# I am getting this error on langchain
**URL:**
**Author:**  [@diyarkaya489](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fdiyarkaya489)%5C
**Post date:** [February 9, 2025, 3:07pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fi-am-getting-this-error-on-langchain%2F139867%2F1 "2025-02-09T15:07:55Z")
```auto
from langchain_community.llms import HuggingFaceHub
hf=HuggingFaceHub(
repo_id="google/flan-t5-large",
task="text2text-generation", # Explicitly specify the task
model_kwargs={"temperature":0.7,"max_length":100},
huggingfacehub_api_token="hf_... Ue"
)
text="What is the capital of Turkey"
output=hf.invoke(text)
print(output)
```
ValueError: Task text2text-generation has no recommended model. Please specify a model explicitly. Visit [Tasks - Hugging Face](https://huggingface.co/tasks) for more info.
Why I am getting this error. I just checked Api token multiple times and still give this error.
---
**Author:**  [@John6666](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJohn6666)%5C
**Post date:** [February 9, 2025, 3:11pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fi-am-getting-this-error-on-langchain%2F139867%2F2 "2025-02-09T15:11:37Z")
It seems that the function has been discontinued.
[https://python.langchain.com/api\_reference/community/llms/langchain\_community.llms.huggingface\_hub.HuggingFaceHub.html](https://python.langchain.com/api_reference/community/llms/langchain_community.llms.huggingface_hub.HuggingFaceHub.html)
---
**Author:**  [@diyarkaya489](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fdiyarkaya489)%5C
**Post date:** [February 9, 2025, 3:33pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fi-am-getting-this-error-on-langchain%2F139867%2F3 "2025-02-09T15:33:18Z")
Still I used HuggingFaceEndpoin but still ı am getting same error, could you give me code example?
---
**Author:**  [@mahmutc](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fmahmutc)%5C
**Post date:** [February 9, 2025, 10:17pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fi-am-getting-this-error-on-langchain%2F139867%2F4 "2025-02-09T22:17:34Z")
try this one:
```auto
from langchain_huggingface.llms.huggingface_endpoint import HuggingFaceEndpoint
llm = HuggingFaceEndpoint(
task='text-generation',
model="deepseek-ai/DeepSeek-R1",
max_new_tokens=100,
temperature=0.7,
huggingfacehub_api_token="your_api"
)
print(llm.invoke("What is the capital of Turkey"))
```
---
**Author:**  [@John6666](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJohn6666)%5C
**Post date:** [February 11, 2025, 3:37pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fi-am-getting-this-error-on-langchain%2F139867%2F6 "2025-02-11T15:37:19Z")
The token has been leaked. Please invalidate the token as soon as possible.
---
**Author:**  [@ashu456465](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fashu456465)%5C
**Post date:** [February 11, 2025, 3:55pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fi-am-getting-this-error-on-langchain%2F139867%2F7 "2025-02-11T15:55:27Z")
> [@ashu456465](#):
>
> [
> Screenshot 2025-02-11 210330939×395 9.34 KB
> ](https://us1.discourse-cdn.com/hellohellohello/original/3X/c/6/c6caee4a7505fde27b0d48a7c5a0ba4632fe2af0.png)
i had already invalidated the token …
---
**Author:**  [@ashu456465](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fashu456465)%5C
**Post date:** [February 11, 2025, 4:05pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fi-am-getting-this-error-on-langchain%2F139867%2F8 "2025-02-11T16:05:50Z")
bro can u give a slution for this too?? it is showing the same error
ValueError: Task text2text-generation has no recommended model. Please specify a model explicitly. Visit [Tasks - Hugging Face](https://huggingface.co/tasks) for more info.
---
**Author:**  [@John6666](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJohn6666)%5C
**Post date:** [February 11, 2025, 4:29pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fi-am-getting-this-error-on-langchain%2F139867%2F9 "2025-02-11T16:29:12Z")
If the same solution as above is okay, this should work. The error message says that you can just overwrite the task.
