Remember my remote Ollama server:port in .env #615
Conversation
…moteOllamaServer (what is passed by user upon execution) first and only then within os.environ['REMOTE_OLLAMA_SERVER'] (what user has stored in dotenv.
installer/client/cli/fabric.py
Outdated
| @@ -177,32 +177,32 @@ def main(): | |||
| else: | |||
| text = standalone.get_cli_input() | |||
| if args.stream and not args.context: | |||
| if args.remoteOllamaServer: | |||
| standalone.streamMessage(text, host=args.remoteOllamaServer) | |||
| if os.environ["REMOTE_OLLAMA_SERVER"] or args.remoteOllamaServer: | |||
There was a problem hiding this comment.
Calling os.environ["REMOTE_OLLAMA_SERVER"] will result in a KeyError: 'REMOTE_OLLAMA_SERVER' when a user doesn't have the REMOTE_OLLAMA_SERVER key in their .env file.
You should be using something like os.environ.get('REMOTE_OLLAMA_SERVER', None) instead.
(This comment is applicable for all similar calls you added.)
There was a problem hiding this comment.
Agree, thanks! I replaced the os.environ["REMOTE_OLLAMA_SERVER"] calls with os.environ.get('REMOTE_OLLAMA_SERVER', None) as you suggested.
Additionally, I added all of that to the PraisonAI agents section, replacing the http://localhost:11434/v1 to make agents call the remote Ollama server if needed.
…llama server usage possible.
|
We're getting ready to migrate to Golang; please resubmit then if this hasn't been addressed. Thank you! |
|
Could we have this merged for those of us who have working Python installs with a private Llama server? It really does make a difference... |
RATIONALE
In order to streamline local LLM use on servers, here is a tiny update that simplifies calling remote Ollama models from the terminal machines. You can do so by setting the --remoteOllamaServer flag in each fabric call... every time you do a call. For me personally it's 40 extra characters that include the --remoteOllamaServer flag plus IP and port.
To further simplify this process, I propose adding support for the REMOTE_OLLAMA_SERVER environment variable, which enables users to configure their remote Ollama server settings globally. This enhancement fits well within the general quick setup paradigm and caters to a broader range of users who may not require this feature in every situation.
CHANGES
REMOTE_OLLAMA_SERVERenvironment variable.streamMessageto useREMOTE_OLLAMA_SERVERif available.Standaloneclass to prioritizeREMOTE_OLLAMA_SERVER.ollama.Client.remoteOllamaServerargument.