Help needed to extract certain fields from email using llama3.2

[khteh]

Checked other resources

• I added a very descriptive title to this question.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.

Commit to Help

• I commit to help with one of those options 👆

Example Code

I have the following model:

class EmailModel(BaseModel):
    """
    Example:
    Date: December 25, 2024
    From: Mickey Mouse <mickey@mouse.com>
    """
    date_str: str | None = Field(
        default=None,
        exclude=True,
        repr=False,
        description="The date of the email reformatted to match YYYY-mm-dd. This is usually found in the \"Date:\" field in the email.",
    )
    name: str | None = Field(
        default=None,
        description="The name of the email sender. This is usually found in the \"From:\" field in the email formatted as \"name <email>\"",
    )
    phone: str | None = Field(
        default=None,
        description="The phone number of the email sender (if present in the message). This is usually found in the signature at the end of the email body.",
    )
    email: str | None = Field(
        default=None,
        description="The email addreess of the email sender (if present in the message). This is usually found in the same \"From:\" field in the email formatted as \"name <email>\"",
    )
    @staticmethod
    def _convert_string_to_date(date_str: str | None) -> date | None:
        try:
            return datetime.strptime(date_str, "%Y-%m-%d").date() if date_str else None
        except Exception as e:
            print(e)
            return None

    @computed_field
    @property
    def date_of_email(self) -> date | None:
        return self._convert_string_to_date(self.date_str)

The chain:

    _email_parser_prompt = ChatPromptTemplate.from_messages(
        [
            (
                "system",
                """
                Parse the date of email, sender's name, sender's phone, sender's email, project id, site location,
                violation type, required changes, compliance deadline, and maximum potential fine from the email. 
                If any of the fields aren't present, don't populate them. 
                Try to cast dates into the YYYY-mm-dd format. Don't populate fields if they're not present in the email.
                Here's the email:
                {email}
                """,
            ),
            ("human", "{email}"),
            #("placeholder", "{email}"), #should be a list of base messages
        ]
    )
    self._chainLLM = init_chat_model("llama3.2", model_provider="ollama", temperature=0)
        self._email_parser_chain = (
            self._email_parser_prompt
            | self._chainLLM.with_structured_output(EmailModel)
        )

The class method:

@dataclass
class EmailRAGState(TypedDict):
    email: str
    extract: EmailModel | None

    async def ParseEmail(self, state: EmailRAGState, config: RunnableConfig) -> EmailRAGState:
        """
        Extract structured fields from an email.
        This should be used when the email message comes from
        a regulatory body or auditor regarding a property or
        construction site that the company works on.
        """
        logging.info(f"\n=== {self.ParseEmail.__name__} ===")
        state["extract"] = await self._email_parser_chain.with_config(config).ainvoke({"email": state["email"]})
        print(f"Extract: {state['extract']}")
        return state

The pytest:

@pytest.mark.asyncio
#@pytest.mark.skip(reason="https://github.com/langchain-ai/langchain/discussions/30412")
async def test_email_parser_chain(EmailRAGFixture):
    state = {
         "email": EMAILS[0],
         "extract": None,
    }
    config = RunnableConfig(run_name="Email RAG Test", thread_id=datetime.now())
    result: EmailRAGState = await EmailRAGFixture.ParseEmail(state, config)

The output:

Extract: name=None phone=None email='compliance.osha@osha.gov'

Description

It fails to extract the name and phone :-(

System Info

langchain==0.3.20
langchain-community==0.3.19
langchain-core==0.3.45
langchain-google-genai==2.1.0
langchain-google-vertexai==2.0.9
langchain-openai==0.3.8
langchain-text-splitters==0.3.6