Fix: Changed keyword from assisstant to secretary

[V-Silpin]

Description

This PR fixes the issue of content policy trigger bug in Azure OpenAI LLM. The actual cause of this trigger was a keyword "assistant". So I have added some code which replaces the keyword to "secretary " in the user prompt in azure_openai.py and azure_openai_structured.py . By changing the keyword the Memory.add function is working properly, hence fixing the bug.

Fixes #2636

Type of change

• Bug fix (non-breaking change which fixes an issue)

How Has This Been Tested?

• Unit Test
• Test Script (please provide)

Test Script

from dotenv import load_dotenv
import os

from mem0.memory.main import Memory

load_dotenv()

llm_provider = os.getenv("AZURE_OPENAI_PROVIDER")
llm_model = os.getenv("AZURE_OPENAI_MODEL")
llm_temperature = float(os.getenv("AZURE_OPENAI_TEMPERATURE"))
llm_max_tokens = int(os.getenv("AZURE_OPENAI_MAX_TOKENS"))
llm_api_version = os.getenv("AZURE_OPENAI_API_VERSION")
llm_azure_deployment = os.getenv("AZURE_OPENAI_DEPLOYMENT")
llm_azure_endpoint = os.getenv("AZURE_OPENAI_ENDPOINT")
llm_api_key = os.getenv("AZURE_OPENAI_API_KEY")

vs_provider = os.getenv("AZURE_VECTOR_STORE_PROVIDER")
vs_service_name = os.getenv("AZURE_VECTOR_STORE_SERVICE_NAME")
vs_api_key = os.getenv("AZURE_VECTOR_STORE_API_KEY")
vs_collection_name = os.getenv("AZURE_VECTOR_STORE_COLLECTION_NAME_MEM")
vs_embedding_model_dims = int(os.getenv("AZURE_VECTOR_STORE_EMBEDDING_MODEL_DIMS"))

em_provider = os.getenv("EMBEDDING_AZURE_PROVIDER")
em_model = os.getenv("EMBEDDING_AZURE_MODEL")
em_api_version = os.getenv("EMBEDDING_AZURE_API_VERSION")
em_azure_deployment = os.getenv("EMBEDDING_AZURE_DEPLOYMENT")
em_azure_endpoint = os.getenv("EMBEDDING_AZURE_ENDPOINT")
em_api_key = os.getenv("EMBEDDING_AZURE_API_KEY")

config = {
    "llm": {
        "provider": llm_provider,
        "config": {
            "model": llm_model,
            "temperature": llm_temperature,
            "max_tokens": llm_max_tokens,
            "azure_kwargs": {
                  "azure_deployment": llm_azure_deployment,
                  "api_version": llm_api_version,
                  "azure_endpoint": llm_azure_endpoint,
                  "api_key": llm_api_key,
              }
        }
    },
    "vector_store": {
        "provider": vs_provider,
        "config": {
            "service_name": vs_service_name,
            "api_key": vs_api_key,
            "collection_name": vs_collection_name, 
            "embedding_model_dims": vs_embedding_model_dims,
        }
    },
    "embedder": {
        "provider": em_provider,
        "config": {
            "model": em_model,
            "api_key": em_api_key,
            "azure_kwargs": {
                  "api_version": em_api_version,
                  "azure_deployment": em_azure_deployment,
                  "azure_endpoint": em_azure_endpoint,
                  "api_key": em_api_key,
              }
        }
    }
}

os.environ["OPENAI_API_KEY"] = llm_api_key

print("Before creating memory")
mem = Memory.from_config(config_dict=config)
print("After creating memory")

messages = [
    {"role": "user", "content": "Hi, I'm Alex. I'm a vegetarian and I'm allergic to nuts."},
    {"role": "assistant", "content": "Hello Alex! I've noted that you're a vegetarian and have a nut allergy. I'll keep this in mind for any food-related recommendations or discussions."}
]

print(vars(mem))

print("Storing inferred memories")
result = mem.add(messages, user_id="alice", metadata={"category": "book_recommendations"})
print("Result of storing inferred memories")
print(result)

all_memories = mem.get_all(user_id="alice")
print("Mem from azure")
print(all_memories)

Checklist:

• My code follows the style guidelines of this project
• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• My changes generate no new warnings
• I have added tests that prove my fix is effective or that my feature works
• New and existing unit tests pass locally with my changes
• Any dependent changes have been merged and published in downstream modules
• I have checked my code and corrected any misspellings

Maintainer Checklist

• closes Memory.add triggering Azure OpenAI's content management policy #2636
• Made sure Checks passed

[CLAassistant]

All committers have signed the CLA.

[V-Silpin]

@prateekchhikara Can you pls review this PR which solves the issue #2636

[Dev-Khant]

Hey @V-Silpin Can you please sign the CLA contract?

[V-Silpin]

@Dev-Khant I have completed signing the CLA contract

[V-Silpin]

@Dev-Khant can you pls review & merge the code

[V-Silpin]

@Dev-Khant can you pls merge this PR, all the corrections are done.

Merging this PR will resolve this issue #2636

[prateekchhikara]

@V-Silpin, thanks for raising the PR. Could you please update the PR description to include the issue and its fix?

[V-Silpin]

@prateekchhikara I have updated the PR description, mentioned the issue & the fix

Kindly merge this PR

[V-Silpin]

@prateekchhikara any issues with the PR?

[V-Silpin]

@prateekchhikara @Dev-Khant

Pls merge this PR, as we need this issue #2636 to be solved urgently

[Dev-Khant]

Hey, can you please rebase with main, add a test for this and also run the formatting with pre-commit? Once the CI tests pass we can merge this.

[V-Silpin]

@Dev-Khant I have added a testcase, done rebase & pre-commit. Kindly review it.

[Dev-Khant]

Hey @V-Silpin There are few merge conflicts can you please resolve it?

[V-Silpin]

@Dev-Khant Merge Conflict Fixed

[Dev-Khant]

Thanks for the contribution, looks good to me.