scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-09 22:31:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 133

docs Logging / Guardrail Integrations

Browse source
This commit is contained in:
Ishaan Jaff 2025-05-10 16:40:25 -07:00
parent d087aa1620
commit c4074ec7a1
2 changed files with 23 additions and 19 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

8
docs/my-website/docs/proxy/guardrails/bedrock.md
View file

@ -144,7 +144,13 @@ Bedrock guardrails support PII detection and masking capabilities. To enable thi
Here's how to configure it in your config.yaml:
```yaml showLineNumbers title="litellm bedrock guardrailconfig.yaml"
```yaml showLineNumbers title="litellm proxy config.yaml"
model_list:
- model_name: gpt-3.5-turbo
litellm_params:
model: openai/gpt-3.5-turbo
api_key: os.environ/OPENAI_API_KEY
guardrails:
- guardrail_name: "bedrock-pre-guard"
litellm_params:

34
docs/my-website/release_notes/v1.69.0-stable/index.md
View file

@ -120,17 +120,11 @@ This new release brings support for:
## Logging / Guardrail Integrations
- **Custom Logger API**: v2 Custom Callback API (send llm logs to custom api) - [PR](https://github.com/BerriAI/litellm/pull/10575)
- **File Processing**:
- Unified File ID output support - [PR](https://github.com/BerriAI/litellm/pull/10713)
- Support for writing files to all deployments - [PR](https://github.com/BerriAI/litellm/pull/10708)
- Complete unified batch ID support - replacing model in jsonl to be deployment model name - [PR](https://github.com/BerriAI/litellm/pull/10719)
- Beta support for unified file ID (managed files) for batches - [PR](https://github.com/BerriAI/litellm/pull/10650)
- **Model Validation**:
- Added target model name validation - [PR](https://github.com/BerriAI/litellm/pull/10722)
- **JSON Logging**:
- Fixed bug where duplicate JSON logs were getting emitted - [PR](https://github.com/BerriAI/litellm/pull/10580)
- **Vector Stores**:
- Added documentation for StandardLoggingVectorStoreRequest - [PR](https://github.com/BerriAI/litellm/pull/10535)
- **OpenTelemetry**:
- Fixed OpenTelemetry to follow genai semantic conventions + support for 'instructions' param for TTS - [PR](https://github.com/BerriAI/litellm/pull/10608)
- ** Bedrock PII**:
- Add support for PII Masking with bedrock guardrails - [Get Started](https://docs.litellm.ai/docs/proxy/guardrails/bedrock#pii-masking-with-bedrock-guardrails), [PR](https://github.com/BerriAI/litellm/pull/10608)
- Added documentation for StandardLoggingVectorStoreRequest - [PR](https://github.com/BerriAI/litellm/pull/10535)
## Performance / Reliability Improvements
- **Python Compatibility**:
@ -141,8 +135,6 @@ This new release brings support for:
- Fixed cache miss for Gemini models with response_format - [PR](https://github.com/BerriAI/litellm/pull/10635)
- **Azure**:
- Fixed passing through of azure_ad_token_provider parameter - [PR](https://github.com/BerriAI/litellm/pull/10694)
- **OpenTelemetry**:
- Fixed OpenTelemetry to follow genai semantic conventions + support for 'instructions' param for TTS - [PR](https://github.com/BerriAI/litellm/pull/10608)
- **Databricks**:
- Fixed issue when Databricks uses external model and delta could be empty - [PR](https://github.com/BerriAI/litellm/pull/10540)
@ -150,11 +142,6 @@ This new release brings support for:
- **CLI**:
- Added `--version` flag to `litellm-proxy` CLI - [PR](https://github.com/BerriAI/litellm/pull/10704)
- Added dedicated `litellm-proxy` CLI - [PR](https://github.com/BerriAI/litellm/pull/10578)
- **Documentation**:
- Added management client documentation - [PR](https://github.com/BerriAI/litellm/pull/10703)
- Changed Llama-API link for LiteLLM - [PR](https://github.com/BerriAI/litellm/pull/10556)
- Added GPTLocalhost to projects docs - [PR](https://github.com/BerriAI/litellm/pull/10687)
- Updated Instructor documentation - [PR](https://github.com/BerriAI/litellm/pull/10549)
- **Enterprise**:
- Refactored to use pip package for enterprise folder - [PR](https://github.com/BerriAI/litellm/pull/10709)
- Added MCP Server DB Schema - [PR](https://github.com/BerriAI/litellm/pull/10641)
@ -167,6 +154,17 @@ This new release brings support for:
- **General**:
- Fixed bug where duplicate JSON logs were getting emitted - [PR](https://github.com/BerriAI/litellm/pull/10580)
- **File Processing**:
- Unified File ID output support - [PR](https://github.com/BerriAI/litellm/pull/10713)
- Support for writing files to all deployments - [PR](https://github.com/BerriAI/litellm/pull/10708)
- Complete unified batch ID support - replacing model in jsonl to be deployment model name - [PR](https://github.com/BerriAI/litellm/pull/10719)
- Beta support for unified file ID (managed files) for batches - [PR](https://github.com/BerriAI/litellm/pull/10650)
- **Model Validation**:
- Added target model name validation - [PR](https://github.com/BerriAI/litellm/pull/10722)
## New Contributors
- [@zoltan-ongithub](https://github.com/zoltan-ongithub) made their first contribution in [PR #10568](https://github.com/BerriAI/litellm/pull/10568)
- [@mkavinkumar1](https://github.com/mkavinkumar1) made their first contribution in [PR #10548](https://github.com/BerriAI/litellm/pull/10548)