fix(examples): correct nim_base_url to avoid doubled /v1/ in combined notebook

Address Greptile feedback on PR #1906 (combined_guardrails_nim.ipynb).

The local-deployment override set `nim_base_url = "http://localhost:8125/v1/"`,
which collides with `nim_server_endpoint = "/v1/security/nvidia/nemoguard-jailbreak-detect"`
(set in the YAML and not overridden). The `join_nim_url` helper in
`nemoguardrails/library/jailbreak_detection/request.py` rstrips the base's
trailing slash, lstrips the endpoint's leading slash, and urljoins the two
relatively — producing `http://localhost:8125/v1/v1/security/.../nemoguard-jailbreak-detect`
(double `/v1/`, 404 from the NIM). Local jailbreak detection was silently
bypassed.

Fix: drop the `/v1/` suffix from the local base, matching the remote pattern
(`https://ai.api.nvidia.com`) and the canonical NemoGuard NIM examples in
the repo docs (caching/model-memory-cache.md, the tracing tutorial). The
`/v1` already lives in nim_server_endpoint; both deployments now follow the
same convention.

The cell 7 markdown is updated with a "Note on the jailbreak-detection NIM
URL convention" paragraph explaining the rule and the join_nim_url mechanism
so future readers don't trip on this.

Note: this is a pre-existing bug on `develop` (combined_guardrails_nim.ipynb
was inherited unchanged for PR #1906). The same incorrect pattern also lives
in jailbreak_detection_nim.ipynb on dev/schilton/update-docs-and-tutorials
and will need the same fix when that notebook ships.

