mirror of
https://github.com/katanemo/plano.git
synced 2026-04-25 08:46:24 +02:00
fb0581fd39
* pushing draft PR * transformations are working. Now need to add some tests next * updated tests and added necessary response transformations for Anthropics' message response object * fixed bugs for integration tests * fixed doc tests * fixed serialization issues with enums on response * adding some debug logs to help * fixed issues with non-streaming responses * updated the stream_context to update response bytes * the serialized bytes length must be set in the response side * fixed the debug statement that was causing the integration tests for wasm to fail * fixing json parsing errors * intentionally removing the headers * making sure that we convert the raw bytes to the correct provider type upstream * fixing non-streaming responses to tranform correctly * /v1/messages works with transformations to and from /v1/chat/completions * updating the CLI and demos to support anthropic vs. claude * adding the anthropic key to the preference based routing tests * fixed test cases and added more structured logs * fixed integration tests and cleaned up logs * added python client tests for anthropic and openai * cleaned up logs and fixed issue with connectivity for llm gateway in weather forecast demo * fixing the tests. python dependency order was broken * updated the openAI client to fix demos * removed the raw response debug statement * fixed the dup cloning issue and cleaned up the ProviderRequestType enum and traits * fixing logs * moved away from string literals to consts * fixed streaming from Anthropic Client to OpenAI * removed debug statement that would likely trip up integration tests * fixed integration tests for llm_gateway * cleaned up test cases and removed unnecessary crates * fixing comments from PR * fixed bug whereby we were sending an OpenAIChatCompletions request object to llm_gateway even though the request may have been AnthropicMessages --------- Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-4.local> Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-9.local> Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-10.local> Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-41.local> Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-136.local>
81 lines
2 KiB
YAML
81 lines
2 KiB
YAML
version: v0.1.0
|
|
|
|
listeners:
|
|
ingress_traffic:
|
|
address: 0.0.0.0
|
|
port: 10000
|
|
message_format: openai
|
|
timeout: 30s
|
|
|
|
egress_traffic:
|
|
address: 0.0.0.0
|
|
port: 12000
|
|
message_format: openai
|
|
timeout: 30s
|
|
|
|
endpoints:
|
|
weather_forecast_service:
|
|
endpoint: host.docker.internal:18083
|
|
connect_timeout: 0.005s
|
|
|
|
overrides:
|
|
# confidence threshold for prompt target intent matching
|
|
prompt_target_intent_matching_threshold: 0.6
|
|
|
|
llm_providers:
|
|
- access_key: $GROQ_API_KEY
|
|
model: groq/llama-3.2-3b-preview
|
|
|
|
- access_key: $OPENAI_API_KEY
|
|
model: openai/gpt-4o
|
|
default: true
|
|
|
|
- access_key: $OPENAI_API_KEY
|
|
model: openai/gpt-4o-mini
|
|
|
|
- access_key: $ANTHROPIC_API_KEY
|
|
model: anthropic/claude-sonnet-4-20250514
|
|
|
|
system_prompt: |
|
|
You are a helpful assistant.
|
|
|
|
prompt_guards:
|
|
input_guards:
|
|
jailbreak:
|
|
on_exception:
|
|
message: Looks like you're curious about my abilities, but I can only provide assistance for weather forecasting.
|
|
|
|
prompt_targets:
|
|
- name: get_current_weather
|
|
description: Get current weather at a location.
|
|
parameters:
|
|
- name: location
|
|
description: The location to get the weather for
|
|
required: true
|
|
type: string
|
|
format: City, State
|
|
- name: days
|
|
description: the number of days for the request
|
|
required: true
|
|
type: int
|
|
endpoint:
|
|
name: weather_forecast_service
|
|
path: /weather
|
|
http_method: POST
|
|
|
|
- name: default_target
|
|
default: true
|
|
description: This is the default target for all unmatched prompts.
|
|
endpoint:
|
|
name: weather_forecast_service
|
|
path: /default_target
|
|
http_method: POST
|
|
system_prompt: |
|
|
You are a helpful assistant! Summarize the user's request and provide a helpful response.
|
|
# if it is set to false arch will send response that it received from this prompt target to the user
|
|
# if true arch will forward the response to the default LLM
|
|
auto_llm_dispatch_on_response: false
|
|
|
|
tracing:
|
|
random_sampling: 100
|
|
trace_arch_internal: true
|