Bug: model Field Missing Error in Replicate Class Due to Misidentification in Validator

[Pooyash1998]

Checked other resources

• I added a very descriptive title to this issue.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.
• I am sure that this is a bug in LangChain rather than my code.
• The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).

Example Code

from langchain_community.llms import Replicate

replicate = Replicate(
model="meta/meta-llama-3-405b-instruct",
model_kwargs={"temperature": 0.7}
)

Error Message and Stack Trace (if applicable)

pydantic_core._pydantic_core.ValidationError: 1 validation error for Replicate
model
Field required [type=missing, input_value=..., input_type=..., ...]

Description

When initializing the Replicate class, the model field is incorrectly treated as an extra field and moved into model_kwargs, resulting in a validation error. This happens due to the way the build_extra validator processes the field aliases.
Suggested Fix:
In the build_extra method, replace the use of field.alias with field.name to ensure proper recognition of all fields:
@model_validator(mode="before") @classmethod def build_extra(cls, values: Dict[str, Any]) -> Any: all_required_field_names = {field.name for field in get_fields(cls).values()} # Remaining logic...
Or defining "model" as an alias in a Field can also solve the problem :
class Replicate(LLM): model: str = Field(..., alias="model")

System Info

System Information

OS: Linux
OS Version: #1 SMP Fri Mar 29 23:14:13 UTC 2024
Python Version: 3.12.6 (main, Sep 10 2024, 00:05:17) [GCC 11.4.0]

Package Information

langchain_core: 0.3.6
langchain: 0.3.1
langchain_community: 0.3.1
langsmith: 0.1.129
langchain_chroma: 0.1.4
langchain_huggingface: 0.1.0
langchain_ollama: 0.2.0
langchain_openai: 0.2.0
langchain_text_splitters: 0.3.0
langserve: 0.3.0

Optional packages not installed

langgraph

Other Dependencies

aiohttp: 3.10.5
async-timeout: 4.0.3
chromadb: 0.5.7
dataclasses-json: 0.6.7
fastapi: 0.114.2
httpx: 0.27.2
huggingface-hub: 0.24.7
jsonpatch: 1.33
numpy: 1.26.4
ollama: 0.3.3
openai: 1.45.1
orjson: 3.10.7
packaging: 24.1
pydantic: 2.9.1
pydantic-settings: 2.5.2
PyYAML: 6.0.2
requests: 2.32.3
sentence-transformers: 3.1.0
SQLAlchemy: 2.0.34
sse-starlette: 1.8.2
tenacity: 8.5.0
tiktoken: 0.7.0
tokenizers: 0.19.1
transformers: 4.44.2
typing-extensions: 4.12.2

[devneel]

Having this same issue. Copy pasting the example from https://python.langchain.com/docs/integrations/llms/replicate/ doesn't work. I get the model Field Missing Error

[ken-vat]

same here, even with model included in kwargs -
llm = Replicate(
model_kwargs={"model": "meta/meta-llama-3-70b-instruct", "temperature": 0, "max_length": 300, "top_p": 1, "stop": []},
)

[Pooyash1998]

A temporary fix is to copy replicate.py from langchain library, modify it by adding the alias to "model" like this :
class Replicate(LLM): model: str = Field(..., alias="model")
and then import the Replicate class directly from your project and not from langchain library