedding 2 │ ▼ Vector Database (Pinecone / Weaviate / Qdrant / pgvector) │ ▼ Gemini / Claude / ChatGPT │ ▼ Answer

New documents can be automatically processed as soon as they're saved in FileMaker.

This keeps the knowledge base always up to date.

When do you use embeddings?

Embeddings are interesting when you:

Have more than a few hundred documents
Want to support natural language use
Want AI to answer based on your own knowledge
Want to build smart search functionality
Want to feed chatbots with company information
Want to automate support processes
Want to unlock knowledge that is currently hidden in documents

For simple keyword search, embeddings are often not needed.

For AI-driven knowledge platforms, they're now virtually indispensable.

Practical applications

Within FileMaker, we increasingly see applications such as:

AI Helpdesk

Let users ask questions about manuals, procedures, and work instructions.

Smart document finder

Find documents by meaning rather than by keywords.

Customer support

Automatically find relevant support tickets from the past.

Safety management

Make safety procedures directly accessible to employees on site.

CRM Intelligence

Let AI gather relevant customer information from thousands of notes and contact moments.

Project assistant

Quickly find previous project experiences, solutions, and documentation.

Conclusion

Gemini Embedding 2 forms an important building block for modern AI solutions.

By converting business knowledge into vectors, it becomes possible to find information not only by words, but especially by meaning.

For FileMaker developers, this opens the door to:

Intelligent knowledge bases
AI assistants
Semantic search engines
Advanced RAG solutions
Smarter helpdesks
Knowledge-driven chatbots

Where Large Language Models provide answer generation, embeddings ensure that the right knowledge is found.

And it's precisely that combination that makes business AI truly valuable.

Want to know more?

Would you like to know how you can combine Gemini Embedding 2 with FileMaker, a vector database, and an AI model like Gemini, Claude, or ChatGPT?

Contact Loggix. We help organizations build AI solutions that leverage their own data, processes, and knowledge.