```py
from langchain_huggingface.llms.huggingface_endpoint import HuggingFaceEndpoint
chain = LLMChain(
llm = HuggingFaceEndpoint(
task='text-generation', # overwrite task
model="deepseek-ai/DeepSeek-R1",
temperature=0,
huggingfacehub_api_token="hf_ *****"
),
prompt=prompt
)
```
---
**Author:**  [@Shaleensr](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FShaleensr)%5C
**Post date:** [May 11, 2025, 9:27am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fi-am-getting-this-error-on-langchain%2F139867%2F10 "2025-05-11T09:27:06Z")
Hi @mahmutc ,
I am a student trying to learn the stuff. This snippet dint work for me for some reason.
Here is the error log I received:
Traceback (most recent call last):
File “C:\Users\SS\Desktop\Camp\_langchain\_models\2.ChatModels\2\_chatmodel\_hf\_api.py”, line 9, in
print(llm.invoke(“What is the capital of Turkey”))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File “C:\Users\SS\Desktop\Camp\_langchain\_models\venv\Lib\site-packages\langchain\_core\language\_models\llms.py”, line 387, in invoke
self.generate\_prompt(
File “C:\Users\SS\Desktop\Camp\_langchain\_models\venv\Lib\site-packages\langchain\_core\language\_models\llms.py”, line 764, in generate\_prompt
return self.generate(prompt\_strings, stop=stop, callbacks=callbacks, \*\*kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File “C:\Users\SS\Desktop\Camp\_langchain\_models\venv\Lib\site-packages\langchain\_core\language\_models\llms.py”, line 971, in generate
return self.\_generate\_helper(
^^^^^^^^^^^^^^^^^^^^^^
File “C:\Users\SS\Desktop\Camp\_langchain\_models\venv\Lib\site-packages\langchain\_core\language\_models\llms.py”, line 790, in \_generate\_helper
self.\_generate(
File “C:\Users\SS\Desktop\Camp\_langchain\_models\venv\Lib\site-packages\langchain\_core\language\_models\llms.py”, line 1545, in \_generate
self.\_call(prompt, stop=stop, run\_manager=run\_manager, \*\*kwargs)
File “C:\Users\SS\Desktop\Camp\_langchain\_models\venv\Lib\site-packages\langchain\_huggingface\llms\huggingface\_endpoint.py”, line 312, in _call
response\_text = self.client.text\_generation(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File “C:\Users\SS\Desktop\Camp\_langchain\_models\venv\Lib\site-packages\huggingface\_hub\inference\_client.py”, line 2297, in text\_generation
provider\_helper = get\_provider\_helper(self.provider, task=“text-generation”, model=model\_id)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\SS\Desktop\Camp\_langchain\_models\venv\Lib\site-packages\huggingface\_hub\inference\_providers\_init_.py", line 169, in get\_provider\_helper
raise ValueError(
ValueError: Provider ‘featherless-ai’ not supported. Available values: ‘auto’ or any provider from
[‘black-forest-labs’, ‘cerebras’, ‘cohere’, ‘fal-ai’, ‘fireworks-ai’, ‘hf-inference’, ‘hyperbolic’, ‘nebius’, ‘novita’, ‘openai’, ‘replicate’, ‘sambanova’, ‘together’].Passing ‘auto’ (default value) will automatically select the first provider available for the model, sorted by the user’s order in [Hugging Face – The AI community building the future.](https://hf.co/settings/inference-providers).
I look forward to hearing from you.
Thanks,
SS
---
**Author:**  [@John6666](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJohn6666)%5C
**Post date:** [May 11, 2025, 9:48am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fi-am-getting-this-error-on-langchain%2F139867%2F11 "2025-05-11T09:48:35Z")
It seems an ongoing issue.
>
>
> \### Describe the bug
>
> It looks like \`GET /api/models/...?expand=inferenceProvide…rMapping\` is returning a still unsupported inference provider.
>
> https://github.com/huggingface/huggingface\_hub/blob/785835fc58defeff40368663589cca0a9a8808da/src/huggingface\_hub/inference/\_providers/\_\_init\_\_.py#L52-L131
>
> Would it be more convenient to skip unsupported providers instead of raising an exception?
