> For the complete documentation index, see [llms.txt](https://docs.datasaur.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.datasaur.ai/llm-projects.md). # LLM Projects - [LLM Labs Introduction](https://docs.datasaur.ai/llm-projects/llm-introduction.md): LLM Labs is where teams build, compare and evaluate private and open-weight LLMs before deploying them inside their own infrastructure. - [Sandbox](https://docs.datasaur.ai/llm-projects/sandbox.md): Sandbox is a platform designed for your LLM experimentation. It allows you to integrate your knowledge base and deploy models easily. - [Direct Access LLMs](https://docs.datasaur.ai/llm-projects/sandbox/direct-access-llms.md) - [File attachment](https://docs.datasaur.ai/llm-projects/sandbox/file-attachment.md) - [Conversational prompt](https://docs.datasaur.ai/llm-projects/sandbox/conversational-prompt.md) - [Model Context Protocol (MCP)](https://docs.datasaur.ai/llm-projects/sandbox/model-context-protocol-mcp.md) - [Deployment](https://docs.datasaur.ai/llm-projects/deployment.md) - [Deployment API](https://docs.datasaur.ai/llm-projects/deployment/deployment-api.md) - [Knowledge base](https://docs.datasaur.ai/llm-projects/knowledge-base.md) - [External Object Storage](https://docs.datasaur.ai/llm-projects/knowledge-base/external-object-storage.md) - [File Properties](https://docs.datasaur.ai/llm-projects/knowledge-base/file-properties.md) - [Chunk Editor](https://docs.datasaur.ai/llm-projects/knowledge-base/chunk-editor.md) - [Periodic Sync](https://docs.datasaur.ai/llm-projects/knowledge-base/periodic-sync.md) - [Models](https://docs.datasaur.ai/llm-projects/models.md) - [Amazon SageMaker JumpStart](https://docs.datasaur.ai/llm-projects/models/amazon-sagemaker-jumpstart.md) - [Amazon Bedrock](https://docs.datasaur.ai/llm-projects/models/amazon-bedrock.md) - [Open AI](https://docs.datasaur.ai/llm-projects/models/open-ai.md) - [Azure OpenAI](https://docs.datasaur.ai/llm-projects/models/azure-openai.md) - [Vertex AI](https://docs.datasaur.ai/llm-projects/models/vertex-ai.md) - [Custom model](https://docs.datasaur.ai/llm-projects/models/custom-model.md) - [Fine-tuning](https://docs.datasaur.ai/llm-projects/models/fine-tuning.md) - [LLM Comparison Table](https://docs.datasaur.ai/llm-projects/models/llm-comparison-table.md) - [Evaluation](https://docs.datasaur.ai/llm-projects/evaluation.md) - [Automated Evaluation](https://docs.datasaur.ai/llm-projects/evaluation/automated-evaluation.md) - [Multi-model evaluation](https://docs.datasaur.ai/llm-projects/evaluation/automated-evaluation/multi-application-evaluation.md) - [Custom metrics](https://docs.datasaur.ai/llm-projects/evaluation/automated-evaluation/custom-metrics.md) - [Ranking (RLHF)](https://docs.datasaur.ai/llm-projects/evaluation/ranking-rlhf.md) - [Rating](https://docs.datasaur.ai/llm-projects/evaluation/rating.md) - [Performance Monitoring](https://docs.datasaur.ai/llm-projects/evaluation/performance-monitoring.md) - [Dataset](https://docs.datasaur.ai/llm-projects/dataset.md) - [Pricing Plan](https://docs.datasaur.ai/llm-projects/pricing-plan.md) --- # 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 that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.datasaur.ai/llm-projects.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. 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.