feder-cr/Jobs_Applier_AI_Agent_AIHawk · error · ValueError

Section ' ' not found in either resume or…

Error message

Section '{section_name}' not found in either resume or job_application_profile.

What it means

After a section name is extracted from the LLM reply, the code looks the section up with getattr on both the resume object and job_application_profile. If both lookups return None, the section genuinely does not exist in the user's data, and the ValueError is raised with the offending section name.

Solutions

1. Add the missing section to your resume YAML / job_application_profile data so the lookup succeeds.
2. Make the section lookup fall back to a sensible default (e.g. personal_info) instead of raising.
3. If sections were renamed in a schema update, re-generate or migrate the resume/profile objects.

Example fix

# before
resume:  # no certifications key
# after
resume:
  certifications: "AWS Solutions Architect 2023"

SECTION_FIELDS = {'personal_info','skills','education','experience_details','projects','availability','salary_expectations','certifications','languages','interests','cover_letter'}
missing = [s for s in SECTION_FIELDS if getattr(resume, s, None) is None and getattr(profile, s, None) is None]
# sections in `missing` will raise if the LLM picks them

def has_section(resume, profile, name: str) -> bool:
    return getattr(resume, name, None) is not None or getattr(profile, name, None) is not None

try:
    ans = llm_manager.answer_question_textual_wide_range(q)
except ValueError as e:
    if 'not found in either resume' in str(e):
        ans = default_answer(q)  # fallback, e.g. skip the question
    else:
        raise

When it happens

Trigger: The LLM classifies a question under a section (e.g. 'certifications') that is absent from both the resume YAML and the job application profile, so getattr(resume, 'certifications', None) and getattr(job_application_profile, ...) are both None.

Common situations: Sparse resumes missing optional sections, resume schema changes that renamed fields, or an LLM misclassification into a section the user never filled in.

Understand the failure class

Background: "missing required argument" and "the following required arguments were not provided": what required-argument errors mean and how to fix them — this error's family across 20 libraries.

Related errors

• Chain not defined for section
• Could not extract section name from the response.
• Failed to get a response from the model after multiple…
• No numbers found in the string
• Unsupported model type

AI-assisted analysis of feder-cr/Jobs_Applier_AI_Agent_AIHawk@79155b52fa (2026-08-28). Data as JSON: /api/errors/725457b136aecb19. Report an issue: GitHub.

Appendix: source

Thrown at src/libs/llm_manager.py:596

            chain = chains.get(section_name)
            raw_output = chain.invoke(
                {
                    RESUME: self.resume,
                    JOB_DESCRIPTION: self.job_description,
                    COMPANY: self.job.company,
                }
            )
            output = self._clean_llm_output(raw_output)
            logger.debug(f"Cover letter generated: {output}")
            return output
        resume_section = getattr(self.resume, section_name, None) or getattr(
            self.job_application_profile, section_name, None
        )
        if resume_section is None:
            logger.error(
                f"Section '{section_name}' not found in either resume or job_application_profile."
            )
            raise ValueError(
                f"Section '{section_name}' not found in either resume or job_application_profile."
            )
        chain = chains.get(section_name)
        if chain is None:
            logger.error(f"Chain not defined for section '{section_name}'")
            raise ValueError(f"Chain not defined for section '{section_name}'")
        raw_output = chain.invoke(
            {RESUME_SECTION: resume_section, QUESTION: question}
        )
        output = self._clean_llm_output(raw_output)
        logger.debug(f"Question answered: {output}")
        return output

    def answer_question_numeric(
        self, question: str, default_experience: str = 3
    ) -> str:
        logger.debug(f"Answering numeric question: {question}")
        func_template = self._preprocess_template_string(

View on GitHub (pinned to 79155b52fa)