phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

LocalInferenceImpl update for LS 0.1 (#911)

Browse source 
# What does this PR do?

To work with the updated iOSCalendarAssistantWithLocalInf
[here](https://github.com/meta-llama/llama-stack-apps/compare/ios_local).

In short, provide a summary of what this PR does and why. Usually, the
relevant context should be present in a linked issue.

- [ ] Addresses issue (#issue)


## Test Plan

Please describe:
 - tests you ran to verify your changes with result summaries.
 - provide instructions so it can be reproduced.


## Sources

Please link relevant resources if necessary.


## Before submitting

- [ ] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [ ] Ran pre-commit to handle lint / formatting issues.
- [ ] Read the [contributor
guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md),
      Pull Request section?
- [ ] Updated relevant documentation.
- [ ] Wrote necessary unit or integration tests.
This commit is contained in:
Jeff Tang 2025-02-02 09:49:40 -08:00 • committed by GitHub
parent 7fdbd5b642
commit 587753da2f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 53 additions and 37 deletions
Download patch file Download diff file Expand all files Collapse all files

46
llama_stack/providers/inline/ios/inference/LocalInferenceImpl/LocalInference.swift
View file

@ -40,7 +40,7 @@ public class LocalInference: Inference {
public func chatCompletion(request: Components.Schemas.ChatCompletionRequest) -> AsyncStream<Components.Schemas.ChatCompletionResponseStreamChunk> {
return AsyncStream { continuation in
runnerQueue.async {
let workItem = DispatchWorkItem {
do {
var tokens: [String] = []
@ -69,9 +69,10 @@ public class LocalInference: Inference {
continuation.yield(
Components.Schemas.ChatCompletionResponseStreamChunk(
event: Components.Schemas.ChatCompletionResponseEvent(
delta: .ToolCallDelta(Components.Schemas.ToolCallDelta(
content: .case1(""),
parse_status: Components.Schemas.ToolCallParseStatus.started
delta: .tool_call(Components.Schemas.ToolCallDelta(
parse_status: Components.Schemas.ToolCallParseStatus.started,
tool_call: .case1(""),
_type: Components.Schemas.ToolCallDelta._typePayload.tool_call
)
),
event_type: .progress
@ -95,14 +96,18 @@ public class LocalInference: Inference {
text = token
}
var delta: Components.Schemas.ChatCompletionResponseEvent.deltaPayload
var delta: Components.Schemas.ContentDelta
if ipython {
delta = .ToolCallDelta(Components.Schemas.ToolCallDelta(
content: .case1(text),
parse_status: .in_progress
delta = .tool_call(Components.Schemas.ToolCallDelta(
parse_status: .in_progress,
tool_call: .case1(text),
_type: .tool_call
))
} else {
delta = .case1(text)
delta = .text(Components.Schemas.TextDelta(
text: text,
_type: Components.Schemas.TextDelta._typePayload.text)
)
}
if stopReason == nil {
@ -129,7 +134,12 @@ public class LocalInference: Inference {
continuation.yield(
Components.Schemas.ChatCompletionResponseStreamChunk(
event: Components.Schemas.ChatCompletionResponseEvent(
delta: .ToolCallDelta(Components.Schemas.ToolCallDelta(content: .case1(""), parse_status: .failure)),
delta: .tool_call(Components.Schemas.ToolCallDelta(
parse_status: Components.Schemas.ToolCallParseStatus.failed,
tool_call: .case1(""),
_type: Components.Schemas.ToolCallDelta._typePayload.tool_call
)
),
event_type: .progress
)
// TODO: stopReason
@ -141,10 +151,12 @@ public class LocalInference: Inference {
continuation.yield(
Components.Schemas.ChatCompletionResponseStreamChunk(
event: Components.Schemas.ChatCompletionResponseEvent(
delta: .ToolCallDelta(Components.Schemas.ToolCallDelta(
content: .ToolCall(toolCall),
parse_status: .success
)),
delta: .tool_call(Components.Schemas.ToolCallDelta(
parse_status: Components.Schemas.ToolCallParseStatus.succeeded,
tool_call: Components.Schemas.ToolCallDelta.tool_callPayload.ToolCall(toolCall),
_type: Components.Schemas.ToolCallDelta._typePayload.tool_call
)
),
event_type: .progress
)
// TODO: stopReason
@ -155,7 +167,10 @@ public class LocalInference: Inference {
continuation.yield(
Components.Schemas.ChatCompletionResponseStreamChunk(
event: Components.Schemas.ChatCompletionResponseEvent(
delta: .case1(""),
delta: .text(Components.Schemas.TextDelta(
text: "",
_type: Components.Schemas.TextDelta._typePayload.text)
),
event_type: .complete
)
// TODO: stopReason
@ -166,6 +181,7 @@ public class LocalInference: Inference {
print("Inference error: " + error.localizedDescription)
}
}
runnerQueue.async(execute: workItem)
}
}
}