LiteLLM setup fails with Presidio guardrail despite Analyzer/Anonymizer services working

[aksh-at-aeris]

What happened?

Description

Analyzer and Anonymizer services are working fine, however LiteLLM setup fails when using the Presidio guardrail.

Error:

---

Steps to Reproduce

1. Ensure Presidio Analyzer and Anonymizer services are running successfully.
2. Configure LiteLLM with the configuration below.
3. Run LiteLLM with guardrail: presidio and mode: pre_call.
4. Observe the ContentTypeError and 404 response.

---

Expected Behavior

LiteLLM should be able to successfully call Presidio Analyzer and then Anonymizer and receive a valid JSON response.

---

Actual Behavior

LiteLLM attempts a call to the Presidio Analyzer but ends with unexpected mimetype text/html.

---

LiteLLM Configuration

model_list:
  - model_name: claude-sonnet-4@20250514
    litellm_params:
      model: vertex_ai/claude-3-5-sonnet-v2@20241022
      vertex_ai_project: os.environ/PROJECT_ID
      vertex_ai_location: "global"
  - model_name: gemini-2.5-pro
    litellm_params:
      model: vertex_ai/gemini-2.5-pro
      vertex_ai_project: os.environ/PROJECT_ID
      vertex_ai_location: "global"
  - model_name: gemini-2.5-flash
    litellm_params:
      model: vertex_ai/gemini-2.5-flash
      vertex_ai_project: os.environ/PROJECT_ID
      vertex_ai_location: "global"
  - model_name: gemini-3-pro-preview
    litellm_params:
      model: vertex_ai/gemini-3-pro-preview
      vertex_ai_project: os.environ/PROJECT_ID
      vertex_ai_location: "global"
  - model_name: gpt-40
    litellm_params:
      model: azure/gpt-4o-chatgpt
      api_base: https://openai-poc-useast2.openai.azure.com/
      api_version: "2024-08-01-preview"
      api_key: os.environ/AZURE_API_KEY
  - model_name: gpt-4.1
    litellm_params:
      model: azure/gpt-4.1-*****
      api_base: https://openai-poc-useast2.openai.azure.com/
      api_version: "2024-08-01-preview"
      api_key: os.environ/AZURE_API_KEY
  - model_name: gpt-5
    litellm_params:
      model: azure/gpt-5-chat-*****
      api_base: https://openai-poc-useast2.openai.azure.com/
      api_version: "2025-01-01-preview"
      api_key: os.environ/AZURE_API_KEY
  - model_name: gemini-2.5-pro-preview-05-06
    litellm_params:
      model: vertex_ai/gemini-2.5-pro
      vertex_ai_project: os.environ/PROJECT_ID
      vertex_ai_location: "global"
  - model_name: gemini-2.5-flash-preview-04-17
    litellm_params:
      model: vertex_ai/gemini-2.5-flash
      vertex_ai_project: os.environ/PROJECT_ID
      vertex_ai_location: "global"
  - model_name: gemini-2.0-flash-exp
    litellm_params:
      model: vertex_ai/gemini-2.5-flash
      vertex_ai_project: os.environ/PROJECT_ID
      vertex_ai_location: "global"

guardrails:
  - guardrail_name: "presidio-pii"
    litellm_params:
      guardrail: presidio
      mode: "pre_call"
      default_on: true
      presidio_language: "en"

general_settings:
  master_key: ********

litellm_settings:
  drop_params: true

### Relevant log output

```shell
aiohttp.client_exceptions.ContentTypeError: 404, message='Attempt to decode JSON with unexpected mimetype: text/html; charset=utf-8', url='https://****-presidio-analyzer-******.us-west1.run.app/analyze'

Are you a ML Ops Team?

No

What LiteLLM version are you on ?

main branch

Twitter / LinkedIn details

No response