5a558eb09e
TypeScript SDK Compatibility V1.x E2E Tests / Select Node version matrix (push) Has been cancelled
TypeScript SDK Compatibility V1.x E2E Tests / TypeScript SDK Compatibility V1.x E2E Tests Node ${{matrix.node_version}} (push) Has been cancelled
TypeScript SDK E2E Tests / TypeScript SDK E2E Tests Node ${{matrix.node_version}} (push) Has been cancelled
Opik Optimizer - E2E Tests / build-opik (push) Has been cancelled
TypeScript SDK Compatibility V1.x E2E Tests / build-opik (push) Has been cancelled
Python SDK E2E Tests / Select Python version matrix (push) Has been cancelled
Python SDK E2E Tests / Python SDK E2E Tests ${{matrix.python_version}} (push) Has been cancelled
Python SDK E2E Tests / build-opik (push) Has been cancelled
Python SDK Compatibility V1.x E2E Tests / Select Python version matrix (push) Has been cancelled
Python SDK Compatibility V1.x E2E Tests / Python SDK Compatibility V1.x E2E Tests ${{matrix.python_version}} (push) Has been cancelled
Python SDK Compatibility V1.x E2E Tests / build-opik (push) Has been cancelled
TypeScript SDK E2E Tests / Select Node version matrix (push) Has been cancelled
TypeScript SDK E2E Tests / build-opik (push) Has been cancelled
Opik Optimizer - E2E Tests / Opik Optimizer E2E Tests Python ${{matrix.python_version}} (push) Has been cancelled
Opik Optimizer - E2E Tests / Opik Optimizer Integration Smoke Tests (push) Has been cancelled
🐙 Code Quality / detect (push) Has been cancelled
🐙 Code Quality / lint (${{ matrix.leg.name }}) (push) Has been cancelled
🐙 Code Quality / summary (push) Has been cancelled
TypeScript SDK Library Integration Tests / Check Secrets (push) Has been cancelled
TypeScript SDK Library Integration Tests / opik-vercel (Vercel AI SDK / eve) (push) Has been cancelled
SDK Library Integration Tests Runner / Check Secrets (push) Has been cancelled
SDK Library Integration Tests Runner / Missed OpenAI API Key Warning (push) Has been cancelled
SDK Library Integration Tests Runner / Build (push) Has been cancelled
SDK Library Integration Tests Runner / openai_tests (push) Has been cancelled
SDK Library Integration Tests Runner / langchain_tests (push) Has been cancelled
SDK Library Integration Tests Runner / langchain_legacy_tests (push) Has been cancelled
SDK Library Integration Tests Runner / llama_index_tests (push) Has been cancelled
SDK Library Integration Tests Runner / anthropic_tests (push) Has been cancelled
SDK Library Integration Tests Runner / mistral_tests (push) Has been cancelled
SDK Library Integration Tests Runner / groq_tests (push) Has been cancelled
SDK Library Integration Tests Runner / aisuite_tests (push) Has been cancelled
SDK Library Integration Tests Runner / haystack_tests (push) Has been cancelled
SDK Library Integration Tests Runner / dspy_tests (push) Has been cancelled
SDK Library Integration Tests Runner / crewai_v0_tests (push) Has been cancelled
SDK Library Integration Tests Runner / crewai_v1_tests (push) Has been cancelled
SDK Library Integration Tests Runner / genai_tests (push) Has been cancelled
SDK Library Integration Tests Runner / adk_tests (push) Has been cancelled
SDK Library Integration Tests Runner / adk_legacy_1_3_0_tests (push) Has been cancelled
SDK Library Integration Tests Runner / evaluation_metrics_tests (push) Has been cancelled
SDK Library Integration Tests Runner / bedrock_tests (push) Has been cancelled
SDK Library Integration Tests Runner / litellm_tests (push) Has been cancelled
SDK Library Integration Tests Runner / harbor_tests (push) Has been cancelled
SDK Library Integration Tests Runner / Slack Notification (push) Has been cancelled
Lint Opik Helm Chart / render-equality (push) Has been cancelled
Opik Optimizer - Unit Tests / Opik Optimizer Unit Tests Python ${{matrix.python_version}} (push) Has been cancelled
