# Ollama integraion, API\_BASE key - Rasa Pro CALM

**URL:** <https://forum.rasa.com/t/ollama-integraion-api-base-key-rasa-pro-calm/64315>\
**Category:** Rasa CALM\
**Created:** [November 4, 2024, 7:55am UTC](https://forum.rasa.com/t/ollama-integraion-api-base-key-rasa-pro-calm/64315 "2024-11-04T07:55:08Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![sk1382](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/sk1382/32/24367_2.png) [@sk1382](https://forum.rasa.com/u/sk1382)\
**Post date:** [November 4, 2024, 7:55am UTC](https://forum.rasa.com/t/ollama-integraion-api-base-key-rasa-pro-calm/64315/1 "2024-11-04T07:55:08Z")

</div>

This is my **config.yml:**

```auto
recipe: default.v1
language: en
pipeline:
  - name: NLUCommandAdapter
  - name: MultiStepLLMCommandGenerator
    llm:
      provider: ollama
      model: example
      api_base: "http://localhost:8080/v1"
    flow_retrieval:
      embeddings:
        provider: "huggingface_local"
        model: "sentence-transformers/all-mpnet-base-v2"
        model_kwargs:
          device: "cpu"
        encode_kwargs:
          normalize_embeddings: true

policies:
- name: FlowPolicy
assistant_id: 20241023-095359-finite-subfloor

```

I am trying to host this [model](https://rasa/cmd_gen_codellama_13b_calm_demo) in local using ollama. Then its asking to set `OLLAMA_API_BASE` key to set.

I have tried several ways by changing endpoints and port in the `api_base` in the **config.yml** and terminal/powershell. And also i tried setting different ports in terminal while hosting the model like this `OLLAMA_HOST=8080 ollama serve`

No matter what I do the response isnt reaching the hosted model from `rasa inspect`. Could anyone explain and tell /which endpoint should I set while hosting and using it with `rasa inspect`?

Any helping response would be appreciated. @jtrasa