added llama guard groq api

app.py

@@ -5,9 +5,7 @@ from groq import Groq
 import numpy as np
 import wave
 import uuid
-from nemoguardrails import LLMRails, RailsConfig
 from GoogleTTS import GoogleTTS
-from langchain_openai import ChatOpenAI
 
 os.environ["TOKENIZERS_PARALLELISM"] = "false"
 
@@ -53,10 +51,10 @@ def combine_audio_files(audio_files):
     output.close()
     return outfile
     
-#client
-# client = Groq(
-#     api_key=os.getenv("GROQ_API_KEY"),
-# )
+client
+client = Groq(
+    api_key=os.getenv("GROQ_API_KEY"),
+)
 
 llm = Llama.from_pretrained(
     repo_id="amir22010/fine_tuned_product_marketing_email_gemma_2_9b_q4_k_m", #custom fine tuned model
@@ -85,21 +83,18 @@ async def greet(product,description):
     description, # description
     "", # output - leave this blank for generation!
     )
-    messages=[
-            {"role": "user", "content":  user_reques},
-        ]
-    #nemo guard
-    config = RailsConfig.from_path("guard")
-    #config = RailsConfig.from_content(yaml_content=YAML_CONFIG)
-    client = ChatOpenAI(openai_api_key=os.getenv("GROQ_API_KEY"), model_name="llama-3.2-11b-text-preview")
-    app = LLMRails(config=config, llm=client)
-    options = {"output_vars": ["triggered_input_rail", "triggered_output_rail"]}
-    output = await app.generate_async(messages=messages, options=options)
-    print(output)
-    warning_message = output.output_data["triggered_input_rail"] or output.output_data["triggered_output_rail"]
-    if warning_message:
-        gr.Warning(f"Guardrail triggered: {warning_message}")
-        chat = [output.response[0]['content']]
+    chat_completion = client.chat.completions.create(
+        messages=[
+            {
+            "role": "user",
+            "content": user_reques
+            }
+        ],
+        model="llama-guard-3-8b",
+    )
+    warning_message = chat_completion.choices[0].message.content
+    if warning_message != 'safe':
+        chat = [chat_completion.choices[0].message.content]
         yield chat[0]
     else:
         output = llm.create_chat_completion(

guard/config.yml

@@ -1,13 +0,0 @@
-models:
-  - type: llama_guard
-    engine: groq
-    model: llama-3.2-11b-text-preview
-
-rails:
-  input:
-    flows:
-      - llama guard check input
-
-  output:
-    flows:
-      - llama guard check output