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

Author: svenchilton

examples/notebooks/combined_guardrails_nim.ipynb

@@ -130,201 +130,14 @@
   {
    "cell_type": "markdown",
    "metadata": {},
-   "source": [
-    "## Combined Configuration\n",
-    "\n",
-    "All four guardrails are configured in a single `RailsConfig`. The `prompts` section provides the safety classification templates for the content safety and topic control NIMs."
-   ]
+   "source": "## Combined Configuration\n\nAll four guardrails are configured in a single `RailsConfig`. The `prompts` section provides the safety classification templates for the content safety and topic control NIMs.\n\n**Note on the jailbreak-detection NIM URL convention.** For the NemoGuard NIM, `nim_base_url` should NOT include a `/v1/` suffix — the `/v1` lives in `nim_server_endpoint` (set to `/v1/security/nvidia/nemoguard-jailbreak-detect` in the YAML below). The [`join_nim_url`](../../nemoguardrails/library/jailbreak_detection/request.py) helper rstrips the base's trailing slash, lstrips the endpoint's leading slash, and `urljoin`s the two relatively — so a `/v1/` in the base would produce a doubled-path 404 (e.g., `http://localhost:8125/v1/v1/security/...`). The convention applies to both remote and local deployments; the local override below preserves it.\n"
   },
   {
    "cell_type": "code",
    "execution_count": null,
    "metadata": {},
    "outputs": [],
-   "source": [
-    "# For remote deployment:\n",
-    "# import os\n",
-    "# os.environ[\"NVIDIA_API_KEY\"] = \"nvapi-...\"\n",
-    "\n",
-    "YAML_CONFIG = \"\"\"\n",
-    "models:\n",
-    "  - type: main\n",
-    "    engine: nim\n",
-    "    model: meta/llama-3.1-8b-instruct\n",
-    "\n",
-    "  - type: content_safety\n",
-    "    engine: nim\n",
-    "    model: nvidia/llama-3.1-nemotron-safety-guard-8b-v3\n",
-    "\n",
-    "  - type: topic_control\n",
-    "    engine: nim\n",
-    "    model: nvidia/llama-3.1-nemoguard-8b-topic-control\n",
-    "\n",
-    "rails:\n",
-    "  input:\n",
-    "    flows:\n",
-    "      - jailbreak detection model\n",
-    "      - content safety check input $model=content_safety\n",
-    "      - topic safety check input $model=topic_control\n",
-    "      - gliner detect pii on input\n",
-    "  output:\n",
-    "    flows:\n",
-    "      - content safety check output $model=content_safety\n",
-    "      - gliner detect pii on output\n",
-    "  config:\n",
-    "    gliner:\n",
-    "      threshold: 0.5\n",
-    "      input:\n",
-    "        entities:\n",
-    "          - first_name\n",
-    "          - last_name\n",
-    "          - ssn\n",
-    "          - date_of_birth\n",
-    "          - phone_number\n",
-    "          - street_address\n",
-    "          - email\n",
-    "      output:\n",
-    "        entities:\n",
-    "          - first_name\n",
-    "          - last_name\n",
-    "          - ssn\n",
-    "          - date_of_birth\n",
-    "          - phone_number\n",
-    "          - email\n",
-    "    jailbreak_detection:\n",
-    "      nim_base_url: \"https://ai.api.nvidia.com\"\n",
-    "      nim_server_endpoint: \"/v1/security/nvidia/nemoguard-jailbreak-detect\"\n",
-    "      api_key_env_var: NVIDIA_API_KEY\n",
-    "\n",
-    "prompts:\n",
-    "  - task: content_safety_check_input $model=content_safety\n",
-    "    content: |\n",
-    "      Task: Check if there is unsafe content in the user or agent messages in the below conversation in accordance with our safety policy with the below categories. Provide a 'safe' or 'unsafe' rating for both the user message and the agent response. If there is unsafe content, please also provide a list of violated categories according to our safety policy below.\n",
-    "\n",
-    "      <BEGIN UNSAFE CONTENT CATEGORIES>\n",
-    "      S1: Violence.\n",
-    "      S2: Sexual.\n",
-    "      S3: Criminal Planning/Confessions.\n",
-    "      S4: Guns and Illegal Weapons.\n",
-    "      S5: Controlled/Regulated Substances.\n",
-    "      S6: Suicide and Self Harm.\n",
-    "      S7: Sexual (minor).\n",
-    "      S8: Hate/Identity Hate.\n",
-    "      S9: PII/Privacy.\n",
-    "      S10: Harassment.\n",
-    "      S11: Threat.\n",
-    "      S12: Profanity.\n",
-    "      S13: Needs Caution.\n",
-    "      S14: Other.\n",
-    "      S15: Manipulation.\n",
-    "      S16: Fraud/Deception.\n",
-    "      S17: Malware.\n",
