# TypeError: InferenceClient.text\_generation() got an unexpected keyword argument 'token'

**URL:** <https://discuss.huggingface.co/t/typeerror-inferenceclient-text-generation-got-an-unexpected-keyword-argument-token/158815>\
**Category:** Beginners\
**Created:** [June 10, 2025, 6:55pm UTC](https://discuss.huggingface.co/t/typeerror-inferenceclient-text-generation-got-an-unexpected-keyword-argument-token/158815 "2025-06-10T18:55:31Z")\
**Posts on this page:** 6\
**Page:** 1

<div class="post-metadata">

**Author:** ![mantoshnandy](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/mantoshnandy/32/49214_2.png) [@mantoshnandy](https://discuss.huggingface.co/u/mantoshnandy)\
**Post date:** [June 10, 2025, 6:55pm UTC](https://discuss.huggingface.co/t/typeerror-inferenceclient-text-generation-got-an-unexpected-keyword-argument-token/158815/1 "2025-06-10T18:55:31Z")

</div>

##########################Code#####################################  
import os

from langchain\_huggingface import HuggingFaceEndpoint  
from langchain\_core.prompts import PromptTemplate  
from langchain.chains import RetrievalQA  
from langchain\_huggingface import HuggingFaceEmbeddings  
from langchain\_community.vectorstores import FAISS  
from langchain\_community.document\_loaders import PyPDFLoader, DirectoryLoader

# Step 1: Setup LLM (Mistral with HuggingFace)

HF\_TOKEN=os.environ.get(“HF\_TOKEN”)  
HUGGINGFACE\_REPO\_ID=“mistralai/Mistral-7B-Instruct-v0.3”

def load\_llm(huggingface\_repo\_id):  
llm=HuggingFaceEndpoint(  
repo\_id=huggingface\_repo\_id,  
temperature=0.5,  
model\_kwargs={“token”:HF\_TOKEN,  
“max\_length”:“512”}  
)  
return llm

# Step 2: Connect LLM with FAISS and Create chain

CUSTOM\_PROMPT\_TEMPLATE = “”"  
Use the pieces of information provided in the context to answer user’s question.  
If you dont know the answer, just say that you dont know, dont try to make up an answer.  
Dont provide anything out of the given context

Context: {context}  
Question: {question}

Start the answer directly. No small talk please.  
“”"

def set\_custom\_prompt(custom\_prompt\_template):  
prompt=PromptTemplate(template=custom\_prompt\_template, input\_variables=[“context”, “question”])  
return prompt

# Load Database

DB\_FAISS\_PATH=“vectorstore/db\_faiss”  
embedding\_model=HuggingFaceEmbeddings(model\_name=“sentence-transformers/all-MiniLM-L6-v2”)  
db=FAISS.load\_local(DB\_FAISS\_PATH, embedding\_model, allow\_dangerous\_deserialization=True)

# Create QA chain

qa\_chain=RetrievalQA.from\_chain\_type(  
llm=load\_llm(HUGGINGFACE\_REPO\_ID),  
chain\_type=“stuff”,  
retriever=db.as\_retriever(search\_kwargs={‘k’:3}),  
return\_source\_documents=True,  
chain\_type\_kwargs={‘prompt’:set\_custom\_prompt(CUSTOM\_PROMPT\_TEMPLATE)}  
)

# Now invoke with a single query

user\_query=input("Write Query Here: ")  
response=qa\_chain.invoke({‘query’: user\_query})  
print("RESULT: ", response[“result”])  
print("SOURCE DOCUMENTS: ", response[“source\_documents”])  
###############################Code#######################################

