From d15664c8e6dd30dfc2f25ad6884ba5dcf0e995a8 Mon Sep 17 00:00:00 2001 From: Krish Dholakia Date: Sat, 14 Jun 2025 19:38:46 -0700 Subject: [PATCH] Litellm stable docs 06 14 2025 p2 (#11738) * docs: track which items need docs * docs(anthropic.md): add tool_choice="none" to docs * docs: add docs for new anthropic + perplexity features * docs: cleanup mistral reasoning docs * docs: add links to docs * docs(index.md): update docs * docs: refactor to add a new 'integrations' tab to docs * refactor(docs/): create separate tab for integrations make it easier to highlight new integrations * docs: sort sidebar * docs: update --- docs/my-website/docs/enterprise.md | 95 ++++++++++---- docs/my-website/docs/hosted.md | 66 ---------- docs/my-website/docs/integrations/index.md | 5 + docs/my-website/docs/providers/anthropic.md | 57 ++++++++ .../docs/providers/custom_llm_server.md | 9 +- docs/my-website/docs/providers/mistral.md | 8 +- docs/my-website/docs/providers/perplexity.md | 63 +++++++++ docs/my-website/docs/reasoning_content.md | 21 +-- docs/my-website/docusaurus.config.js | 10 +- .../release_notes/v1.72.6-stable/index.md | 62 ++++----- docs/my-website/sidebars.js | 124 ++++++++---------- 11 files changed, 300 insertions(+), 220 deletions(-) delete mode 100644 docs/my-website/docs/hosted.md create mode 100644 docs/my-website/docs/integrations/index.md diff --git a/docs/my-website/docs/enterprise.md b/docs/my-website/docs/enterprise.md index 706ca33714..353fe29721 100644 --- a/docs/my-website/docs/enterprise.md +++ b/docs/my-website/docs/enterprise.md @@ -7,6 +7,8 @@ For companies that need SSO, user management and professional support for LiteLL Get free 7-day trial key [here](https://www.litellm.ai/#trial) ::: +## Enterprise Features + Includes all enterprise features. @@ -18,32 +20,13 @@ This covers: - [**Enterprise Features**](./proxy/enterprise) - ✅ **Feature Prioritization** - ✅ **Custom Integrations** -- ✅ **Professional Support - Dedicated discord + slack** +- ✅ **Professional Support - Dedicated Slack/Teams channel** -Deployment Options: +## Self-Hosted -**Self-Hosted** -1. Manage Yourself - you can deploy our Docker Image or build a custom image from our pip package, and manage your own infrastructure. In this case, we would give you a license key + provide support via a dedicated support channel. +Manage Yourself - you can deploy our Docker Image or build a custom image from our pip package, and manage your own infrastructure. In this case, we would give you a license key + provide support via a dedicated support channel. -2. We Manage - you give us subscription access on your AWS/Azure/GCP account, and we manage the deployment. - -**Managed** - -You can use our cloud product where we setup a dedicated instance for you. - -## Frequently Asked Questions - -### SLA's + Professional Support - -Professional Support can assist with LLM/Provider integrations, deployment, upgrade management, and LLM Provider troubleshooting. We can’t solve your own infrastructure-related issues but we will guide you to fix them. - -- 1 hour for Sev0 issues - 100% production traffic is failing -- 6 hours for Sev1 - <100% production traffic is failing -- 24h for Sev2-Sev3 between 7am – 7pm PT (Monday through Saturday) - setup issues e.g. Redis working on our end, but not on your infrastructure. -- 72h SLA for patching vulnerabilities in the software. - -**We can offer custom SLAs** based on your needs and the severity of the issue ### What’s the cost of the Self-Managed Enterprise edition? @@ -58,8 +41,72 @@ You just deploy [our docker image](https://docs.litellm.ai/docs/proxy/deploy) an LITELLM_LICENSE="eyJ..." ``` -No data leaves your environment. +**No data leaves your environment.