tkmind/tkmind_go
1
0
Fork 0
Code Issues Pull Requests Actions 4 Packages Projects Releases Wiki Activity

docs: add in ollama (#82)

Browse Source
This commit is contained in:
Michael Neale
2024-09-21 10:41:49 +10:00
committed by GitHub
parent 18c9ed47f6
commit cf81f7a096
1 changed files with 3 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+3 -1
View File
@@ -101,14 +101,16 @@ default:
You can edit this configuration file to use different LLMs and toolkits in `goose`. `goose can also be extended to support any LLM or combination of LLMs You can edit this configuration file to use different LLMs and toolkits in `goose`. `goose can also be extended to support any LLM or combination of LLMs
#### provider #### provider
Provider of LLM. LLM providers that currently are supported by `goose`: Provider of LLM. LLM providers that currently are supported by `goose` (more can be supported by plugins):
| Provider | Required environment variable(s) to access provider | | Provider | Required environment variable(s) to access provider |
| :----- | :------------------------------ | | :----- | :------------------------------ |
| openai | `OPENAI_API_KEY` | | openai | `OPENAI_API_KEY` |
| anthropic | `ANTHROPIC_API_KEY` | | anthropic | `ANTHROPIC_API_KEY` |
| databricks | `DATABRICKS_HOST` and `DATABRICKS_TOKEN` | | databricks | `DATABRICKS_HOST` and `DATABRICKS_TOKEN` |
| ollama * | `OLLAMA_HOST` and ollama running |
* ollama is for local LLMs, and is limited by the tool calling model you can choose and run on local hardware, considered experimental.
#### processor #### processor
Model for complex, multi-step tasks such as writing code and executing commands. Example: `gpt-4o`. You should choose the model based the provider you configured. Model for complex, multi-step tasks such as writing code and executing commands. Example: `gpt-4o`. You should choose the model based the provider you configured.