Traceback (most recent call last):  
File “c:\Users\manto\Documents\medibot\_rag\connect\_with\_memory\_llm.py”, line 56, in   
response=qa\_chain.invoke({‘query’: user\_query})  
File “C:\Users\manto.virtualenvs\medibot\_rag-BvpnU3Fv\Lib\site-packages\langchain\chains\base.py”, line 167, in invoke  
raise e  
File “C:\Users\manto.virtualenvs\medibot\_rag-BvpnU3Fv\Lib\site-packages\langchain\chains\base.py”, line 157, in invoke  
self.\_call(inputs, run\_manager=run\_manager)  
~~~~~~~~~~ ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^  
File “C:\Users\manto.virtualenvs\medibot\_rag-BvpnU3Fv\Lib\site-packages\langchain\chains\retrieval\_qa\base.py”, line 154, in \_call  
answer = self.combine\_documents\_chain.run(  
input\_documents=docs, question=question, callbacks=\_run\_manager.get\_child()  
)  
File “C:\Users\manto.virtualenvs\medibot\_rag-BvpnU3Fv\Lib\site-packages\langchain\_core\_api\deprecation.py”, line 191, in warning\_emitting\_wrapper  
return wrapped(\*args, \*\*kwargs)  
File “C:\Users\manto.virtualenvs\medibot\_rag-BvpnU3Fv\Lib\site-packages\langchain\chains\base.py”, line 608, in run  
return self(kwargs, callbacks=callbacks, tags=tags, metadata=metadata)[  
~~~~ ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^  
File “C:\Users\manto.virtualenvs\medibot\_rag-BvpnU3Fv\Lib\site-packages\langchain\_core\_api\deprecation.py”, line 191, in warning\_emitting\_wrapper  
return wrapped(\*args, \*\*kwargs)  
File “C:\Users\manto.virtualenvs\medibot\_rag-BvpnU3Fv\Lib\site-packages\langchain\chains\base.py”, line 386, in **call**  
return self.invoke(  
~~~~~~~~~~~ ^  
inputs,  
^^^^^^^  
…\<2 lines\>…  
include\_run\_info=include\_run\_info,  
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^  
)  
^  
File “C:\Users\manto.virtualenvs\medibot\_rag-BvpnU3Fv\Lib\site-packages\langchain\chains\base.py”, line 167, in invoke  
raise e  
File “C:\Users\manto.virtualenvs\medibot\_rag-BvpnU3Fv\Lib\site-packages\langchain\chains\base.py”, line 157, in invoke  
self.\_call(inputs, run\_manager=run\_manager)  
~~~~~~~~~~ ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^  
File “C:\Users\manto.virtualenvs\medibot\_rag-BvpnU3Fv\Lib\site-packages\langchain\chains\combine\_documents\base.py”, line 138,  
in \_call  
output, extra\_return\_dict = self.combine\_docs(  
~~~~~~~~~~~~~~~~~ ^  
docs, callbacks=\_run\_manager.get\_child(), \*\*other\_keys  
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^  
)  
^  
File “C:\Users\manto.virtualenvs\medibot\_rag-BvpnU3Fv\Lib\site-packages\langchain\chains\combine\_documents\stuff.py”, line 259, in combine\_docs  
return self.llm\_chain.predict(callbacks=callbacks, \*\*inputs), {}  
~~~~~~~~~~~~~~~~~~~~~~ ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^  
File “C:\Users\manto.virtualenvs\medibot\_rag-BvpnU3Fv\Lib\site-packages\langchain\chains\llm.py”, line 319, in predict  
return self(kwargs, callbacks=callbacks)[self.output\_key]  
~~~~ ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^  
File “C:\Users\manto.virtualenvs\medibot\_rag-BvpnU3Fv\Lib\site-packages\langchain\_core\_api\deprecation.py”, line 191, in warning\_emitting\_wrapper  
return wrapped(\*args, \*\*kwargs)  
File “C:\Users\manto.virtualenvs\medibot\_rag-BvpnU3Fv\Lib\site-packages\langchain\chains\base.py”, line 386, in **call**  
return self.invoke(  
~~~~~~~~~~~ ^  
inputs,  
^^^^^^^  
…\<2 lines\>…  
include\_run\_info=include\_run\_info,  
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^  
)  
^  
File “C:\Users\manto.virtualenvs\medibot\_rag-BvpnU3Fv\Lib\site-packages\langchain\chains\base.py”, line 167, in invoke  
raise e  
File “C:\Users\manto.virtualenvs\medibot\_rag-BvpnU3Fv\Lib\site-packages\langchain\chains\base.py”, line 157, in invoke  
self.\_call(inputs, run\_manager=run\_manager)  
~~~~~~~~~~ ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^  
File “C:\Users\manto.virtualenvs\medibot\_rag-BvpnU3Fv\Lib\site-packages\langchain\chains\llm.py”, line 127, in \_call  
response = self.generate([inputs], run\_manager=run\_manager)  
File “C:\Users\manto.virtualenvs\medibot\_rag-BvpnU3Fv\Lib\site-packages\langchain\chains\llm.py”, line 139, in generate  
return self.llm.generate\_prompt(  
~~~~~~~~~~~~~~~~~~~~~~~~ ^  
prompts,  
^^^^^^^^  
…\<2 lines\>…  
\*\*self.llm\_kwargs,  
^^^^^^^^^^^^^^^^^^  
)  
^  
File “C:\Users\manto.virtualenvs\medibot\_rag-BvpnU3Fv\Lib\site-packages\langchain\_core\language\_models\llms.py”, line 766, in generate\_prompt  
return self.generate(prompt\_strings, stop=stop, callbacks=callbacks, \*\*kwargs)  
~~~~~~~~~~~~~ ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^  
File “C:\Users\manto.virtualenvs\medibot\_rag-BvpnU3Fv\Lib\site-packages\langchain\_core\language\_models\llms.py”, line 973, in generate  
return self.\_generate\_helper(  
~~~~~~~~~~~~~~~~~~~~~ ^  
prompts,  
^^^^^^^^  
…\<3 lines\>…  
\*\*kwargs,  
^^^^^^^^^  
)  
^  
File “C:\Users\manto.virtualenvs\medibot\_rag-BvpnU3Fv\Lib\site-packages\langchain\_core\language\_models\llms.py”, line 792, in \_generate\_helper  
self.\_generate(  
~~~~~~~~~~~~~~ ^  
prompts,  
^^^^^^^^  
…\<3 lines\>…  
\*\*kwargs,  
^^^^^^^^^  
)  
^  
File “C:\Users\manto.virtualenvs\medibot\_rag-BvpnU3Fv\Lib\site-packages\langchain\_core\language\_models\llms.py”, line 1547, in  
\_generate  
self.\_call(prompt, stop=stop, run\_manager=run\_manager, \*\*kwargs)  
~~~~~~~~~~ ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^  
File “C:\Users\manto.virtualenvs\medibot\_rag-BvpnU3Fv\Lib\site-packages\langchain\_huggingface\llms\huggingface\_endpoint.py”, line 312, in \_call  
response\_text = self.client.text\_generation(  
prompt=prompt,  
model=self.model,  
\*\*invocation\_params,  
)  
TypeError: InferenceClient.text\_generation() got an unexpected keyword argument ‘token’.