** + + +## Hosted LiteLLM Proxy + +LiteLLM maintains the proxy, so you can focus on your core products. + +We provide a dedicated proxy for your team, and manage the infrastructure. + +### **Status**: GA + +Our proxy is already used in production by customers. + +See our status page for [**live reliability**](https://status.litellm.ai/) + +### **Benefits** +- **No Maintenance, No Infra**: We'll maintain the proxy, and spin up any additional infrastructure (e.g.: separate server for spend logs) to make sure you can load balance + track spend across multiple LLM projects. +- **Reliable**: Our hosted proxy is tested on 1k requests per second, making it reliable for high load. +- **Secure**: LiteLLM is SOC-2 Type 2 and ISO 27001 certified, to make sure your data is as secure as possible. + +### Supported data regions for LiteLLM Cloud + +You can find [supported data regions litellm here](../docs/data_security#supported-data-regions-for-litellm-cloud) + + +## Frequently Asked Questions + +### SLA's + Professional Support + +Professional Support can assist with LLM/Provider integrations, deployment, upgrade management, and LLM Provider troubleshooting. We can’t solve your own infrastructure-related issues but we will guide you to fix them. + +- 1 hour for Sev0 issues - 100% production traffic is failing +- 6 hours for Sev1 - <100% production traffic is failing +- 24h for Sev2-Sev3 between 7am – 7pm PT (Monday through Saturday) - setup issues e.g. Redis working on our end, but not on your infrastructure. +- 72h SLA for patching vulnerabilities in the software. + +**We can offer custom SLAs** based on your needs and the severity of the issue ## Data Security / Legal / Compliance FAQs -[Data Security / Legal / Compliance FAQs](./data_security.md) \ No newline at end of file +[Data Security / Legal / Compliance FAQs](./data_security.md) + + +### Pricing + +Pricing is based on usage. We can figure out a price that works for your team, on the call. + +[**Contact Us to learn more**](https://calendly.com/d/4mp-gd3-k5k/litellm-1-1-onboarding-chat) + + + +## **Screenshots** + +### 1. Create keys + + + +### 2. Add Models + + + +### 3. Track spend + + + + +### 4. Configure load balancing + + diff --git a/docs/my-website/docs/hosted.md b/docs/my-website/docs/hosted.md deleted file mode 100644 index 99bfe99031..0000000000 --- a/docs/my-website/docs/hosted.md +++ /dev/null @@ -1,66 +0,0 @@ -import Image from '@theme/IdealImage'; - -# Hosted LiteLLM Proxy - -LiteLLM maintains the proxy, so you can focus on your core products. - -## [**Get Onboarded**](https://calendly.com/d/4mp-gd3-k5k/litellm-1-1-onboarding-chat) - -This is in alpha. Schedule a call with us, and we'll give you a hosted proxy within 30 minutes. - -[**🚨 Schedule Call**](https://calendly.com/d/4mp-gd3-k5k/litellm-1-1-onboarding-chat) - -### **Status**: Alpha - -Our proxy is already used in production by customers. - -See our status page for [**live reliability**](https://status.litellm.ai/) - -### **Benefits** -- **No Maintenance, No Infra**: We'll maintain the proxy, and spin up any additional infrastructure (e.g.: separate server for spend logs) to make sure you can load balance + track spend across multiple LLM projects. -- **Reliable**: Our hosted proxy is tested on 1k requests per second, making it reliable for high load. -- **Secure**: LiteLLM is currently undergoing SOC-2 compliance, to make sure your data is as secure as possible. - -## Data Privacy & Security - -You can find our [data privacy & security policy for cloud litellm here](../docs/data_security#litellm-cloud) - -## Supported data regions for LiteLLM Cloud - -You can find [supported data regions litellm here](../docs/data_security#supported-data-regions-for-litellm-cloud) - -### Pricing - -Pricing is based on usage. We can figure out a price that works for your team, on the call. - -[**🚨 Schedule Call**](https://calendly.com/d/4mp-gd3-k5k/litellm-1-1-onboarding-chat) - -## **Screenshots** - -### 