>
> \### Reproduction
>
> \#### \`requirements.txt\`
>
> \`\`\`console
> huggingface\_hub==0.31.1
> \`\`\`
>
> \#### \`example.py\`
>
> \`\`\`python
> from huggingface\_hub import InferenceClient
>
> InferenceClient("meta-llama/Llama-3.1-70B-Instruct").chat\_completion(messages=\[\])
> \`\`\`
>
> \### Logs
>
> \#### \`python example.py\`
>
> \`\`\`python
> Traceback (most recent call last):
> File "/.../example.py", line 13, in \
> InferenceClient("meta-llama/Llama-3.1-70B-Instruct").chat\_completion(messages=\[\])
> ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ^^^^^^^^^^^^^
> File "/.../.venv/lib/python3.13/site-packages/huggingface\_hub/inference/\_client.py", line 886, in chat\_completion
> provider\_helper = get\_provider\_helper(
> self.provider,
> ...\<3 lines\>...
> else payload\_model,
> )
> File "/.../.venv/lib/python3.13/site-packages/huggingface\_hub/inference/\_providers/\_\_init\_\_.py", line 169, in get\_provider\_helper
> raise ValueError(
> ...\<3 lines\>...
> )
> ValueError: Provider 'featherless-ai' not supported. Available values: 'auto' or any provider from \['black-forest-labs', 'cerebras', 'cohere', 'fal-ai', 'fireworks-ai', 'hf-inference', 'hyperbolic', 'nebius', 'novita', 'openai', 'replicate', 'sambanova', 'together'\].Passing 'auto' (default value) will automatically select the first provider available for the model, sorted by the user's order in https://hf.co/settings/inference-providers.
> \`\`\`
>
> \#### \GET \https://huggingface.co/api/models/meta-llama/Llama-3.1-70B-Instruct?expand=inferenceProviderMapping\\
>
> \`\`\`json
> {
> "\_id": "66969ad27a033bf62173f3e2",
> "id": "meta-llama/Llama-3.1-70B-Instruct",
> "inferenceProviderMapping": {
> "featherless-ai": {
> "status": "live",
> "providerId": "meta-llama/Meta-Llama-3.1-70B-Instruct",
> "task": "conversational"
> },
> "novita": {
> "status": "live",
> "providerId": "meta-llama/llama-3.1-70b-instruct",
> "task": "conversational"
> },
> "nebius": {
> "status": "live",
> "providerId": "meta-llama/Meta-Llama-3.1-70B-Instruct-fast",
> "task": "conversational"
> },
> "hyperbolic": {
> "status": "staging",
> "providerId": "meta-llama/Meta-Llama-3.1-70B-Instruct",
> "task": "conversational"
> }
> }
> }
> \`\`\`
>
> \### System info
>
> \`\`\`console
> \- huggingface\_hub version: 0.31.0
> \- Platform: macOS-15.4.1-arm64-arm-64bit-Mach-O
> \- Python version: 3.13.3
> \- Running in iPython ?: No
> \- Running in notebook ?: No
> \- Running in Google Colab ?: No
> \- Running in Google Colab Enterprise ?: No
> \- Token path ?: /.../.cache/huggingface/token
> \- Has saved token ?: False
> \- Configured git credential helpers: osxkeychain
> \- FastAI: N/A
> \- Tensorflow: N/A
> \- Torch: 2.7.0
> \- Jinja2: 3.1.6
> \- Graphviz: N/A
> \- keras: N/A
> \- Pydot: N/A
> \- Pillow: 11.2.1
> \- hf\_transfer: 0.1.9
> \- gradio: N/A
> \- tensorboard: N/A
> \- numpy: 2.2.5
> \- pydantic: 2.10.6
> \- aiohttp: 3.11.18
> \- hf\_xet: 1.1.0
> \- ENDPOINT: https://huggingface.co
> \- HF\_HUB\_CACHE: /.../.cache/huggingface/hub
> \- HF\_ASSETS\_CACHE: /.../.cache/huggingface/assets
> \- HF\_TOKEN\_PATH: /.../.cache/huggingface/token
> \- HF\_STORED\_TOKENS\_PATH: /.../.cache/huggingface/stored\_tokens
> \- HF\_HUB\_OFFLINE: False
> \- HF\_HUB\_DISABLE\_TELEMETRY: False
> \- HF\_HUB\_DISABLE\_PROGRESS\_BARS: None
