# Model/parse response is the same as the payload

**URL:** <https://forum.rasa.com/t/model-parse-response-is-the-same-as-the-payload/38208>\
**Category:** Rasa Open Source\
**Created:** [December 18, 2020, 4:02pm UTC](https://forum.rasa.com/t/model-parse-response-is-the-same-as-the-payload/38208 "2020-12-18T16:02:27Z")\
**Posts on this page:** 6\
**Page:** 1

<div class="post-metadata">

**Author:** ![stv](https://avatars.discourse-cdn.com/v4/letter/s/ce73a5/32.png) [@stv](https://forum.rasa.com/u/stv)\
**Post date:** [December 18, 2020, 4:02pm UTC](https://forum.rasa.com/t/model-parse-response-is-the-same-as-the-payload/38208/1 "2020-12-18T16:02:27Z")

</div>

So, when I use spacy or bert configurations, the rasa intent classification works perfectly fine in command line [ie rasa shell].

However, when I publish the model together with rasa server to a url and when I call the model/parse endpoint, I receive the original text that I sent as payload.

What is crazy is that when I use the default config.yml … aka I don’t use spacy and I don’t use bert … the url endpoint returns the expected response.

Here are my configs:

SPACY… works in command line, but not in url

```auto
language: en
pipeline:
  - name: SpacyNLP
  - name: "SpacyTokenizer"
  - name: "SpacyFeaturizer"
    model: "en_core_web_md"
  - name: DIETClassifier
    epochs: 50

```

BERT… works in command line, but not in url:

```auto
language: en
pipeline:
  - name: HFTransformersNLP
  - name: LanguageModelTokenizer
  - name: LanguageModelFeaturizer    
    model_name: "bert"
    model_weights: "rasa/LaBSE"
  - name: DIETClassifier
    epochs: 50

```

DEFAULT… works in command line and in url:

```auto
language: en
pipeline:
  - name: WhitespaceTokenizer
  - name: RegexFeaturizer
    case_sensitive: False
  - name: LexicalSyntacticFeaturizer
  - name: CountVectorsFeaturizer
    analyzer: word
  - name: DIETClassifier
    epochs: 50

```

---

<div class="post-metadata">

**Author:** ![mloubser](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/mloubser/32/13021_2.png) [@mloubser](https://forum.rasa.com/u/mloubser)\
**Post date:** [December 28, 2020, 12:31pm UTC](https://forum.rasa.com/t/model-parse-response-is-the-same-as-the-payload/38208/2 "2020-12-28T12:31:43Z")

</div>

Is the response code still 200 with spacy and bert?

---

<div class="post-metadata">

**Author:** ![stv](https://avatars.discourse-cdn.com/v4/letter/s/ce73a5/32.png) [@stv](https://forum.rasa.com/u/stv)\
**Post date:** [January 6, 2021, 2:49am UTC](https://forum.rasa.com/t/model-parse-response-is-the-same-as-the-payload/38208/3 "2021-01-06T02:49:43Z")

</div>

Yes

---

<div class="post-metadata">

**Author:** ![mloubser](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/mloubser/32/13021_2.png) [@mloubser](https://forum.rasa.com/u/mloubser)\
**Post date:** [January 6, 2021, 12:55pm UTC](https://forum.rasa.com/t/model-parse-response-is-the-same-as-the-payload/38208/4 "2021-01-06T12:55:57Z")

</div>

What version are you on? I tried to reproduce this on version 2.1.3, but the [parse endpoint](https://rasa.com/docs/rasa/pages/http-api#operation/parseModelMessage) returns parse info as expected for both spacy and default models (using the configs you posted)

---

<div class="post-metadata">

**Author:** ![stv](https://avatars.discourse-cdn.com/v4/letter/s/ce73a5/32.png) [@stv](https://forum.rasa.com/u/stv)\
**Post date:** [January 6, 2021, 1:57pm UTC](https://forum.rasa.com/t/model-parse-response-is-the-same-as-the-payload/38208/5 "2021-01-06T13:57:35Z")

</div>

I would be super happy to send you a zip file which includes Rasa’s web endpoints website using my trained model so you can check it out.

Or… if you want to test it for yourself … try this end point - I just published it with brand new trained model using Spacy: [https://rasa-ella-50-spacy-bpslyfsgba-uc.a.run.app/model/parse](https://rasa-ella-50-spacy-bpslyfsgba-uc.a.run.app/model/parse)

I send this payload: { “text”: “test” }

I receive this response:

```
{
  "text": "\/test",
  "intent": {
    "name": "test",
    "confidence": 1.0
  },
  "intent_ranking": [
    {
      "name": "test",
      "confidence": 1.0
    }
  ],
  "entities": []
}

```

Here is the config file contents: language: en pipeline:

- name: SpacyNLP
- name: “SpacyTokenizer”
- name: “SpacyFeaturizer” model: “en\_core\_web\_lg”
- name: DIETClassifier epochs: 50

No domain yml contents - this is pure NLU/intent classification exercise.

Using bert configuration does the same thing. Using your default settings works just fine.

I tried to test this without the use of the end points, using your Python API… that just opened a brand new can of bug worms and issues with your product - I’ll be having other topics and github issues dedicated to that alone. WHAT A MESS

---

<div class="post-metadata">

**Author:** ![stv](https://avatars.discourse-cdn.com/v4/letter/s/ce73a5/32.png) [@stv](https://forum.rasa.com/u/stv)\
**Post date:** [January 6, 2021, 2:05pm UTC](https://forum.rasa.com/t/model-parse-response-is-the-same-as-the-payload/38208/6 "2021-01-06T14:05:00Z")

</div>

I’d be happy to provide the same model but with Bert training and url so you can experience it yourself.