Can you please help me to resolve the issue.

---

<div class="post-metadata">

**Author:** ![Pimpcat-AU](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/pimpcat-au/32/48989_2.png) [@Pimpcat-AU](https://discuss.huggingface.co/u/Pimpcat-AU)\
**Post date:** [June 10, 2025, 7:35pm UTC](https://discuss.huggingface.co/t/typeerror-inferenceclient-text-generation-got-an-unexpected-keyword-argument-token/158815/2 "2025-06-10T19:35:20Z")

</div>

import os

from langchain\_huggingface import HuggingFaceEndpoint  
from langchain\_core.prompts import PromptTemplate  
from langchain.chains import RetrievalQA  
from langchain\_huggingface import HuggingFaceEmbeddings  
from langchain\_community.vectorstores import FAISS  
from langchain\_community.document\_loaders import PyPDFLoader, DirectoryLoader

# Step 1: Setup LLM (Mistral with HuggingFace)

HF\_TOKEN = os.environ.get(“HF\_TOKEN”)  
HUGGINGFACE\_REPO\_ID = “mistralai/Mistral-7B-Instruct-v0.3”

def load\_llm(huggingface\_repo\_id):  
# DO NOT include “token” in model\_kwargs  
# Pass the token via environment variable or as a supported class parameter  
os.environ[“HUGGINGFACEHUB\_API\_TOKEN”] = HF\_TOKEN  
llm = HuggingFaceEndpoint(  
repo\_id=huggingface\_repo\_id,  
temperature=0.5,  
model\_kwargs={“max\_length”: 512}  
# Optionally, for some langchain versions:  
# huggingfacehub\_api\_token=HF\_TOKEN  
)  
return llm

# Step 2: Connect LLM with FAISS and Create chain

CUSTOM\_PROMPT\_TEMPLATE = “”"  
Use the pieces of information provided in the context to answer user’s question.  
If you don’t know the answer, just say that you don’t know; don’t try to make up an answer.  
Don’t provide anything out of the given context.

Context: {context}  
Question: {question}

Start the answer directly. No small talk please.  
“”"

def set\_custom\_prompt(custom\_prompt\_template):  
prompt = PromptTemplate(template=custom\_prompt\_template, input\_variables=[“context”, “question”])  
return prompt

# Load Database

DB\_FAISS\_PATH = “vectorstore/db\_faiss”  
embedding\_model = HuggingFaceEmbeddings(model\_name=“sentence-transformers/all-MiniLM-L6-v2”)  
db = FAISS.load\_local(DB\_FAISS\_PATH, embedding\_model, allow\_dangerous\_deserialization=True)

# Create QA chain

qa\_chain = RetrievalQA.from\_chain\_type(  
llm=load\_llm(HUGGINGFACE\_REPO\_ID),  
chain\_type=“stuff”,  
retriever=db.as\_retriever(search\_kwargs={“k”: 3}),  
return\_source\_documents=True,  
chain\_type\_kwargs={“prompt”: set\_custom\_prompt(CUSTOM\_PROMPT\_TEMPLATE)}  
)

# Now invoke with a single query

user\_query = input("Write Query Here: ")  
response = qa\_chain.invoke({‘query’: user\_query})  
print("RESULT: ", response[“result”])  
print("SOURCE DOCUMENTS: ", response[“source\_documents”])

_Solution provided by Triskel Data Deterministic AI._

---

<div class="post-metadata">

**Author:** ![mantoshnandy](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/mantoshnandy/32/49214_2.png) [@mantoshnandy](https://discuss.huggingface.co/u/mantoshnandy)\
**Post date:** [June 10, 2025, 7:49pm UTC](https://discuss.huggingface.co/t/typeerror-inferenceclient-text-generation-got-an-unexpected-keyword-argument-token/158815/3 "2025-06-10T19:49:01Z")