-    "      S18: High Risk Gov Decision Making.\n",
-    "      S19: Political/Misinformation/Conspiracy.\n",
-    "      S20: Copyright/Trademark/Plagiarism.\n",
-    "      S21: Unauthorized Advice.\n",
-    "      S22: Illegal Activity.\n",
-    "      S23: Immoral/Unethical.\n",
-    "      <END UNSAFE CONTENT CATEGORIES>\n",
-    "\n",
-    "      <BEGIN CONVERSATION>\n",
-    "\n",
-    "      user: {{ user_input }}\n",
-    "\n",
-    "      <END CONVERSATION>\n",
-    "\n",
-    "      Provide your safety assessment for the above conversation in the below output JSON format:\n",
-    "      {\"User Safety\": safe or unsafe rating for the user message, \"Response Safety\": safe or unsafe rating for the agent response. Omit if no agent response present. \"Safety Categories\": a comma-separated list of applicable safety categories from the provided taxonomy. Omit if all safe.}\n",
-    "\n",
-    "      Do not include anything other than the output JSON in your response.\n",
-    "      Output JSON:\n",
-    "    output_parser: nemoguard_parse_prompt_safety\n",
-    "    max_tokens: 50\n",
-    "\n",
-    "  - task: content_safety_check_output $model=content_safety\n",
-    "    content: |\n",
-    "      Task: Check if there is unsafe content in the user or agent messages in the below conversation in accordance with our safety policy with the below categories. Provide a 'safe' or 'unsafe' rating for both the user message and the agent response. If there is unsafe content, please also provide a list of violated categories according to our safety policy below.\n",
-    "\n",
-    "      <BEGIN UNSAFE CONTENT CATEGORIES>\n",
-    "      S1: Violence.\n",
-    "      S2: Sexual.\n",
-    "      S3: Criminal Planning/Confessions.\n",
-    "      S4: Guns and Illegal Weapons.\n",
-    "      S5: Controlled/Regulated Substances.\n",
-    "      S6: Suicide and Self Harm.\n",
-    "      S7: Sexual (minor).\n",
-    "      S8: Hate/Identity Hate.\n",
-    "      S9: PII/Privacy.\n",
-    "      S10: Harassment.\n",
-    "      S11: Threat.\n",
-    "      S12: Profanity.\n",
-    "      S13: Needs Caution.\n",
-    "      S14: Other.\n",
-    "      S15: Manipulation.\n",
-    "      S16: Fraud/Deception.\n",
-    "      S17: Malware.\n",
-    "      S18: High Risk Gov Decision Making.\n",
-    "      S19: Political/Misinformation/Conspiracy.\n",
-    "      S20: Copyright/Trademark/Plagiarism.\n",
-    "      S21: Unauthorized Advice.\n",
-    "      S22: Illegal Activity.\n",
-    "      S23: Immoral/Unethical.\n",
-    "      <END UNSAFE CONTENT CATEGORIES>\n",
-    "\n",
-    "      <BEGIN CONVERSATION>\n",
-    "\n",
-    "      user: {{ user_input }}\n",
-    "\n",
-    "      response: agent: {{ bot_response }}\n",
-    "\n",
-    "      <END CONVERSATION>\n",
-    "\n",
-    "      Provide your safety assessment for the above conversation in the below output JSON format:\n",
-    "      {\"User Safety\": safe or unsafe rating for the user message, \"Response Safety\": safe or unsafe rating for the agent response. Omit if no agent response present. \"Safety Categories\": a comma-separated list of applicable safety categories from the provided taxonomy. Omit if all safe.}\n",
-    "\n",
-    "      Do not include anything other than the output JSON in your response.\n",
-    "      Output JSON:\n",
-    "    output_parser: nemoguard_parse_response_safety\n",
-    "    max_tokens: 50\n",
-    "\n",
-    "  - task: topic_safety_check_input $model=topic_control\n",
-    "    content: |\n",
-    "      You are a patient support assistant for a healthcare organization. Your role is to\n",
-    "      provide general health information, help patients understand symptoms and conditions,\n",
-    "      explain medications and treatments, and assist with appointment and administrative questions.\n",
-    "\n",
-    "      Guidelines:\n",
-    "      - Only answer questions related to health, wellness, medical conditions, treatments,\n",
-    "        medications, and healthcare administration.\n",
-    "      - Do not answer questions about finance, investments, politics, law, or any topic\n",
-    "        unrelated to healthcare.\n",
-    "      - Do not provide specific diagnoses or prescribe medications — always recommend\n",
-    "        consulting a healthcare professional for personalized medical advice.\n",
-    "      - Do not answer questions asking for personal details about the agent or its creators.\n",
