mirror of
https://github.com/katanemo/plano.git
synced 2026-04-25 00:36:34 +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>
45 lines
927 B
YAML
45 lines
927 B
YAML
version: v0.1.0
|
|
|
|
listeners:
|
|
egress_traffic:
|
|
address: 0.0.0.0
|
|
port: 12000
|
|
message_format: openai
|
|
timeout: 30s
|
|
|
|
llm_providers:
|
|
|
|
- access_key: $OPENAI_API_KEY
|
|
model: openai/gpt-4o-mini
|
|
|
|
- access_key: $OPENAI_API_KEY
|
|
model: openai/gpt-4.1
|
|
|
|
- access_key: $OPENAI_API_KEY
|
|
model: openai/gpt-4o
|
|
default: true
|
|
|
|
- access_key: $MISTRAL_API_KEY
|
|
model: mistral/ministral-3b-latest
|
|
|
|
- access_key: $ANTHROPIC_API_KEY
|
|
model: anthropic/claude-3-7-sonnet-latest
|
|
|
|
- access_key: $ANTHROPIC_API_KEY
|
|
model: anthropic/claude-sonnet-4-0
|
|
|
|
- access_key: $DEEPSEEK_API_KEY
|
|
model: deepseek/deepseek-reasoner
|
|
|
|
- access_key: $GROQ_API_KEY
|
|
model: groq/llama-3.1-8b-instant
|
|
|
|
- access_key: $GEMINI_API_KEY
|
|
model: gemini/gemini-1.5-pro-latest
|
|
|
|
- model: custom/test-model
|
|
base_url: http://host.docker.internal:11223
|
|
provider_interface: openai
|
|
|
|
tracing:
|
|
random_sampling: 100
|