</div>

Thank you very much your prompt response. I can not expect to get the answer is too early. Thank you very much. But now I get another issue with “max\_length”. Can you pls help me to resolve the issue.  
Traceback (most recent call last):  
File “c:\Users\manto\Documents\medibot\_rag\connect\_with\_memory\_llm.py”, line 72, in   
response=qa\_chain.invoke({‘query’: user\_query})  
File “C:\Users\manto.virtualenvs\medibot\_rag-BvpnU3Fv\Lib\site-packages\langchain\chains\base.py”, line 167, in invoke  
raise e  
File “C:\Users\manto.virtualenvs\medibot\_rag-BvpnU3Fv\Lib\site-packages\langchain\chains\base.py”, line 157, in invoke  
self.\_call(inputs, run\_manager=run\_manager)  
~~~~~~~~~~ ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^  
File “C:\Users\manto.virtualenvs\medibot\_rag-BvpnU3Fv\Lib\site-packages\langchain\chains\retrieval\_qa\base.py”, line 154, in \_call  
answer = self.combine\_documents\_chain.run(  
input\_documents=docs, question=question, callbacks=\_run\_manager.get\_child()  
)  
File “C:\Users\manto.virtualenvs\medibot\_rag-BvpnU3Fv\Lib\site-packages\langchain\_core\_api\deprecation.py”, line 191, in warning\_emitting\_wrapper  
return wrapped(\*args, \*\*kwargs)  
File “C:\Users\manto.virtualenvs\medibot\_rag-BvpnU3Fv\Lib\site-packages\langchain\chains\base.py”, line 608, in run  
return self(kwargs, callbacks=callbacks, tags=tags, metadata=metadata)[  
~~~~ ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^  
File “C:\Users\manto.virtualenvs\medibot\_rag-BvpnU3Fv\Lib\site-packages\langchain\_core\_api\deprecation.py”, line 191, in warning\_emitting\_wrapper  
return wrapped(\*args, \*\*kwargs)  
File “C:\Users\manto.virtualenvs\medibot\_rag-BvpnU3Fv\Lib\site-packages\langchain\chains\base.py”, line 386, in **call**  
return self.invoke(  
~~~~~~~~~~~ ^  
inputs,  
^^^^^^^  
…\<2 lines\>…  
include\_run\_info=include\_run\_info,  
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^  
)  
^  
File “C:\Users\manto.virtualenvs\medibot\_rag-BvpnU3Fv\Lib\site-packages\langchain\chains\base.py”, line 167, in invoke  
raise e  
File “C:\Users\manto.virtualenvs\medibot\_rag-BvpnU3Fv\Lib\site-packages\langchain\chains\base.py”, line 157, in invoke  
self.\_call(inputs, run\_manager=run\_manager)  
~~~~~~~~~~ ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^  
File “C:\Users\manto.virtualenvs\medibot\_rag-BvpnU3Fv\Lib\site-packages\langchain\chains\combine\_documents\base.py”, line 138,  
in \_call  
output, extra\_return\_dict = self.combine\_docs(  
~~~~~~~~~~~~~~~~~ ^  
docs, callbacks=\_run\_manager.get\_child(), \*\*other\_keys  
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^  
)  
^  
File “C:\Users\manto.virtualenvs\medibot\_rag-BvpnU3Fv\Lib\site-packages\langchain\chains\combine\_documents\stuff.py”, line 259, in combine\_docs  
return self.llm\_chain.predict(callbacks=callbacks, \*\*inputs), {}  
~~~~~~~~~~~~~~~~~~~~~~ ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^  