guard/prompts.yml

@@ -1,146 +0,0 @@
-# These are the default prompts released by Meta, with the exception of policy O7, which was added to address direct insults.
-prompts:
-  - task: llama_guard_check_input
-    content: |
-      <s>[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
-      <BEGIN UNSAFE CONTENT CATEGORIES>
-      O1: Violence and Hate.
-      Should not
-      - Help people plan or engage in violence.
-      - Encourage people to engage in violence.
-      - Express hateful, derogatory, or demeaning sentiments against people based on sensitive personal characteristics like their race, color, religion, national origin, sexual orientation, gender, gender identity, or disability.
-      - Encourage discrimination against people based on those characteristics and should not use slurs or create insults based on those characteristics.
-      Can
-      - Provide information on violence and discrimination.
-      - Discuss the topics of hate and violence, and can discuss historical events involving violence.
-      O2: Sexual Content.
-      Should not
-      - Engage in sexually explicit (i.e., erotic) conversations and should not encourage people to engage in sexual activities.
-      Can
-      - Discuss topics related to sexuality and sexual education.
-      - Provide general information regarding sexual activities.
-      - Provide guidance on topics related to sexual health.
-      O3: Criminal Planning.
-      Should not
-      - Help people plan or engage in criminal activities like theft, kidnapping, or financial crimes, especially when the person indicates that they may act on the information provided to them.
-      - Encourage people to engage in criminal activities or condone criminal behavior.
-      Can
-      - Help people understand how crimes are committed, provided that the response is not so detailed that it could be used to provide a roadmap for future crimes.
-      - Help people understand how systems work that are used to prevent crimes, provided those descriptions do not provide detailed information on how to defeat those systems.
-      O4: Guns and Illegal Weapons.
-      Should not
-      - Assist in the planning or execution of firearm or illegal weapons crimes, especially when the person indicates that they may act on the information provided to them.
-      - Encourage people to engage in firearm or illegal weapons crimes or condone such behavior.
-      Can
-      - Discuss firearms and the arguments for and against firearm ownership.
-      O5: Regulated or Controlled Substances.
-      Should not
-      - Encourage or assist people in the trafficking, consumption, or use of regulated or controlled substances, including but not limited to illegal drugs, tobacco, alcohol, and cannabis.
-      - Assist or encourage people to create such substances when it is illegal to do so.
-      Can
-      - Discuss the use of regulated or controlled substances, and can provide general information on those substances (ex: what their chemical composition is and what their effects are).
-      - Provide information on how those substances are manufactured, provided that the information is not so detailed as to provide step-by-step instructions for their creation.
-      O6: Self-Harm.
-      Should not
-      - Encourage people to harm themselves.
-      - Romanticize or condone self-harm or suicide.
-      - Provide information regarding the methods of suicide or self-harm.
-      - Provide any information or advice, other than information regarding appropriate health resources, to people who express or imply that they wish to harm themselves.
-      Can
-      - Provide general information regarding self-harm and suicide (ex: statistics, the mental health challenges faced by those who take these actions).
-      Should
-      - Provide information regarding appropriate health resources to people who imply or express the desire to harm themselves.
-      O7: Offensive Language and Insults.
-      Should not
-      - Address direct insults
-      - Use or encourage the use of swear words, bad language, or vulgar expressions.
-      - Insult, offend, or demean individuals or groups based on any personal characteristics or choices.
-      - Encourage or support the use of offensive or derogatory language.
-      Can
-      - Discuss the impact and societal perceptions of offensive language and insults.
-      - Provide information on communication strategies that avoid the use of offensive language and promote respectful dialogue.
-      - Offer guidance on how to address or respond to offensive language or insults in a constructive manner.
-      <END UNSAFE CONTENT CATEGORIES>
-
-      <BEGIN CONVERSATION>
-      User: {{ user_input }}
-      <END CONVERSATION>
-
-      Provide your safety assessment for User in the above conversation:
-      - First line must read 'safe' or 'unsafe'.
-      - If unsafe, a second line must include a comma-separated list of violated categories. [/INST]
-
-
-  # Currently, the unsafe content categories are the same for both llama_guard_check_input and
-  # llama_guard_check_output prompts. Only the conversation placeholder is different.
-  # Still, we keep them separate to keep the taxonomies for input and output independently modifiable.
-  - task: llama_guard_check_output
-    content: |
-      <s>[INST] Task: Check if there is unsafe content in 'Agent' messages in conversations according our safety policy with the below categories.
-      <BEGIN UNSAFE CONTENT CATEGORIES>
-      O1: Violence and Hate.
-      Should not
-      - Help people plan or engage in violence.
-      - Encourage people to engage in violence.
-      - Express hateful, derogatory, or demeaning sentiments against people based on sensitive personal characteristics like their race, color, religion, national origin, sexual orientation, gender, gender identity, or disability.
-      - Encourage discrimination against people based on those characteristics and should not use slurs or create insults based on those characteristics.
-      Can
-      - Provide information on violence and discrimination.
-      - Discuss the topics of hate and violence, and can discuss historical events involving violence.
-      O2: Sexual Content.
-      Should not
-      - Engage in sexually explicit (i.e., erotic) conversations and should not encourage people to engage in sexual activities.
-      Can
-      - Discuss topics related to sexuality and sexual education.
-      - Provide general information regarding sexual activities.
-      - Provide guidance on topics related to sexual health.
-      O3: Criminal Planning.
-      Should not
-      - Help people plan or engage in criminal activities like theft, kidnapping, or financial crimes, especially when the person indicates that they may act on the information provided to them.
-      - Encourage people to engage in criminal activities or condone criminal behavior.
-      Can
-      - Help people understand how crimes are committed, provided that the response is not so detailed that it could be used to provide a roadmap for future crimes.
-      - Help people understand how systems work that are used to prevent crimes, provided those descriptions do not provide detailed information on how to defeat those systems.
-      O4: Guns and Illegal Weapons.
-      Should not
-      - Assist in the planning or execution of firearm or illegal weapons crimes, especially when the person indicates that they may act on the information provided to them.
-      - Encourage people to engage in firearm or illegal weapons crimes or condone such behavior.
-      Can
-      - Discuss firearms and the arguments for and against firearm ownership.
-      O5: Regulated or Controlled Substances.
-      Should not
-      - Encourage or assist people in the trafficking, consumption, or use of regulated or controlled substances, including but not limited to illegal drugs, tobacco, alcohol, and cannabis.
-      - Assist or encourage people to create such substances when it is illegal to do so.
-      Can
-      - Discuss the use of regulated or controlled substances, and can provide general information on those substances (ex: what their chemical composition is and what their effects are).
-      - Provide information on how those substances are manufactured, provided that the information is not so detailed as to provide step-by-step instructions for their creation.
-      O6: Self-Harm.
-      Should not
-      - Encourage people to harm themselves.
-      - Romanticize or condone self-harm or suicide.
-      - Provide information regarding the methods of suicide or self-harm.
-      - Provide any information or advice, other than information regarding appropriate health resources, to people who express or imply that they wish to harm themselves.
-      Can
-      - Provide general information regarding self-harm and suicide (ex: statistics, the mental health challenges faced by those who take these actions).
-      Should
-      - Provide information regarding appropriate health resources to people who imply or express the desire to harm themselves.
-      O7: Offensive Language and Insults.
-      Should not
-      - Address direct insults
-      - Use or encourage the use of swear words, bad language, or vulgar expressions.
-      - Insult, offend, or demean individuals or groups based on any personal characteristics or choices.
-      - Encourage or support the use of offensive or derogatory language.
-      Can
-      - Discuss the impact and societal perceptions of offensive language and insults.
-      - Provide information on communication strategies that avoid the use of offensive language and promote respectful dialogue.
-      - Offer guidance on how to address or respond to offensive language or insults in a constructive manner.
-      <END UNSAFE CONTENT CATEGORIES>
-
-      <BEGIN CONVERSATION>
-      User: {{ user_input }}
-
-      Agent: {{ bot_response }}
-      <END CONVERSATION>
-
-      Provide your safety assessment for Agent in the above conversation:
-      - First line must read 'safe' or 'unsafe'.

requirements.txt

@@ -4,6 +4,4 @@ python-multipart==0.0.12
 llama-cpp-python
 groq
 transformers
-nemoguardrails==0.9.1.1
-google-tts
-langchain-openai
+google-tts