Skip to content

Build AI methods with your coding agent, then run them anywhere: as an MCP for chatbots, as a webapp for people, or via API for your software.

fix

thomashebrard3c1969db85eb
diff --git a/tests/unit/pipelex/core/test_data/pipes/operators/llm/pipe_llm.py b/tests/unit/pipelex/core/test_data/pipes/operators/llm/pipe_llm.py
index 571551b0f..fa4fc9c17 100644
--- a/tests/unit/pipelex/core/test_data/pipes/operators/llm/pipe_llm.py
+++ b/tests/unit/pipelex/core/test_data/pipes/operators/llm/pipe_llm.py
@@ -99,9 +99,9 @@ definition = "Domain with pipe definitions"
type = "PipeLLM"
definition = "Expert analysis with system prompt"
output = "Text"
-prompt_template = """Extract all articles/items from this invoice text: $extracted_text.
-For each item find: item name, quantity, unit price, total price, description,
-and product code if available. Return each article as separate structured data.
+prompt_template = """
+Extract all articles/items from this invoice text: $extracted_text. For each item find: item name, quantity, unit price, total price, description, and product code if
+ available. Return each article as separate structured data.
"""
''',
PipelexBundleBlueprint(
@@ -112,9 +112,8 @@ and product code if available. Return each article as separate structured data.
type="PipeLLM",
definition="Expert analysis with system prompt",
output=NativeConceptEnum.TEXT,
- prompt_template="""Extract all articles/items from this invoice text: $extracted_text.
-For each item find: item name, quantity, unit price, total price, description,
-and product code if available. Return each article as separate structured data.
+ prompt_template="""Extract all articles/items from this invoice text: $extracted_text. For each item find: item name, quantity, unit price, total price, description, and product code if
+ available. Return each article as separate structured data.
""",
),
},