-    "      - Allow health-related small talk and greetings.\n",
-    "      - For off-topic requests, politely redirect the conversation.\n",
-    "\"\"\"\n",
-    "\n",
-    "config = RailsConfig.from_content(yaml_content=YAML_CONFIG)\n",
-    "\n",
-    "# models order: [main, content_safety, topic_control]\n",
-    "if DEPLOYMENT == \"local\":\n",
-    "    config.models[0].parameters[\"base_url\"] = \"http://localhost:8001/v1\"\n",
-    "    config.models[1].parameters[\"base_url\"] = \"http://localhost:8123/v1\"\n",
-    "    config.models[1].parameters[\"model_name\"] = \"nvidia/llama-3.1-nemotron-safety-guard-8b-v3\"\n",
-    "    config.models[2].parameters[\"base_url\"] = \"http://localhost:8124/v1\"\n",
-    "    config.models[2].parameters[\"model_name\"] = \"nvidia/llama-3.1-nemoguard-8b-topic-control\"\n",
-    "    config.rails.config.gliner.server_endpoint = \"http://localhost:8000/v1/chat/completions\"\n",
-    "    config.rails.config.jailbreak_detection.nim_base_url = \"http://localhost:8125/v1/\"\n",
-    "elif DEPLOYMENT == \"remote\":\n",
-    "    config.models[0].api_key_env_var = \"NVIDIA_API_KEY\"\n",
-    "    config.models[1].api_key_env_var = \"NVIDIA_API_KEY\"\n",
-    "    config.models[2].api_key_env_var = \"NVIDIA_API_KEY\"\n",
-    "    config.rails.config.gliner.server_endpoint = \"https://integrate.api.nvidia.com/v1/chat/completions\"\n",
-    "    config.rails.config.gliner.api_key_env_var = \"NVIDIA_API_KEY\"\n",
-    "\n",
-    "rails = LLMRails(config)"
-   ]
+   "source": "# For remote deployment:\n# import os\n# os.environ[\"NVIDIA_API_KEY\"] = \"nvapi-...\"\n\nYAML_CONFIG = \"\"\"\nmodels:\n  - type: main\n    engine: nim\n    model: meta/llama-3.1-8b-instruct\n\n  - type: content_safety\n    engine: nim\n    model: nvidia/llama-3.1-nemotron-safety-guard-8b-v3\n\n  - type: topic_control\n    engine: nim\n    model: nvidia/llama-3.1-nemoguard-8b-topic-control\n\nrails:\n  input:\n    flows:\n      - jailbreak detection model\n      - content safety check input $model=content_safety\n      - topic safety check input $model=topic_control\n      - gliner detect pii on input\n  output:\n    flows:\n      - content safety check output $model=content_safety\n      - gliner detect pii on output\n  config:\n    gliner:\n      threshold: 0.5\n      input:\n        entities:\n          - first_name\n          - last_name\n          - ssn\n          - date_of_birth\n          - phone_number\n          - street_address\n          - email\n      output:\n        entities:\n          - first_name\n          - last_name\n          - ssn\n          - date_of_birth\n          - phone_number\n          - email\n    jailbreak_detection:\n      nim_base_url: \"https://ai.api.nvidia.com\"\n      nim_server_endpoint: \"/v1/security/nvidia/nemoguard-jailbreak-detect\"\n      api_key_env_var: NVIDIA_API_KEY\n\nprompts:\n  - task: content_safety_check_input $model=content_safety\n    content: |\n      Task: Check if there is unsafe content in the user or agent messages in the below conversation in accordance with our safety policy with the below categories. Provide a 'safe' or 'unsafe' rating for both the user message and the agent response. If there is unsafe content, please also provide a list of violated categories according to our safety policy below.\n\n      <BEGIN UNSAFE CONTENT CATEGORIES>\n      S1: Violence.\n      S2: Sexual.\n      S3: Criminal Planning/Confessions.\n      S4: Guns and Illegal Weapons.\n      S5: Controlled/Regulated Substances.\n      S6: Suicide and Self Harm.\n      S7: Sexual (minor).\n      S8: Hate/Identity Hate.\n      S9: PII/Privacy.\n      S10: Harassment.\n      S11: Threat.\n      S12: Profanity.\n      S13: Needs Caution.\n      S14: Other.\n      S15: Manipulation.\n      S16: Fraud/Deception.\n      S17: Malware.\n      S18: High Risk Gov Decision Making.\n      S19: Political/Misinformation/Conspiracy.\n      S20: Copyright/Trademark/Plagiarism.\n      S21: Unauthorized Advice.\n      S22: Illegal Activity.\n      S23: Immoral/Unethical.\n      <END UNSAFE CONTENT CATEGORIES>\n\n      <BEGIN CONVERSATION>\n\n      user: {{ user_input }}\n\n      <END CONVERSATION>\n\n      Provide your safety assessment for the above conversation in the below output JSON format:\n      {\"User Safety\": safe or unsafe rating for the user message, \"Response Safety\": safe or unsafe rating for the agent response. Omit if no agent response present. \"Safety Categories\": a comma-separated list of applicable safety categories from the provided taxonomy. Omit if all safe.