> \- HF\_HUB\_DISABLE\_SYMLINKS\_WARNING: False
> \- HF\_HUB\_DISABLE\_EXPERIMENTAL\_WARNING: False
> \- HF\_HUB\_DISABLE\_IMPLICIT\_TOKEN: False
> \- HF\_HUB\_ENABLE\_HF\_TRANSFER: False
> \- HF\_HUB\_ETAG\_TIMEOUT: 10
> \- HF\_HUB\_DOWNLOAD\_TIMEOUT: 10
> \`\`\`
---
**Author:**  [@mahmutc](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fmahmutc)%5C
**Post date:** [May 11, 2025, 10:39am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fi-am-getting-this-error-on-langchain%2F139867%2F12 "2025-05-11T10:39:33Z")
Actually, you can change the provider as follows:
```auto
llm = HuggingFaceEndpoint(
model="deepseek-ai/DeepSeek-R1",
provider="sambanova",
)
```
However, I still encounter this strange behavior, even when I change the task to “conversational”:
`ValueError: Task 'text-generation' not supported for provider 'sambanova'. Available tasks: ['conversational', 'feature-extraction']`
$ pip freeze | grep -P ‘(langchain|langchain-huggingface|huggingface-hub)’
huggingface-hub==0.31.1
langchain==0.3.25
langchain-anthropic==0.3.10
langchain-community==0.3.20
langchain-core==0.3.59
langchain-huggingface==0.2.0
langchain-ollama==0.3.0
langchain-text-splitters==0.3.8
---
**Author:**  [@John6666](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJohn6666)%5C
**Post date:** [May 15, 2025, 8:28am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fi-am-getting-this-error-on-langchain%2F139867%2F13 "2025-05-15T08:28:57Z")
About feature-extraction API URL:
> **[sentence-transformers/all-MiniLM-L6-v2 · Updated feature-extraction API URL](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2/discussions/116)**
>
> Hello!
---
**Author:**  [@John6666](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJohn6666)%5C
**Post date:** [May 25, 2025, 11:17am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fi-am-getting-this-error-on-langchain%2F139867%2F15 "2025-05-25T11:17:51Z")
Your token is leaking. Make sure to disable (or refresh) the token so that it is safe.
> **[User access tokens](https://huggingface.co/docs/hub/security-tokens)**
>
> We’re on a journey to advance and democratize artificial intelligence through open source and open science.
---
**Author:**  [@John6666](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJohn6666)%5C
**Post date:** [May 25, 2025, 11:29am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fi-am-getting-this-error-on-langchain%2F139867%2F16 "2025-05-25T11:29:24Z")
Probably, if you look for a way to avoid using `post`, you’ll be able to make it work, but you may need to wait for support on the `langchain` side.
>
>
> \### Describe the bug
>
> The InferenceClient API still does not support many of the… tasks that can be hosted at inference endpoints, but gives a deprecation warning when using \`.post\` to get around this.
>
> \### Reproduction
>
> \`\`\`python
> from huggingface\_hub import InferenceClient, get\_inference\_endpoint
> import json
>
> \# Get endpoint and create client
> MODEL\_NAME = "YOUR\_MODEL\_NAME\_OR\_ENDPOINT\_NAME"
> NAMESPACE = "YOUR\_NAMESPACE"
> endpoint = get\_inference\_endpoint(MODEL\_NAME, namespace=NAMESPACE)
> client = InferenceClient(endpoint.url, timeout=10)
>
> \# Test data
> query = "What is the capital of France?"
> document = "Paris is the capital of France."
