Hủy
Cloud Insights

All documents

AI Inference

FPT Cloud Server
FPT Container
FPT Network
FPT Storage
FPT Cloud Backup & DR
FPT Database Engine
FPT Integration
FPT DevSecOps Services
FPT Monitoring
FPT Security
AI Infrastructure
AI Inference
FPT AI Inference
AI Studio
AI Marketplace
Billing
    Try It Out
    Try It Out
    Updated on 02 Jul 2025
    Print: Export: PDF

    1.2.1. Embedding Model

    Embedding models are transformer-based neural networks that transform chunks of documents (i.e. passages of text) into a numeric representation or vector (IBM, 2024)

    Alt text

    Step 1: Select the type of input you want to test in Input type dropdown.

    Step 2: Select the desired output format for the embedding in Encoding format dropdown.

    Step 3: Choose how to handle input that exceeds the token limit in Truncate dropdown.

    Step 4: You can enter up to 500 characters in Text input.

    Step 5: Hit Run and the system will display the embedding vector (numerical representation) in the Result section.

    1.2.2. Guardrail Model (Coming soon)

    1.2.3. Large Language Model

    Large language models (LLMs) are a category of foundation models trained on immense amounts of data making them capable of understanding and generating natural language and other types of content to perform a wide range of tasks. (IBM, 2023)

    Alt text

    Step 1 (optional): Click on the task that best fits your needs. The system will automatically prepare a response based on your input:

      • Create a go-to-market plan: Generate steps for bringing a product to market.
      • Summarize this report in bullet points: Condense long reports into clear bullet points.
      • Help me prepare talking points for my meeting: Quickly list key ideas for your meetings.
      • Professionalize my email: Rewrite emails to sound more polished and formal.
      • Write a to-do list for a personal project: Generate a checklist to organize your personal work.

    Step 2: Type your question, topic, or specific request related to the selected task into Text input.

    Step 3: Hit Send and the system will display the response directly on the page.

    1.2.4. Speech to Text Model

    Speech to text is the process of converting spoken words into a text transcript (IBM, 2024) Alt text

    Step 1: Select the type of language you want in Source Language dropdown.

    Step 2: Select the Task you want the model to perform in Task dropdown (Transcribe by default)

    Step 3: Click Upload file to upload audio file or Click the mic button icon to record. You can click the play button icon to listen to your audio file

    Step 4: Hit Run and the system will display the transcribe file in the Result section.

    1.2.5. Text to Speech Model

    Text to speech (TTS) is a type of technology that converts text on a digital interface into natural-sounding audio. It can also be referred to as “read aloud” technology, computer-generated speech or speech synthesis (IBM, 2024) Alt text

    Step 1: Select the type of voice you want in Voice dropdown.

    Step 2: Select the speed of your voice in Speed dropdown.

    Step 3: Select the language in Language dropdown.

    Step 4: You can enter up to 500 characters in Text input.

    Step 5: Hit Run and the system will display the audio file in the Result section.

    1.2.6. Vision Language Model

    Vision language model can partition an image into segments based on the spatial features that it has learned about and extracted from the image. The VLM can then supply text descriptions of those segments (IBM, 2025) Alt text

    Upload your image and ask questions related to your image.

    © 2025 FPT Cloud. All Rights Reserved.