Regex filters

Verified Code examples on this page have been automatically tested and verified.

Match and redact prompt content with custom regex patterns or agentgateway’s built-in PII detectors.

Use custom regex patterns and built-in PII detectors to filter LLM requests and responses.

About regex prompt templating

Regex-based prompt guards let you inspect LLM requests and responses against custom regex patterns or built-in PII detectors. Use the reject action to block requests that match a pattern, or the mask action to redact sensitive data in responses before they reach the client.

Built-in prompt guard patterns

Agentgateway includes the following built-in patterns for common PII types that you can reference in your prompt guards.

Pattern	Description
email	Email addresses
phoneNumber	Phone numbers
ssn	Social Security Numbers
creditCard	Credit card numbers
caSin	Canadian Social Insurance Numbers

Custom regex patterns

Use custom patterns to match credentials, secrets, or application-specific sensitive data.

llm:
  models:
  - name: "*"
    provider: openAI
    params:
      model: gpt-4o-mini
      apiKey: "$OPENAI_API_KEY"
    guardrails:
      request:
      - regex:
          action: reject
          rules:
          - pattern: "password[=:]\\s*\\S+"
          - pattern: "api[_-]?key[=:]\\s*\\S+"
          - pattern: "secret[=:]\\s*\\S+"
        rejection:
          status: 400
          headers:
            set:
              content-type: "application/json"
          body: |
            {
              "error": {
                "message": "Request contains credentials",
                "type": "invalid_request_error",
                "code": "credentials_detected"
              }
            }

Before you begin

Install the agentgateway binary.

PII detection

The following example rejects requests that contain PII data, such as Social Security Numbers (using a custom keyword pattern) or email addresses (using the built-in email pattern). When a request is blocked, agentgateway returns a custom error response.

1. Create a configuration file with regex prompt guard policies.

   cat <<'EOF' > config.yaml
   # yaml-language-server: $schema=https://agentgateway.dev/schema/config
   llm:
     models:
     - name: "*"
       provider: openAI
       params:
         model: gpt-4o-mini
         apiKey: "$OPENAI_API_KEY"
       guardrails:
         request:
         - regex:
             action: reject
             rules:
             - pattern: SSN
             - pattern: Social Security
           rejection:
             status: 400
             headers:
               set:
                 content-type: "application/json"
             body: |
               {
                 "error": {
                   "message": "Request rejected: Content contains sensitive information",
                   "type": "invalid_request_error",
                   "code": "content_policy_violation"
                 }
               }
         - regex:
             action: reject
             rules:
             - builtin: email
           rejection:
             status: 400
             headers:
               set:
                 content-type: "application/json"
             body: |
               {
                 "error": {
                   "message": "Request blocked: Contains email address",
                   "type": "invalid_request_error",
                   "code": "pii_detected"
                 }
               }
   EOF

   Setting	Description
   regex.action	The action to take when a pattern matches. Use reject to block the request or mask to redact matched content.
   regex.rules	List of patterns to match against.
   pattern	A custom regex pattern.
   builtin	A built-in PII pattern. See Built-in patterns for available options.
   rejection	Custom response returned when a request is blocked. Specify an HTTP status code, response headers, and a body.

2. Start the agentgateway.

   agentgateway -f config.yaml

3. In a new terminal, send a request to your LLM provider. Verify that the request succeeds.

   curl http://localhost:4000/v1/chat/completions \
     -H "Content-Type: application/json" \
     -d '{
       "model": "gpt-4o-mini",
       "messages": [{"role": "user", "content": "Hello, how are you?"}]
     }'

   Example output:

   :0},"prompt_tokens_details":{"cached_tokens":0,
   "audio_tokens":0}},"choices":[{"message":
   {"content":"Hello! I'm just a program, but I'm here and
   ready to help you. How can I assist you today?",
   "role":"assistant","refusal":null,"annotations":[]},
   "index":0,"logprobs":null,"finish_reason":"stop"}],
   "id":"chatcmpl-DHwlvtADPu5ZFznynSpmSjXL4B6W3",
   "object":"chat.completion",
   "service_tier":"default",
   "system_fingerprint":"fp_a1ddba3226"}

