# Change input\_ids via API Inference for Text Generation

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fchange-input-ids-via-api-inference-for-text-generation%2F80983%3E%5C
**Category:** Beginners\
**Created:** [April 10, 2024, 2:33am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fchange-input-ids-via-api-inference-for-text-generation%2F80983 "2024-04-10T02:33:58Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![frncscp](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/frncscp/32/25653_2.png) [@frncscp](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Ffrncscp)%5C
**Post date:** [April 10, 2024, 2:33am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fchange-input-ids-via-api-inference-for-text-generation%2F80983%2F1 "2024-04-10T02:33:58Z")

</div>

Hi! I’ve been messing around with a script that summarizes a text gotten from an audio transcription, so the text length is pretty variable, when it gets long enough (not much really) I get this error from the query (returns a response.json()):

> {‘error’: ‘Input length of input\_ids is 99, but `max_length` is set to 20. This can lead to unexpected behavior. You should consider increasing `max_length` or, better yet, setting `max_new_tokens`.’, ‘warnings’: [‘There was an inference error: Input length of input\_ids is 99, but `max_length` is set to 20. This can lead to unexpected behavior. You should consider increasing `max_length` or, better yet, setting `max_new_tokens`.’]}

I haven’t been able to find documentation about how to change this parameter for an inference deployment, how can I change the value?

Here’s the code snnipet:

```auto
def query(payload, API_URL, headers):
    response = requests.post(API_URL, headers=headers, json=payload)
    return response.json()

@st.cache_resource(show_spinner = False)
def summarize_(text, prompt, model, key):

    if len(text) > limit_of_tokens:
        limit_index = text.find(".", limit_of_tokens)
        text = text[limit_index + 1:] 
        #get the last biggest possible fragment, normally the last parts of the conversation
        #are the most imporant
    full_query = prompt + text

    API_URL_summarize = f"/static-proxy?url=https%3A%2F%2Fapi-inference.huggingface.co%2Fmodels%2F%7Bmodel%7D"
    headers = {"Authorization": f"Bearer {token}"}

    data = query({
	"inputs": full_query,

    "parameters" : {
    "return_full_text" : False},

    "options" : {
    "wait_for_model" : True}
    }, 
    API_URL_summarize, headers)
    
    result = data[0]['generated_text']
    
    return result

```