--- id: "en/ai-deployment-customization" title: "AI deployment and customization" language: "en" description: "Introducing Zhichao AI's private deployment, GPU computing power, dedicated agents, industry applications and on-demand development." canonical_url: "https://www.babel.cc/public/babelwiki/en/ai-deployment-customization.html" markdown_url: "https://www.babel.cc/public/babelwiki/ai/en/ai-deployment-customization.md" alternates: {"en": "https://www.babel.cc/public/babelwiki/ai/en/ai-deployment-customization.md", "zh": "https://www.babel.cc/public/babelwiki/ai/zh/ai-deployment-customization.md"} reading_note: "文档记录不等于当前部署能力；以实际版本、授权模块与配置为准。保留原文的可选、限制及待确认说明，勿补猜接口。 / Documentation is not a guarantee for every deployment. Preserve optional-module requirements, limitations and unresolved API contracts." --- # AI Deployment and Customization Introducing Zhichao AI's private deployment, GPU computing power, dedicated agents, industry applications and on-demand development. ![AI tools and agents](https://www.babel.cc/public/babelwiki/assets/images/ai-agent.webp) *AI tools and agent entry points, not the detailed interface of each module.* ## Private deployment method Zhichao AI private deployment can be divided into three categories based on data security, budget, computing power, model calling and network search requirements. Actual projects should be subject to formal implementation evaluation. | Method | Description | Applicable scenarios | | --- | --- | --- | | Fully private deployment | Deploy approximately 32B models such as DeepSeek and Qianwen on self-built servers, and model inference and knowledge base capabilities should be run within the customer environment as much as possible | Customers who have strict restrictions on data going out of the domain and have sufficient budget and GPU computing power | | Local vector processing | Deploy vector models and knowledge base storage operations on self-built servers, and use public network large model APIs for question and answer reasoning | Customers who want the knowledge base storage process to be locally controllable and accept external model reasoning | | Vectors are only stored locally | The self-built server saves the vectorized knowledge base, and model inference and vector operations use the public network large model API | Customers who want to reduce local GPU costs and accept external model services | ## Reference server configuration | Deployment method | Server purpose | Reference configuration | GPU configuration | | --- | --- | --- | --- | | Fully private deployment | Computing server | CPU 2*8368Q, 256G memory, 960G SSD *2, 8TB HDD *2 | 5880 ADA 48G *4 | | Local vector processing | Vector server | CPU 2*4310, 128G memory, 480G SSD, 4TB HDD *2 | 3090 24G *2 | | Vectors are only stored locally | Vector server | CPU 2*4310, 128G memory, 480G SSD, 4TB HDD *2 | None | ## External models and network searches Some deployment methods will use the public network large model API, Internet search API or TokenPlan. Optional models and services can include Minmax, GLM, DeepSeek, and Tencent Cloud Internet Search API. The cost will vary with the model, call volume, number of Internet searches and enterprise usage intensity. The official cost is based on the commercial quotation and implementation plan. ## Deployment form Zhichao AI can be used as an optional module of BabelBird Enterprise Drive, and can also be deployed according to enterprise requirements in private deployment projects. Private deployment usually requires additional GPU computing power, model services, vector retrieval or knowledge base indexing services, and needs to be combined with the enterprise's data security, network access and third-party model policy design. ## On-demand development BabelBird can develop exclusive AI applications around enterprise industry scenarios and business processes, such as exclusive agents, business data queries, industry-specific Q&A, document processing processes, AI tags and classification rules, third-party system access, etc. ## Typical Delivery Content - Data scope confirmation, knowledge base design and agent role design. - Configuration of capabilities such as models, vector libraries, OCR, multimodality, and third-party data sources. - Permission linkage, audit logs, access scope and security policy design. - Agent embedding, enterprise portal integration or third-party website access. - Test question and answer set, effect optimization, online training and subsequent maintenance. ## Privatization considerations Whether a private Zhichao AI deployment runs completely within the internal network, whether it calls external models, whether it uses third-party APIs, and whether it supports offline models should be clarified in the implementation plan. Customers involving sensitive data should prioritize data flow, log retention, model training boundaries, and permission audits. ## Permissions and usage boundaries - Internal AI assistance, search and file references follow BabelBird permissions. Custom knowledge-base bots also have a knowledge scope and publication scope; anonymous publication should use knowledge suitable for that audience. - Uploaded BabelBird files that AI can read are automatically ingested and vectorized for AI assistance, AI search and image search. Ingestion does not make files public. A custom knowledge-base bot uses the file scope selected or uploaded for it. - External customer service, website embedding, third-party data sources, privately deployed models and GPU computing power are optional deployment or customization capabilities and should be subject to actual authorization, implementation plan and enterprise configuration. - When AI answers involve high-risk content such as contracts, finance, medical, legal, and engineering safety, the AI ​​output should be used as auxiliary information and reviewed by professionals. ## Related information - [Permission system](https://www.babel.cc/public/babelwiki/en/permissions.html) - [Security and Audit](https://www.babel.cc/public/babelwiki/en/security.html) - [FAQ: Deployment, AI and technical issues](https://www.babel.cc/public/babelwiki/en/faq-technical.html) - Public introduction: