run-llama/llama_index · error · ImportError

Please pip install PyYAML.

Error message

Please pip install PyYAML.

What it means

In SelectionOutputParser.parse, the JSON fallback path does `import yaml` inside an except block. If PyYAML is not installed, the import raises NameError (the later `except yaml.YAMLError` clause references the undefined name), which is converted into ImportError('Please pip install PyYAML.') chained to the original error. So this error only fires when the primary json.loads failed AND pyyaml is missing.

Source

Thrown at llama-index-core/llama_index/core/output_parsers/selection.py:91

        json_string = _marshal_llm_to_json(output)
        try:
            json_obj = json.loads(json_string)
        except json.JSONDecodeError as e_json:
            try:
                import yaml

                # NOTE: parsing again with pyyaml
                #       pyyaml is less strict, and allows for trailing commas
                #       right now we rely on this since guidance program generates
                #       trailing commas
                json_obj = yaml.safe_load(json_string)
            except yaml.YAMLError as e_yaml:
                raise OutputParserException(
                    f"Got invalid JSON object. Error: {e_json} {e_yaml}. "
                    f"Got JSON string: {json_string}"
                )
            except NameError as exc:
                raise ImportError("Please pip install PyYAML.") from exc

        if isinstance(json_obj, dict):
            json_obj = [json_obj]

        if not isinstance(json_obj, list):
            raise ValueError(f"Failed to convert output to JSON: {output!r}")

        json_output = self._format_output(json_obj)
        answers = [Answer.from_dict(json_dict) for json_dict in json_output]
        return StructuredOutput(raw_output=output, parsed_output=answers)

    def format(self, prompt_template: str) -> str:
        return prompt_template + "\n\n" + _escape_curly_braces(FORMAT_STR)

View on GitHub (pinned to afd0fef371)

Solutions

1. Install PyYAML: pip install pyyaml (or reinstall llama-index-core so its dependencies resolve)
2. Pin/verify dependencies in CI: add pyyaml (or llama-index-core with extras) to requirements and run `python -c "import yaml"` as a smoke test
3. If you cannot add deps, ensure model output is strictly valid JSON so the yaml fallback never runs

Example fix

# before
# environment lacking pyyaml -> ImportError: Please pip install PyYAML.

# after
pip install pyyaml
# or in requirements.txt:
#   llama-index-core>=0.10
#   pyyaml>=6.0

try:
    import yaml  # noqa: F401
except ImportError:
    raise SystemExit("PyYAML is required for selection output parsing: pip install pyyaml")

try:
    parsed = selection_output_parser.parse(output)
except ImportError as e:
    if "PyYAML" in str(e):
        raise RuntimeError("install pyyaml (pip install pyyaml) and retry") from e
    raise

When it happens

Trigger: Environment without pyyaml installed; a model emits slightly-off JSON (trailing commas) triggering the yaml fallback; minimal/lean installs (some distros or slim docker images) where pyyaml was excluded, or a venv where llama-index-core was installed without its default extras.

Common situations: Docker slim images; `pip install --no-deps` installs; conflicting environments where pyyaml was uninstalled by another package's resolver; local dev works (pyyaml present transitively) but CI/production fails.

Related errors

• Got invalid JSON object. Error: {e_json} {e_yaml}. Got JSON
• Did not find {key}, please add an environment variable `{env
• Invalid Embedding name: {name}
• `llama-index-embeddings-openai` package not found, please ru
• ****** Could not load OpenAI embedding model. If you intend

AI-assisted analysis of run-llama/llama_index@afd0fef371 (2026-08-15). Data as JSON: /api/errors/b3722437f158f76d. Report an issue: GitHub.