# Docs - Float16

## Document

- [Introduction](https://docs.float16.cloud/getting-started/introduction.md): Introduce Float16.cloud
- [Account](https://docs.float16.cloud/getting-started/account.md): Learn how to create your Float16.cloud account
- [Dashboard](https://docs.float16.cloud/getting-started/account/dashboard.md): View a dashboard with information about activities on your account
- [Profile](https://docs.float16.cloud/getting-started/account/profile.md): Review and update your personal profile information
- [Payment](https://docs.float16.cloud/getting-started/account/payment.md): View current charges
- [Workspace](https://docs.float16.cloud/getting-started/account/workspace.md): Manage your workspace settings and configurations
- [Service Quota](https://docs.float16.cloud/getting-started/account/service-quota.md): Estimate your current quota usage
- [LLM as a service](https://docs.float16.cloud/getting-started/llm-as-a-service.md): Seamless LLM Integration
- [Quick Start](https://docs.float16.cloud/getting-started/llm-as-a-service/quick-start.md): LLM as a service quick start
- [Set the credentials](https://docs.float16.cloud/getting-started/llm-as-a-service/quick-start/set-the-credentials.md): Set your API Key
- [Supported Model](https://docs.float16.cloud/getting-started/llm-as-a-service/supported-model.md): Float16.cloud Model Overview
- [Limitation](https://docs.float16.cloud/getting-started/llm-as-a-service/limitation.md): API Limitation
- [API Reference](https://docs.float16.cloud/getting-started/llm-as-a-service/api-reference.md): API Reference
- [One Click Deploy](https://docs.float16.cloud/getting-started/one-click-deploy.md)
- [Quick Start](https://docs.float16.cloud/getting-started/one-click-deploy/quick-start.md): One Click Deploy quick start
- [Instance Detail](https://docs.float16.cloud/getting-started/one-click-deploy/quick-start/instance-detail.md): Your instance detail
- [Re-generate API Key](https://docs.float16.cloud/getting-started/one-click-deploy/quick-start/re-generate-api-key.md): Manage your API Key
- [Terminate Instance](https://docs.float16.cloud/getting-started/one-click-deploy/quick-start/terminate-instance.md): Terminate your instance
- [Features](https://docs.float16.cloud/getting-started/one-click-deploy/features.md)
- [OpenAI Compatible](https://docs.float16.cloud/getting-started/one-click-deploy/features/openai-compatible.md)
- [Long context and Auto scheduler](https://docs.float16.cloud/getting-started/one-click-deploy/features/long-context-and-auto-scheduler.md)
- [Quantization](https://docs.float16.cloud/getting-started/one-click-deploy/features/quantization.md)
- [Context caching](https://docs.float16.cloud/getting-started/one-click-deploy/features/context-caching.md)
- [Limitation](https://docs.float16.cloud/getting-started/one-click-deploy/limitation.md)
- [Validated model](https://docs.float16.cloud/getting-started/one-click-deploy/validated-model.md)
- [Endpoint Specification](https://docs.float16.cloud/getting-started/one-click-deploy/endpoint-specification.md)
- [Serverless GPU](https://docs.float16.cloud/getting-started/serverless-gpu.md)
- [Quick Start](https://docs.float16.cloud/getting-started/serverless-gpu/quick-start.md): Serverless GPU quick start
- [Mode](https://docs.float16.cloud/getting-started/serverless-gpu/quick-start/mode.md): Serverless GPU Services
- [Task Status](https://docs.float16.cloud/getting-started/serverless-gpu/quick-start/task-status.md): Task Status Description
- [App Features](https://docs.float16.cloud/getting-started/serverless-gpu/quick-start/app-features.md)
- [Project Detail](https://docs.float16.cloud/getting-started/serverless-gpu/quick-start/app-features/project-detail.md)
- [File storage](https://docs.float16.cloud/getting-started/serverless-gpu/quick-start/app-features/file-storage.md)
- [Tutorials](https://docs.float16.cloud/getting-started/serverless-gpu/tutorials.md)
- [Hello World](https://docs.float16.cloud/getting-started/serverless-gpu/tutorials/hello-world.md): Hello World with Float16 Serverless GPU