Python BE E2E Tests / Python BE E2E (push) Has been cancelled
Python Backend Tests / run-python-backend-tests (push) Has been cancelled
Python SDK Unit Tests / Python SDK Unit Tests ${{matrix.python_version}} (push) Has been cancelled
Release Drafter / update_release_draft (push) Has been cancelled
SDK E2E Libraries Integration Tests / Check Secrets (push) Has been cancelled
SDK E2E Libraries Integration Tests / Missed OpenAI API Key Warning (push) Has been cancelled
SDK E2E Libraries Integration Tests / build-opik (push) Has been cancelled
SDK E2E Libraries Integration Tests / E2E Lib Integration Python ${{matrix.python_version}} (push) Has been cancelled
TypeScript SDK Integration Build & Publish / build-and-publish (opik-gemini) (push) Has been cancelled
TypeScript SDK Integration Build & Publish / build-and-publish (opik-langchain) (push) Has been cancelled
TypeScript SDK Integration Build & Publish / build-and-publish (opik-openai) (push) Has been cancelled
TypeScript SDK Integration Build & Publish / build-and-publish (opik-otel) (push) Has been cancelled
TypeScript SDK Integration Build & Publish / build-and-publish (opik-vercel) (push) Has been cancelled
TypeScript SDK Build & Publish / build-and-publish (push) Has been cancelled
TypeScript SDK Unit Tests / Test on Node ${{ matrix.node-version }} (push) Has been cancelled
Backend Tests / discover-tests (push) Has been cancelled
Backend Tests / ${{ matrix.name }} (push) Has been cancelled
Build and Publish SDK / build-and-publish (push) Has been cancelled
Build Opik Docker Images / set-version (push) Has been cancelled
Build Opik Docker Images / build-backend (push) Has been cancelled
Build Opik Docker Images / build-sandbox-executor-python (push) Has been cancelled
Build Opik Docker Images / build-python-backend (push) Has been cancelled
Build Opik Docker Images / build-frontend (push) Has been cancelled
Build Opik Docker Images / create-git-tag (push) Has been cancelled
ClickHouse Migration Cluster Check / validate-clickhouse-migrations (push) Has been cancelled
Docs - Publish / run (push) Has been cancelled
E2E Tests - Post Merge (v2) / 🧪 E2E v2 Tests (${{ github.event.inputs.tier || 't1' }}) (push) Has been cancelled
E2E Tests - Post Merge (v2) / 📢 Slack Notification (push) Has been cancelled
Frontend Unit Tests / Test on Node 20 (push) Has been cancelled
Guardrails E2E Tests / Select Python version matrix (push) Has been cancelled
Guardrails E2E Tests / Guardrails E2E Tests ${{matrix.python_version}} (push) Has been cancelled
Guardrails E2E Tests / 📢 Slack Notification (push) Has been cancelled
Guardrails Backend Unit Tests / Guardrails Backend Unit Tests (push) Has been cancelled
Guardrails Backend Unit Tests / 📢 Slack Notification (push) Has been cancelled
Lint Opik Helm Chart / lint-helm-chart (Helm v3.21.0) (push) Has been cancelled
Lint Opik Helm Chart / lint-helm-chart (Helm v4.2.0) (push) Has been cancelled
Lint Opik Helm Chart / unittest-helm-chart (push) Has been cancelled
247 lines
8.2 KiB
Python
247 lines
8.2 KiB
Python
from __future__ import annotations
|
|
|
|
from typing import Any
|
|
|
|
import pytest
|
|
|
|
from opik_optimizer.api_objects import chat_prompt
|
|
from opik_optimizer.utils import prompt_tracing
|
|
|
|
|
|
class _StubOpikPrompt:
|
|
def __init__(self, name: str, prompt: str) -> None:
|
|
self.name = name
|
|
self.prompt = prompt
|
|
|
|
def __internal_api__to_info_dict__(self) -> dict[str, Any]:
|
|
return {"name": self.name, "version": {"template": self.prompt}}
|
|
|
|
|
|
class _StubOpikChatPrompt:
|
|
def __init__(self, name: str, template: list[dict[str, Any]]) -> None:
|
|
self.name = name
|
|
self.template = template
|
|
|
|
def __internal_api__to_info_dict__(self) -> dict[str, Any]:
|
|
return {"name": self.name, "version": {"template": self.template}}
|
|
|
|
|
|
class _TraceData:
|
|
def __init__(self, metadata: dict[str, Any] | None = None) -> None:
|
|
self.metadata = metadata
|
|
|
|
|
|
class _SpanData:
|
|
def __init__(self, metadata: dict[str, Any] | None = None) -> None:
|
|
self.metadata = metadata
|
|
|
|
|
|
def _patch_opik_prompt_types(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
import opik
|
|
|
|
monkeypatch.setattr(opik, "Prompt", _StubOpikPrompt, raising=False)
|
|
monkeypatch.setattr(opik, "ChatPrompt", _StubOpikChatPrompt, raising=False)
|
|
monkeypatch.setattr(opik, "__version__", "1.9.90", raising=False)
|
|
|
|
|
|
def _patch_prompt_support(monkeypatch: pytest.MonkeyPatch) -> dict[str, Any]:
|
|
from opik import opik_context
|
|
|
|
calls: dict[str, Any] = {"trace": [], "span": []}
|
|
|
|
def update_current_trace(
|
|
*,
|
|
name: str | None = None,
|
|
input: dict[str, Any] | None = None,
|
|
output: dict[str, Any] | None = None,
|
|
metadata: dict[str, Any] | None = None,
|
|
tags: list[str] | None = None,
|
|
_feedback_scores: list[dict[str, Any]] | None = None,
|
|
_thread_id: str | None = None,
|
|
_attachments: list[Any] | None = None,
|
|
prompts: list[Any] | None = None,
|
|
) -> None:
|
|
calls["trace"].append(
|
|
{
|
|
"metadata": metadata,
|
|
"prompts": prompts,
|
|
}
|
|
)
|
|
|
|
def update_current_span(
|
|
*,
|
|
name: str | None = None,
|
|
input: dict[str, Any] | None = None,
|
|
output: dict[str, Any] | None = None,
|
|
metadata: dict[str, Any] | None = None,
|
|
tags: list[str] | None = None,
|
|
usage: dict[str, Any] | None = None,
|
|
_feedback_scores: list[dict[str, Any]] | None = None,
|
|
model: str | None = None,
|
|
_provider: str | None = None,
|
|
total_cost: float | None = None,
|
|
_attachments: list[Any] | None = None,
|
|
_error_info: dict[str, Any] | None = None,
|
|
prompts: list[Any] | None = None,
|
|
) -> None:
|
|
calls["span"].append(
|
|
{
|
|
"metadata": metadata,
|
|
"prompts": prompts,
|
|
}
|
|
)
|
|
|
|
monkeypatch.setattr(opik_context, "update_current_trace", update_current_trace)
|
|
monkeypatch.setattr(opik_context, "update_current_span", update_current_span)
|
|
return calls
|
|
|
|
|
|
def test_normalize_prompt_input__opik_prompt(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
_patch_opik_prompt_types(monkeypatch)
|
|
opik_prompt = _StubOpikPrompt(name="text-prompt", prompt="Hello {name}")
|
|
|
|
normalized, is_single = prompt_tracing.normalize_prompt_input(opik_prompt)
|
|
|
|
assert is_single is True
|
|
prompt = normalized["text-prompt"]
|
|
assert isinstance(prompt, chat_prompt.ChatPrompt)
|
|
assert prompt.user == "Hello {name}"
|
|
assert getattr(prompt, "_opik_prompt_type", None) == "text"
|
|
assert getattr(prompt, "_opik_prompt_source", None) is opik_prompt
|
|
|
|
|
|
def test_normalize_prompt_input__opik_chat_prompt(
|
|
monkeypatch: pytest.MonkeyPatch,
|
|
) -> None:
|
|
_patch_opik_prompt_types(monkeypatch)
|
|
messages = [{"role": "user", "content": "Hi {name}"}]
|
|
opik_chat_prompt = _StubOpikChatPrompt(name="chat-prompt", template=messages)
|
|
|
|
normalized, is_single = prompt_tracing.normalize_prompt_input(opik_chat_prompt)
|
|
|
|
assert is_single is True
|
|
prompt = normalized["chat-prompt"]
|
|
assert isinstance(prompt, chat_prompt.ChatPrompt)
|
|
assert prompt.messages == messages
|
|
assert getattr(prompt, "_opik_prompt_type", None) == "chat"
|
|
assert getattr(prompt, "_opik_prompt_source", None) is opik_chat_prompt
|
|
|
|
|
|
def test_attach_initial_prompts__uses_opik_prompt_api(
|
|
monkeypatch: pytest.MonkeyPatch,
|
|
) -> None:
|
|
_patch_opik_prompt_types(monkeypatch)
|
|
calls = _patch_prompt_support(monkeypatch)
|
|
|
|
from opik import opik_context
|
|
|
|
monkeypatch.setattr(opik_context, "get_current_trace_data", lambda: _TraceData())
|
|
|
|
opik_prompt = _StubOpikPrompt(name="text-prompt", prompt="Hello {name}")
