[GH-ISSUE #114] Missing provider YAML download step in Quick Installation guide #58

New Issue

2026-06-06T22:08:52-04:00

yindo commented

2026-06-06 22:08:52 -04:00

Originally created by @CostanzoPablo on GitHub (Feb 21, 2026).
Original GitHub issue: https://github.com/vxcontrol/pentagi/issues/114

Hi,

I noticed a discrepancy between the Quick Installation guide on https://pentagi.com/get-started
and the Manual Installation steps in the GitHub repository README.md.

In the Quick Installation section, the steps only mention:

mkdir pentagi && cd pentagi
curl -o .env https://raw.githubusercontent.com/vxcontrol/pentagi/master/.env.example

However, it does not include the step required to download the provider configuration files:

curl -o example.custom.provider.yml https://raw.githubusercontent.com/vxcontrol/pentagi/master/examples/configs/custom-openai.provider.yml
curl -o example.ollama.provider.yml https://raw.githubusercontent.com/vxcontrol/pentagi/master/examples/configs/ollama-llama318b.provider.yml

These files are referenced and mounted in docker-compose.yml, and without them:

OpenAI API keys defined in .env may not be used as expected

The model configuration may fall back to defaults or not work correctly

It seems that downloading the provider YAML files is required for a proper setup, even when only using OpenAI with an API key defined in .env.

It would be helpful to add this step to the Quick Installation section to avoid confusion and misconfiguration.

Thanks!

Originally created by @CostanzoPablo on GitHub (Feb 21, 2026). Original GitHub issue: https://github.com/vxcontrol/pentagi/issues/114 Hi, I noticed a discrepancy between the Quick Installation guide on https://pentagi.com/get-started and the Manual Installation steps in the GitHub repository README.md. In the Quick Installation section, the steps only mention: ``` mkdir pentagi && cd pentagi curl -o .env https://raw.githubusercontent.com/vxcontrol/pentagi/master/.env.example ``` However, it does not include the step required to download the provider configuration files: ``` curl -o example.custom.provider.yml https://raw.githubusercontent.com/vxcontrol/pentagi/master/examples/configs/custom-openai.provider.yml curl -o example.ollama.provider.yml https://raw.githubusercontent.com/vxcontrol/pentagi/master/examples/configs/ollama-llama318b.provider.yml ``` These files are referenced and mounted in docker-compose.yml, and without them: OpenAI API keys defined in .env may not be used as expected The model configuration may fall back to defaults or not work correctly It seems that downloading the provider YAML files is required for a proper setup, even when only using OpenAI with an API key defined in .env. It would be helpful to add this step to the Quick Installation section to avoid confusion and misconfiguration. Thanks!

yindo closed this issue

2026-06-06 22:08:52 -04:00

yindo commented

2026-06-06 22:08:53 -04:00

@asdek commented on GitHub (Feb 21, 2026):

Hey @CostanzoPablo,

Thank you for the detailed report! We've updated the page https://pentagi.com/get-started to address this issue.

Important clarification about provider configurations:

The OpenAI, Anthropic, Gemini, and AWS Bedrock providers use built-in default configurations that are included with the PentAGI executable. These providers work out of the box once you provide the API keys in the .env file - no additional YAML files are required.

The provider configuration YAML files (example.custom.provider.yml and example.ollama.provider.yml) are only needed when:

Using Custom LLM providers (via LLM_SERVER_* environment variables)
Using Ollama for local inference

You can also customize model selections for any provider through the PentAGI Web UI by creating custom model configurations tailored to your specific needs.

Thanks again for helping us improve the documentation!

@asdek commented on GitHub (Feb 21, 2026): Hey @CostanzoPablo, Thank you for the detailed report! We've updated the page https://pentagi.com/get-started to address this issue. **Important clarification about provider configurations:** The OpenAI, Anthropic, Gemini, and AWS Bedrock providers use **built-in default configurations** that are included with the PentAGI executable. These providers work out of the box once you provide the API keys in the `.env` file - no additional YAML files are required. The provider configuration YAML files (`example.custom.provider.yml` and `example.ollama.provider.yml`) are only needed when: - Using **Custom LLM providers** (via `LLM_SERVER_*` environment variables) - Using **Ollama** for local inference You can also customize model selections for any provider through the PentAGI Web UI by creating custom model configurations tailored to your specific needs. Thanks again for helping us improve the documentation!

Sign in to join this conversation.

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: vxcontrol/pentagi#58