1. Create keys - - - -### 2. Add Models - - - -### 3. Track spend - - - - -### 4. Configure load balancing - - - -#### [**🚨 Schedule Call**](https://calendly.com/d/4mp-gd3-k5k/litellm-1-1-onboarding-chat) - -## Feature List - -- Easy way to add/remove models -- 100% uptime even when models are added/removed -- custom callback webhooks -- your domain name with HTTPS -- Ability to create/delete User API keys -- Reasonable set monthly cost \ No newline at end of file diff --git a/docs/my-website/docs/integrations/index.md b/docs/my-website/docs/integrations/index.md new file mode 100644 index 0000000000..9731db6e75 --- /dev/null +++ b/docs/my-website/docs/integrations/index.md @@ -0,0 +1,5 @@ +# Integrations + +This section covers integrations with various tools and services that can be used with LiteLLM (either Proxy or SDK). + +Click into each section to learn more about the integrations. \ No newline at end of file diff --git a/docs/my-website/docs/providers/anthropic.md b/docs/my-website/docs/providers/anthropic.md index 1740450b90..b57172afd4 100644 --- a/docs/my-website/docs/providers/anthropic.md +++ b/docs/my-website/docs/providers/anthropic.md @@ -664,6 +664,63 @@ response = completion( ) ``` +### Disable Tool Calling + +You can disable tool calling by setting the `tool_choice` to `"none"`. + + + + +```python +from litellm import completion + +response = completion( + model="anthropic/claude-3-opus-20240229", + messages=messages, + tools=tools, + tool_choice="none", +) + +``` + + + +1. Setup config.yaml + +```yaml +model_list: + - model_name: anthropic-claude-model + litellm_params: + model: anthropic/claude-3-opus-20240229 + api_key: os.environ/ANTHROPIC_API_KEY +``` + +2. Start proxy + +```bash +litellm --config /path/to/config.yaml +``` + +3. Test it! + +Replace `anything` with your LiteLLM Proxy Virtual Key, if [setup](../proxy/virtual_keys). + +```bash +curl http://0.0.0.0:4000/v1/chat/completions \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer anything" \ + -d '{ + "model": "anthropic-claude-model", + "messages": [{"role": "user", "content": "Who won the World Cup in 2022?"}], + "tools": [{"type": "mcp", "server_label": "deepwiki", "server_url": "https://mcp.deepwiki.com/mcp", "require_approval": "never"}], + "tool_choice": "none" + }' +``` + + + + + ### MCP Tool Calling Here's how to use MCP tool calling with Anthropic: diff --git a/docs/my-website/docs/providers/custom_llm_server.md b/docs/my-website/docs/providers/custom_llm_server.md index 2adb6a67cf..5f2cbb02da 100644 --- a/docs/my-website/docs/providers/custom_llm_server.md +++ b/docs/my-website/docs/providers/custom_llm_server.md @@ -8,9 +8,16 @@ Call your custom torch-serve / internal LLM APIs via LiteLLM - For modifying incoming/outgoing calls on proxy, [go here](../proxy/call_hooks.md) ::: +Supported Routes: +- `/v1/chat/completions` -> `litellm.completion` +- `/v1/completions` -> `litellm.text_completion` +- `/v1/embeddings` -> `litellm.embedding` +- `/v1/images/generations` -> `litellm.image_generation` + + ## Quick Start -```python +```python showLineNumbers import litellm from litellm import CustomLLM, completion, get_llm_provider diff --git a/docs/my-website/docs/providers/mistral.md b/docs/my-website/docs/providers/mistral.md index d9e12e4bcf..e0fccba786 100644 --- a/docs/my-website/docs/providers/mistral.md +++ b/docs/my-website/docs/providers/mistral.md @@ -205,11 +205,13 @@ assert isinstance( ) ``` -## Reasoning Capabilities (Magistral Models) +## Reasoning -Mistral's Magistral models support advanced reasoning capabilities that allow the model to think step-by-step before providing answers. LiteLLM provides seamless integration with these reasoning features through OpenAI-compatible parameters. +Mistral does not directly support reasoning, instead it recommends a specific [system