Draft
Conversation
This commit enhances the standalone agentgateway documentation by adding comprehensive LLM provider setup guides and client configuration instructions. ## Provider Documentation ### New Provider Pages - Add dedicated Ollama provider page with installation, configuration, and production deployment guidance - Expand openai-compatible.md with 7 additional providers: - DeepSeek (reasoning and chat models) - Mistral La Plateforme - Perplexity (online search models) - Fireworks AI - vLLM (self-hosted inference engine) - LM Studio (local desktop deployment) ### Enhanced Provider Navigation - Reorganize llm/about.md with categorized provider sections: - Native providers (OpenAI, Anthropic, Gemini, Vertex, Bedrock, Azure) - OpenAI-compatible providers (xAI, Cohere, Together AI, Groq, etc.) - Self-hosted solutions (Ollama, vLLM, LM Studio) - Update llm/providers/_index.md with categorized card layout ## LLM Client Configuration Guides Add comprehensive guides for configuring AI coding tools and SDKs to use agentgateway as their LLM backend: - **Cursor**: Settings UI and JSON configuration methods - **VS Code Continue**: Config file setup, multi-model support - **OpenAI SDK**: Python and Node.js implementation examples - **curl**: Command-line testing and debugging examples Each guide includes: - Prerequisites and installation steps - Configuration options (UI, file, environment variables) - Example agentgateway YAML configurations - Verification steps - Troubleshooting section ## Technical Details - All content created in assets/agw-docs/pages/ for reusability - Content shared between standalone/latest and standalone/main using Hugo reuse shortcode - All YAML configurations validated with agentgateway CLI - Fixed product name capitalization (Agent Gateway → agentgateway) - Hugo build passes with no errors - Spelling and syntax validated ## Files Changed - 26 files total (6 assets, 20 content files) - 8 modified files (provider navigation and index pages) - 18 new files (Ollama provider, LLM client guides) Addresses issues: - solo-io/docs#1944 (supported LLM providers page) - solo-io/docs#1919 (LLM client configuration guides) - #31 (Ollama provider docs) - solo-io/agentgateway-enterprise#76 (self-hosted examples) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
Add comprehensive documentation for configuring LLM providers and clients in Kubernetes deployments of agentgateway: Provider documentation: - Expand OpenAI-compatible providers (Groq, Together AI, Perplexity, Fireworks AI) - Add Ollama guide with external instance connection via headless Service - Add vLLM guide with both external and in-cluster deployment options - Update provider navigation with categorized sections Client documentation: - Add LLM client configuration guide for Kubernetes - Cover Gateway URL discovery (LoadBalancer, port-forward, Ingress) - Include client examples (Cursor, Continue, OpenAI SDK, curl) - Document authentication, TLS, and network considerations All configurations use Gateway API resources (HTTPRoute, AIBackend) and follow Kubernetes best practices for external service connectivity. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
artberger
added
documentation
Deploying agentproxy with
|
| Latest commit: |
ea7169e
|
| Status: | ✅ Deploy successful! |
| Preview URL: | https://3faf6efa.agentproxy.pages.dev |
| Branch Preview URL: | https://docs-kubernetes-llm-provider.agentproxy.pages.dev |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.