TypeError: Can't instantiate abstract class RunnableSerializable[OutputFixingParserRetryChainInput, str] with abstract method invoke

[lehedrn]

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

from typing import List

from langchain_core.exceptions import OutputParserException
from langchain_core.output_parsers import PydanticOutputParser
from langchain_core.runnables import RunnablePassthrough
from langchain_openai import ChatOpenAI
from pydantic import BaseModel, Field

class Actor(BaseModel):
    name: str = Field(description="name of an actor")
    film_names: List[str] = Field(description="list of names of films they starred in")


actor_query = "Generate the filmography for a random actor."

parser = PydanticOutputParser(pydantic_object=Actor)

misformatted = "{'name': 'Tom Hanks', 'film_names': ['Forrest Gump']}"

from langchain.output_parsers import OutputFixingParser

new_parser = OutputFixingParser.from_llm(parser=parser, llm=ChatOpenAI(model="gpt-3.5-turbo-instruct"))

new_parser.parse(misformatted)

Description

I followed the instructions on the How to use the output-fixing parser documentation, but encountered a TypeError when trying to instantiate OutputFixingParser.
Traceback (most recent call last):
File "02_my_outputfixparser.py", line 28, in
new_parser = OutputFixingParser.from_llm(parser=parser, llm=ChatOpenAI(model="gpt-3.5-turbo-instruct"))

File "D:\ProgramData\anaconda3\envs\langchain-test\Lib\site-packages\langchain\output_parsers\fix.py", line 62, in from_llm
return cls(parser=parser, retry_chain=chain, max_retries=max_retries)

File "D:\ProgramData\anaconda3\envs\langchain-test\Lib\site-packages\langchain_core\load\serializable.py", line 125, in init
super().init(*args, **kwargs)
File "D:\ProgramData\anaconda3\envs\langchain-test\Lib\site-packages\pydantic\main.py", line 214, in init
validated_self = self.pydantic_validator.validate_python(data, self_instance=self)

TypeError: Can't instantiate abstract class RunnableSerializable[OutputFixingParserRetryChainInput, str] with abstract method invoke

so, how to use the output-fixing parser

System Info

System Information

OS: Windows
OS Version: 10.0.22631
Python Version: 3.11.10 | packaged by Anaconda, Inc. | (main, Oct 3 2024, 07:22:26) [MSC v.1929 64 bit (AMD64)]

Package Information

langchain_core: 0.3.15
langchain: 0.3.7
langchain_community: 0.3.5
langsmith: 0.1.140
langchain_cli: 0.0.31
langchain_experimental: 0.3.3
langchain_openai: 0.2.6
langchain_text_splitters: 0.3.2
langgraph: 0.2.45
langserve: 0.3.0

Other Dependencies

aiohttp: 3.10.10
async-timeout: Installed. No version info available.
dataclasses-json: 0.6.7
fastapi: 0.115.4
gitpython: 3.1.43
gritql: 0.1.5
httpx: 0.27.2
httpx-sse: 0.4.0
jsonpatch: 1.33
langgraph-checkpoint: 2.0.2
langgraph-sdk: 0.1.35
langserve[all]: Installed. No version info available.
numpy: 1.26.4
openai: 1.54.3
orjson: 3.10.11
packaging: 24.1
pydantic: 2.10.0b1
pydantic-settings: 2.6.1
PyYAML: 6.0.2
requests: 2.32.3
requests-toolbelt: 1.0.0
SQLAlchemy: 2.0.35
sse-starlette: 1.8.2
tenacity: 9.0.0
tiktoken: 0.8.0
tomlkit: 0.12.5
typer[all]: Installed. No version info available.
typing-extensions: 4.12.2
uvicorn: 0.23.2

[feijoes]

The issue is related to version compatibility of dependencies. Upgrade the packages:
pip install --upgrade langchain langchain-openai

[andremonaco]

For me (macOS) upgrading was not enough. Had to pin pydantic to 2.9.2.

langchain==0.3.7
langchain-community==0.3.7
langchain-core== 0.3.18
langchain-openai==0.2.8
pydantic==2.9.2
pydantic-core==2.23.4
pydantic-settings==2.6.1

[lehedrn]

also don't work

[wbadart]

I didn't see any obvious culprits in the pydantic 2.10.0 release notes, but indeed, constraining my pydantic dependency to < 2.10.0 fixed this issue for me.