pydantic.ValidationError: LangChainInterface credentials instance expected when using wxai_langchain

Question

I’m building a RAG application using LangChain and Watsonx AI with Streamlit. I want to create a LangChainInterface instance using my IBM Watsonx API credentials, but I’m getting the following validation error:

pydantic.error_wrappers.ValidationError: 3 validation errors for LangChainInterface credentials instance of Credentials expected (type=type_error.arbitrary_type; expected_arbitrary_type=Credentials) model_id extra fields not permitted (type=value_error.extra) project_id extra fields not permitted (type=value_error.extra)
Traceback:
File "D:\projects\UniGpt\APP\app.py", line 22, in <module>
    llm = LangChainInterface(
          ^^^^^^^^^^^^^^^^^^^
File "C:\Users\CHAMIKA\unigpt-env\Lib\site-packages\langchain_core\load\serializable.py", line 113, in __init__
    super().__init__(*args, **kwargs)
File "pydantic\main.py", line 341, in pydantic.main.BaseModel.__init__

Screenshot of error

Here’s my code:

#import logchain dependancies 
from langchain.document_loaders import PyPDFLoader
from langchain.indexes import VectorstoreIndexCreator
from langchain.chains import RetrievalQA
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.text_splitter import RecursiveCharacterTextSplitter

#bring in steamlit for UI dev
import streamlit as st

#bring in watsonx interface
from wxai_langchain.llm import LangChainInterface,  Credentials

from config import API_KEY,URL,PROJECT_ID
#setup cerdentials directly in the code
creds={
    'api_key': API_KEY,
    'url': URL,
}

#create llm using langchain 
llm = LangChainInterface(
    credentials=creds,
    model_id="granite-3-3-8b-instruct",
    params={
        'decoding_method':'sample',
        'max_new_tokens':200,
        'temprature':0.5
    },
    project_id=PROJECT_ID
)

#function to load and index the pdf document
@st.cache_resource
def load_pdf():
    pdf_name = "Resources/HandBook.pdf"
    #load the pdf
    loader = PyPDFLoader(pdf_name)
    #split the pdf into chunks
    index=VectorstoreIndexCreator(
        embedding=HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2"),
        text_splitter=RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
    ).from_loaders([loader])
    return index

#setup the retrieval qa chain
chain=RetrievalQA.from_chain_type(
    llm=llm, 
    chain_type="stuff",
    retriever=load_pdf().vectorstore.as_retriever(),
    input_key="question"
)


#setup the app title
st.title("Ask UniExpert")

#setup session state message variable to hold all the old message
if "messages" not in st.session_state:
    st.session_state.messages = []

#display all the historical messages
for message in st.session_state.messages:
    with st.chat_message(message["role"]):
        st.markdown(message["content"])

#build a prompt input template to display the prompts
prompt = st.chat_input("Enter your question:")

#if the user hits enter
if prompt:
    #display the prompt
    st.chat_message("user").markdown(prompt)
    #store the user prompt in state
    st.session_state.messages.append({"role": "user", "content": prompt})
    #response from llm
    response=chain.run(prompt)
    #show the response
    st.chat_message("assistant").markdown(response)
    #store the response in state
    st.session_state.messages.append(
        {"role": "assistant", "content": response})

What I’ve tried:

Passing the credentials as a dictionary (as shown above). Searching for a proper Credentials class usage in the documentation.

Question:

How should I correctly create a LangChainInterface instance with Watsonx credentials without triggering pydantic.ValidationError? Should I pass the credentials differently? How can I handle model_id and project_id parameters in the current version of wxai_langchain?

Ajeet Verma · Accepted Answer · 2025-08-23 06:26:12Z

As far as the error (pydantic.ValidationError) you’re getting is concerned, it's because of the following two reasons:

The defined creds must be a typed Credentials object, not a dict.

You can cross-verify it in its source code .

So, instead of defining as dict:

creds={
    'api_key': API_KEY,
    'url': URL,
}

define it as expected Credentials object:

from wxai_langchain.credentials import Credentials 
creds= Credentials(
    api_key=API_KEY,
    api_endpoint=URL,
    project_id=PROJECT_ID
)

In the wxai_langchain you installed, the LangChainInterface model doesn’t accept model_id / project_id at the top level.

Instead of:

#create llm using langchain 
llm = LangChainInterface(
    credentials=creds,
    model_id="granite-3-3-8b-instruct",
    params={
        'decoding_method':'sample',
        'max_new_tokens':200,
        'temprature':0.5
    },
    project_id=PROJECT_ID
)

Use:

#create llm using langchain 
llm = LangChainInterface(
    credentials=creds,
    model="granite-3-3-8b-instruct",
    params={
        'decoding_method':'sample',
        'max_new_tokens':200,
        'temprature':0.5
    }
)

I have already tested and incorporating the above two changes solves the pydantic.ValidationError

---------------------------------------

Having said that, I would suggest you to use the official and in active development langchain-ibm integration instead of wxai-langchain

Collectives™ on Stack Overflow

pydantic.ValidationError: LangChainInterface credentials instance expected when using wxai_langchain

1 Answer 1

Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

Comments

Your Answer

Sign up or log in

Post as a guest

Related