- [Install new library](https://docs.float16.cloud/getting-started/serverless-gpu/tutorials/install-new-library.md): Installing New Libraries in Your Float16 Remote Instance
- [Prepare model weight](https://docs.float16.cloud/getting-started/serverless-gpu/tutorials/prepare-model-weight.md)
- [S3 Copy output from remote](https://docs.float16.cloud/getting-started/serverless-gpu/tutorials/s3-copy-output-from-remote.md): get your output to S3
- [R2 Copy output from remote](https://docs.float16.cloud/getting-started/serverless-gpu/tutorials/r2-copy-output-from-remote.md): get your output to R2
- [Direct upload and download](https://docs.float16.cloud/getting-started/serverless-gpu/tutorials/direct-upload-and-download.md): Get Endpoint via Float16
- [Server mode](https://docs.float16.cloud/getting-started/serverless-gpu/tutorials/server-mode.md): Get Endpoint via Float16
- [LLM Dynamic Batching](https://docs.float16.cloud/getting-started/serverless-gpu/tutorials/llm-dynamic-batching.md): Get Endpoint via Float16
- [Train and Inference MNIST](https://docs.float16.cloud/getting-started/serverless-gpu/tutorials/train-and-inference-mnist.md): Get Endpoint via Float16
- [Etc.](https://docs.float16.cloud/getting-started/serverless-gpu/tutorials/etc..md): Get Endpoint via Float16
- [CLI References](https://docs.float16.cloud/getting-started/serverless-gpu/cli-references.md)
- [FAQ](https://docs.float16.cloud/getting-started/serverless-gpu/faq.md): Frequently Ask Question about Serverless GPU
- [Playground](https://docs.float16.cloud/getting-started/playground.md): Learn and play with us.
- [FloatChat](https://docs.float16.cloud/getting-started/playground/floatchat.md): Chat Playground for developers
- [FloatPrompt](https://docs.float16.cloud/getting-started/playground/floatprompt.md): Create Prompt, Run and Share with your colleague
- [Quantize by Float16](https://docs.float16.cloud/getting-started/playground/quantize-by-float16.md)
- [Float16 - Colab](https://docs.float16.cloud/getting-started/playground/float16-colab.md)
- [Q\&A Bot (RAG)](https://docs.float16.cloud/use-case/q-and-a-bot-rag.md)
- [Text-to-SQL](https://docs.float16.cloud/use-case/text-to-sql.md)
- [OpenAI with Rate Limit](https://docs.float16.cloud/use-case/openai-with-rate-limit.md)
- [OpenAI with Guardrail](https://docs.float16.cloud/use-case/openai-with-guardrail.md)
- [Multiple Agents](https://docs.float16.cloud/use-case/multiple-agents.md)
- [Q\&A Chatbots (RAG + Agents)](https://docs.float16.cloud/use-case/q-and-a-chatbots-rag-+-agents.md)
- [The Beginner's LLM Development Journey](https://docs.float16.cloud/journey/the-beginners-llm-development-journey.md)
- [Glossary](https://docs.float16.cloud/journey/glossary.md): Essential terminology in the world of Large Language Models (LLM)
- [\[English Version\] LLM Glossary](https://docs.float16.cloud/journey/glossary/english-version-llm-glossary.md): LLM Glossary in English Language
- [\[ภาษาไทย\] LLM Glossary](https://docs.float16.cloud/journey/glossary/llm-glossary.md): LLM Glossary ฉบับภาษาไทย
- [How to install node](https://docs.float16.cloud/journey/how-to-install-node.md): node installation guide
- [Variable](https://docs.float16.cloud/prompting/variable.md)
- [Condition](https://docs.float16.cloud/prompting/condition.md)
- [Demonstration](https://docs.float16.cloud/prompting/demonstration.md)
- [Loop](https://docs.float16.cloud/prompting/loop.md)
- [Formatting](https://docs.float16.cloud/prompting/formatting.md)
- [Chat](https://docs.float16.cloud/prompting/chat.md)
- [Technical term (Retrieve)](https://docs.float16.cloud/prompting/technical-term-retrieve.md)
- [Privacy Policy](https://docs.float16.cloud/privacy-policy.md): Float16's Privacy Policy
- [Terms & Conditions](https://docs.float16.cloud/terms-and-conditions.md): Float16's Terms and Conditions


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on a page URL with the `ask` query parameter:
```
GET https://docs.float16.cloud/getting-started/introduction.md?ask=<question>
```
The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.