}\n\n      Do not include anything other than the output JSON in your response.\n      Output JSON:\n    output_parser: nemoguard_parse_prompt_safety\n    max_tokens: 50\n\n  - task: content_safety_check_output $model=content_safety\n    content: |\n      Task: Check if there is unsafe content in the user or agent messages in the below conversation in accordance with our safety policy with the below categories. Provide a 'safe' or 'unsafe' rating for both the user message and the agent response. If there is unsafe content, please also provide a list of violated categories according to our safety policy below.\n\n      <BEGIN UNSAFE CONTENT CATEGORIES>\n      S1: Violence.\n      S2: Sexual.\n      S3: Criminal Planning/Confessions.\n      S4: Guns and Illegal Weapons.\n      S5: Controlled/Regulated Substances.\n      S6: Suicide and Self Harm.\n      S7: Sexual (minor).\n      S8: Hate/Identity Hate.\n      S9: PII/Privacy.\n      S10: Harassment.\n      S11: Threat.\n      S12: Profanity.\n      S13: Needs Caution.\n      S14: Other.\n      S15: Manipulation.\n      S16: Fraud/Deception.\n      S17: Malware.\n      S18: High Risk Gov Decision Making.\n      S19: Political/Misinformation/Conspiracy.\n      S20: Copyright/Trademark/Plagiarism.\n      S21: Unauthorized Advice.\n      S22: Illegal Activity.\n      S23: Immoral/Unethical.\n      <END UNSAFE CONTENT CATEGORIES>\n\n      <BEGIN CONVERSATION>\n\n      user: {{ user_input }}\n\n      response: agent: {{ bot_response }}\n\n      <END CONVERSATION>\n\n      Provide your safety assessment for the above conversation in the below output JSON format:\n      {\"User Safety\": safe or unsafe rating for the user message, \"Response Safety\": safe or unsafe rating for the agent response. Omit if no agent response present. \"Safety Categories\": a comma-separated list of applicable safety categories from the provided taxonomy. Omit if all safe.}\n\n      Do not include anything other than the output JSON in your response.\n      Output JSON:\n    output_parser: nemoguard_parse_response_safety\n    max_tokens: 50\n\n  - task: topic_safety_check_input $model=topic_control\n    content: |\n      You are a patient support assistant for a healthcare organization. Your role is to\n      provide general health information, help patients understand symptoms and conditions,\n      explain medications and treatments, and assist with appointment and administrative questions.\n\n      Guidelines:\n      - Only answer questions related to health, wellness, medical conditions, treatments,\n        medications, and healthcare administration.\n      - Do not answer questions about finance, investments, politics, law, or any topic\n        unrelated to healthcare.\n      - Do not provide specific diagnoses or prescribe medications — always recommend\n        consulting a healthcare professional for personalized medical advice.\n      - Do not answer questions asking for personal details about the agent or its creators.\n      - Allow health-related small talk and greetings.\n      - For off-topic requests, politely redirect the conversation.\n\"\"\"\n\nconfig = RailsConfig.from_content(yaml_content=YAML_CONFIG)\n\n# models order: [main, content_safety, topic_control]\nif DEPLOYMENT == \"local\":\n    config.models[0].parameters[\"base_url\"] = \"http://localhost:8001/v1\"\n    config.models[1].parameters[\"base_url\"] = \"http://localhost:8123/v1\"\n    config.models[1].parameters[\"model_name\"] = \"nvidia/llama-3.1-nemotron-safety-guard-8b-v3\"\n    config.models[2].parameters[\"base_url\"] = \"http://localhost:8124/v1\"\n    config.models[2].parameters[\"model_name\"] = \"nvidia/llama-3.1-nemoguard-8b-topic-control\"\n    config.rails.config.gliner.server_endpoint = \"http://localhost:8000/v1/chat/completions\"\n    config.rails.config.jailbreak_detection.nim_base_url = \"http://localhost:8125\"\nelif DEPLOYMENT == \"remote\":\n    config.models[0].api_key_env_var = \"NVIDIA_API_KEY\"\n    config.models[1].api_key_env_var = \"NVIDIA_API_KEY\"\n    config.models[2].api_key_env_var = \"NVIDIA_API_KEY\"\n    config.rails.config.gliner.server_endpoint = \"https://integrate.api.nvidia.com/v1/chat/completions\"\n    config.rails.config.gliner.api_key_env_var = \"NVIDIA_API_KEY\"\n\nrails = LLMRails(config)"
   },
   {
    "cell_type": "markdown",