File “C:\Users\manto.virtualenvs\medibot\_rag-BvpnU3Fv\Lib\site-packages\langchain\chains\llm.py”, line 319, in predict  
return self(kwargs, callbacks=callbacks)[self.output\_key]  
~~~~ ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^  
File “C:\Users\manto.virtualenvs\medibot\_rag-BvpnU3Fv\Lib\site-packages\langchain\_core\_api\deprecation.py”, line 191, in warning\_emitting\_wrapper  
return wrapped(\*args, \*\*kwargs)  
File “C:\Users\manto.virtualenvs\medibot\_rag-BvpnU3Fv\Lib\site-packages\langchain\chains\base.py”, line 386, in **call**  
return self.invoke(  
~~~~~~~~~~~ ^  
inputs,  
^^^^^^^  
…\<2 lines\>…  
include\_run\_info=include\_run\_info,  
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^  
)  
^  
File “C:\Users\manto.virtualenvs\medibot\_rag-BvpnU3Fv\Lib\site-packages\langchain\chains\base.py”, line 167, in invoke  
raise e  
File “C:\Users\manto.virtualenvs\medibot\_rag-BvpnU3Fv\Lib\site-packages\langchain\chains\base.py”, line 157, in invoke  
self.\_call(inputs, run\_manager=run\_manager)  
~~~~~~~~~~ ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^  
File “C:\Users\manto.virtualenvs\medibot\_rag-BvpnU3Fv\Lib\site-packages\langchain\chains\llm.py”, line 127, in \_call  
response = self.generate([inputs], run\_manager=run\_manager)  
File “C:\Users\manto.virtualenvs\medibot\_rag-BvpnU3Fv\Lib\site-packages\langchain\chains\llm.py”, line 139, in generate  
return self.llm.generate\_prompt(  
~~~~~~~~~~~~~~~~~~~~~~~~ ^  
prompts,  
^^^^^^^^  
…\<2 lines\>…  
\*\*self.llm\_kwargs,  
^^^^^^^^^^^^^^^^^^  
)  
^  
File “C:\Users\manto.virtualenvs\medibot\_rag-BvpnU3Fv\Lib\site-packages\langchain\_core\language\_models\llms.py”, line 766, in generate\_prompt  
return self.generate(prompt\_strings, stop=stop, callbacks=callbacks, \*\*kwargs)  
~~~~~~~~~~~~~ ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^  
File “C:\Users\manto.virtualenvs\medibot\_rag-BvpnU3Fv\Lib\site-packages\langchain\_core\language\_models\llms.py”, line 973, in generate  
return self.\_generate\_helper(  
~~~~~~~~~~~~~~~~~~~~~ ^  
prompts,  
^^^^^^^^  
…\<3 lines\>…  
\*\*kwargs,  
^^^^^^^^^  
)  
^  
File “C:\Users\manto.virtualenvs\medibot\_rag-BvpnU3Fv\Lib\site-packages\langchain\_core\language\_models\llms.py”, line 792, in \_generate\_helper  
self.\_generate(  
~~~~~~~~~~~~~~ ^  
prompts,  
^^^^^^^^  
…\<3 lines\>…  
\*\*kwargs,  
^^^^^^^^^  
)  
^  
File “C:\Users\manto.virtualenvs\medibot\_rag-BvpnU3Fv\Lib\site-packages\langchain\_core\language\_models\llms.py”, line 1547, in  
\_generate  
self.\_call(prompt, stop=stop, run\_manager=run\_manager, \*\*kwargs)  
~~~~~~~~~~ ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^  
File “C:\Users\manto.virtualenvs\medibot\_rag-BvpnU3Fv\Lib\site-packages\langchain\_huggingface\llms\huggingface\_endpoint.py”, line 312, in \_call  
response\_text = self.client.text\_generation(  
prompt=prompt,  
model=self.model,  
\*\*invocation\_params,  
)  
TypeError: InferenceClient.text\_generation() got an unexpected keyword argument ‘max\_length’

