Add minimal python client example for the server, streaming callback #7373
+176
−0
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
When integrating llama.cpp with web services I use the server for inference. I find the server is fast and efficient using this method as the client is more or less pass-through.
There doesn't seem to be a good set of python examples for the server, possibly because most people use the openai client library? I was using this, but found it difficult to pass llama.cpp specific parameters such as cache_prompt, also it required that it required the model parameter to be present, even though it is not used by the server.
Here is a minimal python client that supports streaming. There is a streaming callback function that receives the data, here you can do things like check for "." for building sentences and passing them to a voice server, minimizing latency.