prompt](https://docs.mistral.ai/capabilities/reasoning/) to use with their magistral models. By setting the `reasoning_effort` parameter, LiteLLM will prepend the system prompt to the request. -### Supported Magistral Models +If an existing system message is provided, LiteLLM will send both as a list of system messages (you can verify this by enabling `litellm._turn_on_debug()`). + +### Supported Models | Model Name | Function Call | |----------------|--------------------------------------------------------------| diff --git a/docs/my-website/docs/providers/perplexity.md b/docs/my-website/docs/providers/perplexity.md index 5ef1f8861a..2fcb49c60f 100644 --- a/docs/my-website/docs/providers/perplexity.md +++ b/docs/my-website/docs/providers/perplexity.md @@ -39,6 +39,69 @@ for chunk in response: print(chunk) ``` +## Reasoning Effort + +Requires v1.72.6+ + +:::info + +See full guide on Reasoning with LiteLLM [here](../reasoning_content) + +::: + +You can set the reasoning effort by setting the `reasoning_effort` parameter. + + + + +```python +from litellm import completion +import os + +os.environ['PERPLEXITYAI_API_KEY'] = "" +response = completion( + model="perplexity/sonar-reasoning", + messages=messages, + reasoning_effort="high" +) +print(response) +``` + + + +1. Setup config.yaml + +```yaml +model_list: + - model_name: perplexity-sonar-reasoning-model + litellm_params: + model: perplexity/sonar-reasoning + api_key: os.environ/PERPLEXITYAI_API_KEY +``` + +2. Start proxy + +```bash +litellm --config /path/to/config.yaml +``` + +3. Test it! + +Replace `anything` with your LiteLLM Proxy Virtual Key, if [setup](../proxy/virtual_keys). + +```bash +curl http://0.0.0.0:4000/v1/chat/completions \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer anything" \ + -d '{ + "model": "perplexity-sonar-reasoning-model", + "messages": [{"role": "user", "content": "Who won the World Cup in 2022?"}], + "reasoning_effort": "high" + }' +``` + + + ## Supported Models All models listed here https://docs.perplexity.ai/docs/model-cards are supported. Just do `model=perplexity/`. diff --git a/docs/my-website/docs/reasoning_content.md b/docs/my-website/docs/reasoning_content.md index fb3640fdc1..f9cab01639 100644 --- a/docs/my-website/docs/reasoning_content.md +++ b/docs/my-website/docs/reasoning_content.md @@ -40,7 +40,7 @@ LiteLLM will standardize the `reasoning_content` in the response and `thinking_b ## Quick Start - + ```python showLineNumbers from litellm import completion @@ -58,25 +58,6 @@ response = completion( print(response.choices[0].message.content) ``` - - - -```python showLineNumbers -from litellm import completion -import os - -os.environ["MISTRAL_API_KEY"] = "" - -response = completion( - model="mistral/magistral-medium-2506", - messages=[ - {"role": "user", "content": "What is 15 multiplied by 7? Show your reasoning."}, - ], - reasoning_effort="medium", -) -print(response.choices[0].message.content) -``` - diff --git a/docs/my-website/docusaurus.config.js b/docs/my-website/docusaurus.config.js index 8d480131ff..373b0655bb 100644 --- a/docs/my-website/docusaurus.config.js +++ b/docs/my-website/docusaurus.config.js @@ -120,16 +120,16 @@ const config = { label: 'Docs', }, { - sidebarId: 'tutorialSidebar', + sidebarId: 'integrationsSidebar', position: 'left', - label: 'Enterprise', - to: "docs/enterprise" + label: 'Integrations', + to: "docs/integrations" }, { sidebarId: 'tutorialSidebar', position: 'left', - label: 'Hosted', - to: "docs/hosted" + label: 'Enterprise', + to: "docs/enterprise" }, { to: '/release_notes', label: 'Release Notes', position: 'left' }, { diff --git a/docs/my-website/release_notes/v1.72.6-stable/index.md b/docs/my-website/release_notes/v1.72.6-stable/index.md index e3e84f250c..41da1ec1ac 100644 --- a/docs/my-website/release_notes/v1.72.6-stable/index.md +++ b/docs/my-website/release_notes/v1.72.6-stable/index.md @@ -65,47 +65,47 @@ This version is not out yet. ### Updated Models #### Bugs -- **Watsonx** +- **[Watsonx](../../docs/providers/watsonx)** - Ignore space id on Watsonx deployments (throws json errors) - [PR](https://github.com/BerriAI/litellm/pull/11527) -- **Ollama** +- **[Ollama](../../docs/providers/ollama)** - Set tool call id for streaming calls - [PR](https://github.com/BerriAI/litellm/pull/11528) -- **Gemini (VertexAI + Google AI Studio)** +- **Gemini ([VertexAI](../../docs/providers/vertex) + [Google AI Studio](../../docs/providers/gemini))** - Fix tool call indexes - [PR](https://github.com/BerriAI/litellm/pull/11558) - Handle empty string for arguments in function calls - [PR](https://github.com/BerriAI/litellm/pull/11601) - Add audio/ogg mime type support when inferring from file url’s - [PR](https://github.com/BerriAI/litellm/pull/11635) -- **Custom LLM** +- **[Custom LLM](../../docs/providers/custom_llm_server)** - Fix passing api_base, api_key, litellm_params_dict to custom_llm embedding methods - [PR](https://github.com/BerriAI/litellm/pull/11450) s/o [ElefHead](https://github.com/ElefHead) -- **Huggingface** +- **[Huggingface](../../docs/providers/huggingface)** - Add /chat/completions to endpoint url when missing - [PR](https://github.com/BerriAI/litellm/pull/11630) -- **Deepgram** +- **[Deepgram](../../docs/providers/deepgram)** - Support async httpx calls - [PR](https://github.com/BerriAI/litellm/pull/11641) -- **Anthropic** +- **[Anthropic](../../docs/providers/anthropic)** - Append prefix (if set) to assistant content start - [PR](https://github.com/BerriAI/litellm/pull/11719) #### Features -- **VertexAI** +- **[VertexAI](../../docs/providers/vertex)** - Support vertex credentials set via env var on passthrough - [PR](https://github.com/BerriAI/litellm/pull/11527) - Support for choosing ‘global’ region when model is only available there - [PR](https://github.com/BerriAI/litellm/pull/11566) - Anthropic passthrough cost calculation + token tracking - [PR](https://github.com/BerriAI/litellm/pull/11611) - Support ‘global’ vertex region on passthrough - [PR](https://github.com/BerriAI/litellm/pull/11661) -- **Anthropic** - - ‘none’ tool choice param support - [PR](https://github.com/BerriAI/litellm/pull/11695) -- **Perplexity** - - Add ‘reasoning_effort’ support - [PR](https://github.com/BerriAI/litellm/pull/11562) -- **Mistral** - - Add mistral reasoning support - [PR](https://github.com/BerriAI/litellm/pull/11642) -- **SGLang** +- **[Anthropic](../../docs/providers/anthropic)** + - ‘none’ tool choice param support - [PR](https://github.com/BerriAI/litellm/pull/11695), [Get Started](../../docs/providers/anthropic#disable-tool-calling) +- **[Perplexity](../../docs/providers/perplexity)** + - Add ‘reasoning_effort’ support - [PR](https://github.com/BerriAI/litellm/pull/11562), [Get Started](../../docs/providers/perplexity#reasoning-effort) +- **[Mistral](../../docs/providers/mistral)** + - Add mistral reasoning support - [PR](https://github.com/BerriAI/litellm/pull/11642), [Get Started](../../docs/providers/mistral#reasoning) +- **[SGLang](../../docs/providers/openai_compatible)** - Map context window exceeded error for proper handling - [PR](https://github.com/BerriAI/litellm/pull/11575/) -- **Deepgram** +- **[Deepgram](../../docs/providers/deepgram)** - Provider specific params support - [PR](https://github.com/BerriAI/litellm/pull/11638) -- **Azure** +- **[Azure](../../docs/providers/azure)** - Return content safety filter results - [PR](https://github.com/BerriAI/litellm/pull/11655) --- ## LLM API Endpoints #### Bugs -- **Chat Completion** +- **[Chat Completion](../../docs/completion/input)** - Streaming - Ensure consistent ‘created’ across chunks - [PR](https://github.com/BerriAI/litellm/pull/11528) #### Features - **MCP** @@ -113,11 +113,11 @@ This version is not out yet. - Add permission management for MCP List + Call Tool operations - [PR](https://github.com/BerriAI/litellm/pull/11682), [Docs](../../docs/mcp#-mcp-permission-management) - Streamable HTTP server support - [PR](https://github.com/BerriAI/litellm/pull/11628), [PR](https://github.com/BerriAI/litellm/pull/11645), [Docs](../../docs/mcp#using-your-mcp) - Use Experimental dedicated Rest endpoints for list, calling MCP tools - [PR](https://github.com/BerriAI/litellm/pull/11684) -- **Responses API** - - NEW API Endpoint - List input items - [PR](https://github.com/BerriAI/litellm/pull/11602) +- **[Responses API](../../docs/response_api)** + - NEW API Endpoint - List input items - [PR](https://github.com/BerriAI/litellm/pull/11602) [NEEDS DOCS] - Background mode for OpenAI + Azure OpenAI - [PR](https://github.com/BerriAI/litellm/pull/11640) - Langfuse/other Logging support on responses api requests - [PR](https://github.com/BerriAI/litellm/pull/11685) -- **Chat Completions** +- **[Chat Completions](../../docs/completion/input)** - Bridge for Responses API - allows calling codex-mini via `/chat/completions` and `/v1/messages` - [PR](https://github.com/BerriAI/litellm/pull/11632), [PR](https://github.com/BerriAI/litellm/pull/11685) @@ -126,9 +126,9 @@ This version is not out yet. ## Spend Tracking #### Bugs -- **End Users** +- **[End Users](../../docs/proxy/customers)** - Update enduser spend and budget reset date based on budget duration - [PR](https://github.com/BerriAI/litellm/pull/8460) (s/o [laurien16](https://github.com/laurien16)) -- **Custom Pricing** +- **[Custom Pricing](../../docs/proxy/custom_pricing)** - Convert scientific notation str to int - [PR](https://github.com/BerriAI/litellm/pull/11655) --- @@ -136,11 +136,11 @@ This version is not out yet. ## Management Endpoints / UI #### Bugs -- **Users** +- **[Users](../../docs/proxy/users)** - `/user/info` - fix passing user with `+` in user id - Add admin-initiated password reset flow - [PR](https://github.com/BerriAI/litellm/pull/11618) - Fixes default user settings UI rendering error - [PR](https://github.com/BerriAI/litellm/pull/11674) -- **Budgets** +- **[Budgets](../../docs/proxy/users)** - Correct success message when new user budget is created - [PR](https://github.com/BerriAI/litellm/pull/11608) #### Features @@ -163,15 +163,15 @@ This version is not out yet. ## Logging / Guardrails Integrations #### Bugs -- **Arize** +- **[Arize](../../docs/observability/arize_integration)** - Change space_key header to space_id - [PR](https://github.com/BerriAI/litellm/pull/11595) (s/o [vanities](https://github.com/vanities)) -- **Prometheus** +- **[Prometheus](../../docs/proxy/prometheus)** - Fix total requests increment - [PR](https://github.com/BerriAI/litellm/pull/11718) #### Features -- **Lasso Guardrails** +- **[Lasso Guardrails](../../docs/proxy/guardrails/lasso_security)** - [NEW] Lasso Guardrails support - [PR](https://github.com/BerriAI/litellm/pull/11565) -- **Users** +- **[Users](../../docs/proxy/users)** - New `organizations` param on `/user/new` - allows adding users to orgs on creation - [PR](https://github.com/BerriAI/litellm/pull/11572/files) - **Prevent double logging when using bridge logic** - [PR](https://github.com/BerriAI/litellm/pull/11687) @@ -180,11 +180,11 @@ This version is not out yet. ## Performance / Reliability Improvements #### Bugs -- **Tag based routing** +- **[Tag based routing](../../docs/proxy/tag_routing)** - Do not consider ‘default’ models when request specifies a tag - [PR](https://github.com/BerriAI/litellm/pull/11454) (s/o [thiagosalvatore](https://github.com/thiagosalvatore)) #### Features -- **Caching** +- **[Caching](../../docs/caching/all_caches)** - New optional ‘litellm[caching]’ pip install for adding disk cache dependencies - [PR](https://github.com/BerriAI/litellm/pull/11600) --- diff --git a/docs/my-website/sidebars.js b/docs/my-website/sidebars.js index 48abfdd916..b71abf9bd0 100644 --- a/docs/my-website/sidebars.js +++ b/docs/my-website/sidebars.js @@ -14,7 +14,57 @@ /** @type {import('@docusaurus/plugin-content-docs').SidebarsConfig} */ const sidebars = { // // By default, Docusaurus generates a sidebar from the docs folder structure - + integrationsSidebar: [ + { type: "doc", id: "integrations/index" }, + { + type: "category", + label: "Observability", + items: [ + { + type: "autogenerated", + dirName: "observability" + } + ], + }, + { + type: "category", + label: "[Beta] Guardrails", + items: [ + "proxy/guardrails/quick_start", + ...[ + "proxy/guardrails/aim_security", + "proxy/guardrails/aporia_api", + "proxy/guardrails/bedrock", + "proxy/guardrails/lasso_security", + "proxy/guardrails/guardrails_ai", + "proxy/guardrails/lakera_ai", + "proxy/guardrails/pangea", + "proxy/guardrails/pii_masking_v2", + "proxy/guardrails/secret_detection", + "proxy/guardrails/custom_guardrail", + "proxy/guardrails/prompt_injection", + ].sort(), + ], + }, + { + type: "category", + label: "Alerting & Monitoring", + items: [ + "proxy/prometheus", + "proxy/alerting", + "proxy/pagerduty" + ].sort() + }, + { + type: "category", + label: "[Beta] Prompt Management", + items: [ + "proxy/prompt_management", + "proxy/custom_prompt_management" + ].sort() + }, + + ], // But you can create a sidebar manually tutorialSidebar: [ { type: "doc", id: "index" }, // NEW @@ -139,31 +189,10 @@ const sidebars = { items: [ "proxy/logging", "proxy/logging_spec", - "proxy/team_logging", - "proxy/prometheus", - "proxy/alerting", - "proxy/pagerduty"], - }, - { - type: "category", - label: "[Beta] Guardrails", - items: [ - "proxy/guardrails/quick_start", - ...[ - "proxy/guardrails/aim_security", - "proxy/guardrails/aporia_api", - "proxy/guardrails/bedrock", - "proxy/guardrails/lasso_security", - "proxy/guardrails/guardrails_ai", - "proxy/guardrails/lakera_ai", - "proxy/guardrails/pangea", - "proxy/guardrails/pii_masking_v2", - "proxy/guardrails/secret_detection", - "proxy/guardrails/custom_guardrail", - "proxy/guardrails/prompt_injection", - ].sort(), + "proxy/team_logging" ], }, + { type: "category", label: "Secret Managers", @@ -455,14 +484,7 @@ const sidebars = { }, ], }, - { - type: "category", - label: "[Beta] Prompt Management", - items: [ - "proxy/prompt_management", - "proxy/custom_prompt_management" - ], - }, + { type: "category", label: "Load Testing", @@ -473,44 +495,6 @@ const sidebars = { "load_test_rpm", ] }, - { - type: "category", - label: "Logging & Observability", - items: [ - "observability/agentops_integration", - "observability/langfuse_integration", - "observability/langfuse_otel_integration", - "observability/lunary_integration", - "observability/deepeval_integration", - "observability/mlflow", - "observability/gcs_bucket_integration", - "observability/langsmith_integration", - "observability/literalai_integration", - "observability/opentelemetry_integration", - "observability/logfire_integration", - "observability/argilla", - "observability/arize_integration", - "observability/phoenix_integration", - "debugging/local_debugging", - "observability/raw_request_response", - "observability/custom_callback", - "observability/humanloop", - "observability/scrub_data", - "observability/braintrust", - "observability/sentry", - "observability/lago", - "observability/helicone_integration", - "observability/openmeter", - "observability/promptlayer_integration", - "observability/wandb_integration", - "observability/slack_integration", - "observability/athina_integration", - "observability/greenscale_integration", - "observability/supabase_integration", - `observability/telemetry`, - "observability/opik_integration", - ], - }, { type: "category", label: "Tutorials",