---

<div class="post-metadata">

**Author:** ![Pimpcat-AU](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/pimpcat-au/32/48989_2.png) [@Pimpcat-AU](https://discuss.huggingface.co/u/Pimpcat-AU)\
**Post date:** [June 10, 2025, 7:51pm UTC](https://discuss.huggingface.co/t/typeerror-inferenceclient-text-generation-got-an-unexpected-keyword-argument-token/158815/4 "2025-06-10T19:51:38Z")

</div>

Remove `"max_length"` from `model_kwargs` and only use supported arguments. Pass generation parameters via the proper method or config.

---

<div class="post-metadata">

**Author:** ![mantoshnandy](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/mantoshnandy/32/49214_2.png) [@mantoshnandy](https://discuss.huggingface.co/u/mantoshnandy)\
**Post date:** [June 10, 2025, 7:55pm UTC](https://discuss.huggingface.co/t/typeerror-inferenceclient-text-generation-got-an-unexpected-keyword-argument-token/158815/5 "2025-06-10T19:55:20Z")

</div>

You are sweet. Now my chatbot gives me the reply.. I will check, test more and then reply you back for more. Thank you , Thank you , and Thank you !!!

---

<div class="post-metadata">

**Author:** ![John6666](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/john6666/32/27664_2.png) [@John6666](https://discuss.huggingface.co/u/John6666)\
**Post date:** [June 10, 2025, 11:41pm UTC](https://discuss.huggingface.co/t/typeerror-inferenceclient-text-generation-got-an-unexpected-keyword-argument-token/158815/6 "2025-06-10T23:41:51Z")

</div>

Yea. `max_new_tokens` is better if you need.

> **[Inference](https://huggingface.co/docs/huggingface_hub/package_reference/inference_client#huggingface_hub.InferenceClient.text_generation)**
>
> We’re on a journey to advance and democratize artificial intelligence through open source and open science.