> sentence\_ranking\_style\_inputs = \[\[query, document\]\]
> text\_classification\_style\_inputs = \[{"text": query, "text\_pair": document}\]
>
> \# 1. Using post method
> response\_bytes = client.post(json={"inputs": sentence\_ranking\_style\_inputs})
> print(json.loads(response\_bytes))
> \# Problem: post method has deprecation warning
>
> \# 2. Using text\_classification task
> try:
> result = client.text\_classification(text\_classification\_style\_inputs) # There's no way to inject the inputs format that would have worked on this task for reranking
> print(result)
> except Exception as e:
> print(f"text\_classification error: {e}")
> \# Problem: text\_classification doesn't properly support text pairs format needed for reranking/cross-encoding
>
> \# 3. Using sentence\_similarity task
> try:
> result = client.sentence\_similarity(sentence\_ranking\_style\_inputs) # There's no direct way to inject the inputs format that would have worked on this task for reranking
> print(result)
> except Exception as e:
> print(f"sentence\_similarity error: {e}")
> \# Problem: No direct support for sentence ranking despite endpoint supporting this task
> \`\`\`
>
> Ideally, the sentence\_ranking task is supported.
>
> \### Logs
>
> \`\`\`shell
>
> \`\`\`
>
> \### System info
>
> \`\`\`shell
> \- huggingface\_hub version: 0.30.2
> \- Platform: macOS-15.4-arm64-arm-64bit
> \- Python version: 3.12.10
> \- Running in iPython ?: No
> \- Running in notebook ?: No
> \- Running in Google Colab ?: No
> \- Running in Google Colab Enterprise ?: No
> \- Token path ?: redacted
> \- Has saved token ?: False
> \- Configured git credential helpers: redacted
> \- FastAI: N/A
> \- Tensorflow: N/A
> \- Torch: 2.7.0
> \- Jinja2: 3.1.6
> \- Graphviz: N/A
> \- keras: N/A
> \- Pydot: N/A
> \- Pillow: 11.2.1
> \- hf\_transfer: N/A
> \- gradio: N/A
> \- tensorboard: N/A
> \- numpy: 1.26.4
> \- pydantic: 2.11.4
> \- aiohttp: 3.11.18
> \- hf\_xet: N/A
> \- ENDPOINT: https://huggingface.co
> \- HF\_HUB\_CACHE: redacted
> \- HF\_ASSETS\_CACHE: redacted
> \- HF\_TOKEN\_PATH: redacted
> \- HF\_STORED\_TOKENS\_PATH: redacted
> \- HF\_HUB\_OFFLINE: False
> \- HF\_HUB\_DISABLE\_TELEMETRY: False
> \- HF\_HUB\_DISABLE\_PROGRESS\_BARS: None
> \- HF\_HUB\_DISABLE\_SYMLINKS\_WARNING: False
> \- HF\_HUB\_DISABLE\_EXPERIMENTAL\_WARNING: False
> \- HF\_HUB\_DISABLE\_IMPLICIT\_TOKEN: False
> \- HF\_HUB\_ENABLE\_HF\_TRANSFER: False
> \- HF\_HUB\_ETAG\_TIMEOUT: 10
> \- HF\_HUB\_DOWNLOAD\_TIMEOUT: 10
> \`\`\`
---
**Author:**  [@omsite45](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fomsite45)%5C
**Post date:** [May 25, 2025, 11:40am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fi-am-getting-this-error-on-langchain%2F139867%2F17 "2025-05-25T11:40:11Z")
STILL GETTING ERROR
---
**Author:**  [@John6666](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJohn6666)%5C
**Post date:** [May 25, 2025, 11:59am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fi-am-getting-this-error-on-langchain%2F139867%2F18 "2025-05-25T11:59:47Z")
Hmm… If it hasn’t been completely abolished, it might still work.
>
```auto
pip install huggingface_hub==0.30.0
```
Or raise an issue.
> **[Issues · langchain-ai/langchain](https://github.com/langchain-ai/langchain/issues)**
>
> 🦜🔗 Build context-aware reasoning applications. Contribute to langchain-ai/langchain development by creating an account on GitHub.