feder-cr/Jobs_Applier_AI_Agent_AIHawk · error · ValueError

Chain not defined for section '{section_name}'

Error message

Chain not defined for section '{section_name}'

What it means

Even when the section exists in the data, answer_question_textual_wide_range needs an LCEL chain per section (chains.get(section_name)) to answer the question. If the dict has no chain registered under the extracted name, a ValueError is raised because there is no way to generate an answer.

Source

Thrown at src/libs/llm_manager.py:602

                }
            )
            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(
            prompts.numeric_question_template
        )
        prompt = ChatPromptTemplate.from_template(func_template)
        chain = prompt | self.llm_cheap | StrOutputParser()
        raw_output_str = chain.invoke(
            {

View on GitHub (pinned to 79155b52fa)

Solutions

1. Register a chain for every section name the regex can produce: the keys of chains must cover personal_info, skills, education, experience_details, projects, availability, salary_expectations, certifications, languages, interests, cover_letter.
2. Check for normalization mismatches: extracted names are lowercased with spaces replaced by underscores; align chain keys to that convention.
3. If a section intentionally has no chain, catch the ValueError and fall back to a generic QA chain.

Example fix

# before
chains = {'skills': skills_chain}
# after
chains = {
    'skills': skills_chain,
    'education': education_chain,
    'experience_details': experience_chain,
    'certifications': certifications_chain,
    # ... one entry per recognized section
}

REQUIRED_CHAINS = {'personal_info','skills','education','experience_details','projects','availability','salary_expectations','certifications','languages','interests','cover_letter'}
assert REQUIRED_CHAINS <= set(chains), f'missing chains: {REQUIRED_CHAINS - set(chains)}'

def chains_complete(chains: dict) -> bool:
    REQUIRED = {'personal_info','skills','education','experience_details','projects','availability','salary_expectations','certifications','languages','interests','cover_letter'}
    return REQUIRED.issubset(chains.keys())

try:
    ans = llm_manager.answer_question_textual_wide_range(q)
except ValueError as e:
    if 'Chain not defined' in str(e):
        ans = generic_chain.invoke({'resume_section': '', 'question': q})
    else:
        raise

When it happens

Trigger: The extracted section name (from the LLM reply, lowercased and underscored) has no matching key in the chains mapping, e.g. chains was built for a subset of sections, or a section name normalization mismatch ('salary_expectations' vs 'salary').

Common situations: Customizing the chains dict without adding entries for all regex-recognized sections, renaming chain keys during refactoring, or schema changes introducing new sections.

Related errors

• Unsupported model type: {llm_model_type}
• Could not extract section name from the response.
• Section '{section_name}' not found in either resume or job_a
• No numbers found in the string
• Failed to get a response from the model after multiple attem

AI-assisted analysis of feder-cr/Jobs_Applier_AI_Agent_AIHawk@79155b52fa (2026-08-28). Data as JSON: /api/errors/8e30b021d967280c. Report an issue: GitHub.