Added NSFW text validator

backend/Dockerfile

@@ -47,6 +47,14 @@ RUN --mount=type=cache,target=/root/.cache/uv \
 # Install pinned spaCy model in the final environment used at runtime.
 RUN python -m pip install --no-deps "${SPACY_MODEL_WHEEL_URL}"
 
+# Set HuggingFace cache directory
+ENV HF_HOME=/app/hf_cache
+
+# Pre-download HuggingFace model
+RUN /app/.venv/bin/python -c "from transformers import AutoTokenizer, AutoModelForSequenceClassification; \
+AutoTokenizer.from_pretrained('textdetox/xlmr-large-toxicity-classifier', cache_dir='/app/hf_cache'); \
+AutoModelForSequenceClassification.from_pretrained('textdetox/xlmr-large-toxicity-classifier', cache_dir='/app/hf_cache')"
+
 # -------------------------------
 # Entrypoint (runtime setup)
 # -------------------------------

backend/README.md

@@ -272,39 +272,24 @@ If verification succeeds, tenant's scope (`organization_id`, `project_id`) is re
 > Set `OPENAI_API_KEY` in your `.env` / `.env.test` before using these validators.
 > If the key is missing, `llm_critic` will raise a `ValueError` at build time and `topic_relevance` will return a validation failure with an explicit error message.
 
-1. Ensure that the .env file contains the correct value from `GUARDRAILS_HUB_API_KEY`. The key can be fetched from [here](https://hub.guardrailsai.com/keys).
+1. Ensure that the `.env` file contains the correct value for `GUARDRAILS_HUB_API_KEY`. The key can be fetched from [here](https://hub.guardrailsai.com/keys).
 
-2. Make the `install_guardrails_from_hub.sh` script executable using this command (run this from the `backend` folder) -
+2. Make the `install_guardrails_from_hub.sh` script executable (run from the `backend` folder):
 
 ```bash
 chmod +x scripts/install_guardrails_from_hub.sh
 ```
-3. Run this command to configure Guardrails AI -
 
-```bash
-scripts/install_guardrails_from_hub.sh;        
-```
-
-### Alternate Method
-Run the following commands inside your virtual environment:
+3. Run the script to configure Guardrails and install all hub validators:
 
 ```bash
-uv sync
-guardrails configure
-
-Enable anonymous metrics reporting? [Y/n]: Y
-Do you wish to use remote inferencing? [Y/n]: Y
-Enter API Key below leave empty if you want to keep existing token [HBPo]
-👉 You can find your API Key at https://hub.guardrailsai.com/keys
+GUARDRAILS_HUB_API_KEY=<your-key> bash scripts/install_guardrails_from_hub.sh
 ```
 
-To install any validator from Guardrails Hub:
-```bash
-guardrails hub install hub://guardrails/<validator-name>
-
-Example -
-guardrails hub install hub://guardrails/ban_list
-```
+> **Remote inferencing is enabled by default.** The script sets `ENABLE_REMOTE_INFERENCING=true` unless overridden. This is required for `llamaguard_7b`, which runs inference on the Guardrails Hub. You can disable it explicitly if needed:
+> ```bash
+> GUARDRAILS_HUB_API_KEY=<your-key> ENABLE_REMOTE_INFERENCING=false bash scripts/install_guardrails_from_hub.sh
+> ```
 
 ## Adding a new validator from Guardrails Hub
 To add a new validator from the Guardrails Hub to this project, follow the steps below.

backend/app/api/API_USAGE.md

@@ -100,7 +100,7 @@ Endpoint:
 Optional filters:
 - `ids=<uuid>&ids=<uuid>`
 - `stage=input|output`
-- `type=uli_slur_match|pii_remover|gender_assumption_bias|ban_list|llm_critic|topic_relevance`
+- `type=uli_slur_match|pii_remover|gender_assumption_bias|ban_list|llm_critic|topic_relevance|llamaguard_7b|profanity_free|nsfw_text`
 
 Example:
 
@@ -442,6 +442,9 @@ From `validators.json`:
 - `ban_list`
 - `llm_critic`
 - `topic_relevance`
+- `llamaguard_7b`
+- `profanity_free`
+- `nsfw_text`
 
 Source of truth:
 - `backend/app/core/validators/validators.json`

backend/app/api/docs/guardrails/run_guardrails.md

@@ -8,6 +8,16 @@ Behavior notes:
 - For `ban_list`, `ban_list_id` can be resolved to `banned_words` from tenant ban list configs.
 - For `topic_relevance`, `topic_relevance_config_id` is required and is resolved to `configuration` + `prompt_schema_version` from tenant topic relevance configs in `guardrails.py`. Requires `OPENAI_API_KEY` to be configured; returns a validation failure with an explicit error if missing.
 - For `llm_critic`, `OPENAI_API_KEY` must be configured; returns `success=false` with an explicit error if missing.
+- For `llamaguard_7b`, `policies` accepts human-readable policy names (see table below). If omitted, all policies are enforced by default.
+
+  | `policies` value            | Policy enforced                  |
+  |-----------------------------|----------------------------------|
+  | `no_violence_hate`          | No violence or hate speech       |
+  | `no_sexual_content`         | No sexual content                |
+  | `no_criminal_planning`      | No criminal planning             |
+  | `no_guns_and_illegal_weapons` | No guns or illegal weapons     |
+  | `no_illegal_drugs`          | No illegal drugs                 |
+  | `no_encourage_self_harm`    | No encouragement of self-harm    |
 - `rephrase_needed=true` means the system could not safely auto-fix the input/output and wants the user to retry with a rephrased query.
 - When `rephrase_needed=true`, `safe_text` contains the rephrase prompt shown to the user.
 

backend/app/api/routes/guardrails.py

@@ -258,6 +258,9 @@ def add_validator_logs(
     for log in iteration.outputs.validator_logs:
         result = log.validation_result
 
+        if result is None:
+            continue
+
         if suppress_pass_logs and isinstance(result, PassResult):
             continue
 

backend/app/core/enum.py

@@ -32,3 +32,7 @@ class ValidatorType(Enum):
     GenderAssumptionBias = "gender_assumption_bias"
     BanList = "ban_list"
     TopicRelevance = "topic_relevance"
+    LLMCritic = "llm_critic"
+    LlamaGuard7B = "llamaguard_7b"
+    ProfanityFree = "profanity_free"
+    NSFWText = "nsfw_text"