|
|
normalized, _ = prompt_tracing.normalize_prompt_input(opik_prompt)
|
|
|
|
prompt_tracing.attach_initial_prompts(normalized)
|
|
|
|
assert calls["trace"]
|
|
last_call = calls["trace"][-1]
|
|
assert last_call["prompts"] == [opik_prompt]
|
|
metadata = last_call["metadata"] or {}
|
|
assert "opik_optimizer" in metadata
|
|
assert "initial_prompts" in metadata["opik_optimizer"]
|
|
|
|
|
|
def test_attach_initial_prompts__fallbacks_on_old_sdk(
|
|
monkeypatch: pytest.MonkeyPatch,
|
|
) -> None:
|
|
_patch_opik_prompt_types(monkeypatch)
|
|
import opik
|
|
|
|
monkeypatch.setattr(opik, "__version__", "0.0.1", raising=False)
|
|
calls = _patch_prompt_support(monkeypatch)
|
|
|
|
from opik import opik_context
|
|
|
|
monkeypatch.setattr(opik_context, "get_current_trace_data", lambda: _TraceData())
|
|
|
|
opik_prompt = _StubOpikPrompt(name="text-prompt", prompt="Hello {name}")
|
|
normalized, _ = prompt_tracing.normalize_prompt_input(opik_prompt)
|
|
|
|
prompt_tracing.attach_initial_prompts(normalized)
|
|
|
|
assert calls["trace"]
|
|
last_call = calls["trace"][-1]
|
|
assert last_call["prompts"] is None
|
|
metadata = last_call["metadata"] or {}
|
|
assert "opik_optimizer" in metadata
|
|
|
|
|
|
def test_attach_initial_prompts__optimizer_prompt_uses_metadata_only(
|
|
monkeypatch: pytest.MonkeyPatch,
|
|
) -> None:
|
|
_patch_opik_prompt_types(monkeypatch)
|
|
calls = _patch_prompt_support(monkeypatch)
|
|
|
|
from opik import opik_context
|
|
|
|
monkeypatch.setattr(opik_context, "get_current_trace_data", lambda: _TraceData())
|
|
|
|
prompt = chat_prompt.ChatPrompt(name="p1", user="Hello {name}")
|
|
|
|
prompt_tracing.attach_initial_prompts({"p1": prompt})
|
|
|
|
assert calls["trace"]
|
|
last_call = calls["trace"][-1]
|
|
assert last_call["prompts"] is None
|
|
metadata = last_call["metadata"] or {}
|
|
assert metadata["opik_optimizer"]["initial_prompts"][0]["name"] == "p1"
|
|
assert metadata["opik_prompts"][0]["name"] == "p1"
|
|
opik_version = metadata["opik_prompts"][0]["version"]
|
|
assert opik_version["metadata"]["created_from"] == "opik_ui"
|
|
assert opik_version["metadata"]["type"] == "messages_json"
|
|
|
|
|
|
def test_attach_span_prompt_payload__does_not_include_rendered_messages(
|
|
monkeypatch: pytest.MonkeyPatch,
|
|
) -> None:
|
|
calls = _patch_prompt_support(monkeypatch)
|
|
|
|
from opik import opik_context
|
|
|
|
monkeypatch.setattr(opik_context, "get_current_span_data", lambda: _SpanData())
|
|
|
|
prompt = chat_prompt.ChatPrompt(name="p", user="Hello {name}")
|
|
|
|
prompt_tracing.attach_span_prompt_payload(prompt)
|
|
|
|
assert calls["span"]
|
|
metadata = calls["span"][-1]["metadata"] or {}
|
|
payloads = metadata["opik_optimizer"]["prompt_payloads"]
|
|
assert "rendered_messages" not in payloads[0]
|
|
assert metadata["opik_prompts"][0]["name"] == "p"
|
|
opik_version = metadata["opik_prompts"][0]["version"]
|
|
assert opik_version["metadata"]["created_from"] == "opik_ui"
|
|
assert opik_version["metadata"]["type"] == "messages_json"
|
|
|
|
|
|
def test_record_candidate_prompts__appends_candidates(
|
|
monkeypatch: pytest.MonkeyPatch,
|
|
) -> None:
|
|
calls = _patch_prompt_support(monkeypatch)
|
|
|
|
from opik import opik_context
|
|
|
|
existing_metadata = {"opik_optimizer": {"candidate_prompts": [{"name": "old"}]}}
|
|
monkeypatch.setattr(
|
|
opik_context, "get_current_trace_data", lambda: _TraceData(existing_metadata)
|
|
)
|
|
|
|
prompts = {"p1": chat_prompt.ChatPrompt(name="p1", user="Hello {name}")}
|
|
|
|
prompt_tracing.record_candidate_prompts(prompts)
|
|
|
|
assert calls["trace"]
|
|
metadata = calls["trace"][-1]["metadata"] or {}
|
|
candidate_prompts = metadata["opik_optimizer"]["candidate_prompts"]
|
|
assert len(candidate_prompts) == 2
|
|
assert candidate_prompts[0]["name"] == "old"
|