4. Send a request containing the SSN keyword. The prompt guard blocks the request and returns your custom error response.

   curl http://localhost:4000/v1/chat/completions \
     -H "Content-Type: application/json" \
     -d '{
       "model": "gpt-4o-mini",
       "messages": [{"role": "user", "content": "My SSN is 123-45-6789"}]
     }'

   Example output:

   {
     "error": {
       "message": "Request rejected: Content contains sensitive information",
       "type": "invalid_request_error",
       "code": "content_policy_violation"
     }
   }

5. Send another request with an email address. The prompt guard blocks it by using the built-in email pattern.

   curl http://localhost:4000/v1/chat/completions \
     -H "Content-Type: application/json" \
     -d '{
       "model": "gpt-4o-mini",
       "messages": [{"role": "user", "content": "Contact me at [email protected]"}]
     }'

   Example output:

   {
     "error": {
       "message": "Request blocked: Contains email address",
       "type": "invalid_request_error",
       "code": "pii_detected"
     }
   }

Mask PII in responses

You can also filter LLM responses to redact sensitive data before it reaches the client. When a match is found, agentgateway replaces built-in pattern matches with <ENTITY_TYPE> (for example, <CREDIT_CARD>) and custom pattern matches with <masked>. The following example masks credit card numbers in responses.

Warning

Masking applies only to a buffered response. When the client sets "stream": true , the LLM response is streamed, and agentgateway cannot rewrite content that is already on its way to the client. A response guard that uses action: mask passes the matched content through unmodified, and the client receives no error. To protect a streamed response, use action: reject and set streaming: Enabled . For more information, see Streaming guardrails .

1. Create a configuration that masks phone numbers in LLM responses by using the built-in phoneNumber pattern.

   cat <<'EOF' > config.yaml
   # yaml-language-server: $schema=https://agentgateway.dev/schema/config
   llm:
     models:
     - name: "*"
       provider: openAI
       params:
         model: gpt-4o-mini
         apiKey: "$OPENAI_API_KEY"
       guardrails:
         response:
         - regex:
             action: mask
             rules:
             - builtin: phoneNumber
   EOF

2. Start the agentgateway.

   agentgateway -f config.yaml

3. In a new terminal, send a request to your LLM provider with a phone number and verify that the number is masked in your response.

   curl http://localhost:4000/v1/chat/completions \
     -H "Content-Type: application/json" \
     -d '{
       "model": "gpt-4o-mini",
       "messages": [{"role": "user", "content": "What number is 919 222 1111?"}]
     }'

   Example output:

   {"model":"gpt-4o-mini-2024-07-18","usage":
   {"prompt_tokens":18,"completion_tokens":57,
   "total_tokens":75,"completion_tokens_details":
   {"reasoning_tokens":0,"audio_tokens":0,
   "accepted_prediction_tokens":0,
   "rejected_prediction_tokens":0},"prompt_tokens_details":
   {"cached_tokens":0,"audio_tokens":0}},"choices":
   [{"message":{"content":"The number <PHONE_NUMBER>appears
   to be a phone number in the United States. The area code
   919 serves parts of North Carolina, including cities
   like Raleigh and Durham. If you have a specific
   question or need more information regarding this
   number, please let me know!","role":"assistant",
   "refusal":null,"annotations":[]},"index":0,
   "logprobs":null,"finish_reason":"stop"}],
   "id":"chatcmpl-DHxEv3O5VOQPCmIVPruRiToal0rIe","object":"chat.completion","created":1773171665,
   "service_tier":"default",
   "system_fingerprint":"fp_a1ddba3226"}%