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.

Docs/improved issue templates (#170)

Louis Choquel5735c28ebcf4
diff --git a/.cursor/rules/llms.mdc b/.cursor/rules/llms.mdc
index e75b252e6..281392552 100644
--- a/.cursor/rules/llms.mdc
+++ b/.cursor/rules/llms.mdc
@@ -20,7 +20,7 @@ An llm_handle matches the handle (an id of sorts) with the full specification of
The declaration of llm_handles looks like this in toml syntax:
```toml
[llm_handles]
-gpt-4o-2024-08-06 = { llm_name = "gpt-4o", llm_version = "2024-08-06" }
+gpt-4o-2024-11-20 = { llm_name = "gpt-4o", llm_version = "2024-11-20" }
```
In mosty cases, we only want to use version "latest" and llm_platform_choice "default" in which case the declaration is simply a match of the llm_handle to the llm_name, like this:
diff --git a/.github/DISCUSSION_TEMPLATE/new_idea.md b/.github/DISCUSSION_TEMPLATE/new_idea.md
deleted file mode 100644
index 96bed86b8..000000000
--- a/.github/DISCUSSION_TEMPLATE/new_idea.md
+++ /dev/null
@@ -1,52 +0,0 @@
-### 🤔 What's the current challenge?
-
-<!--
-Describe the pain point or limitation you're experiencing in your workflow:
-- What's difficult or frustrating in your current process?
-- What are you trying to achieve but can't?
-- How does this impact your productivity?
--->
-
-### 💡 Your Idea
-
-<!--
-Share your thoughts on how to address this challenge:
-- What's your proposed solution?
-- How would it work?
-- What would the user experience be like?
--->
-
-### 🎯 Use Cases
-
-<!--
-Help us understand how you would use this in practice:
-- Describe specific scenarios where this would be valuable
-- What kind of projects would benefit from this?
-- How frequently would you use this feature?
--->
-
-### 📈 Expected Impact
-
-<!--
-How would this idea improve your development experience?
-- What would this enable you to do better/faster?
-- How would this make your life easier?
-- Would this benefit other developers in your team?
--->
-
-### 🤝 Community Benefit
-
-<!--
-How might this idea benefit the broader Pipelex community?
-- What types of developers would benefit?
-- How might this attract new users?
-- Could this enable new use cases?
--->
-
----
-
-<!--
-Before submitting:
-- [ ] I have searched existing discussions to avoid duplicates
-- [ ] I'm willing to participate in the discussion and provide additional context if needed
--->
diff --git a/.github/ISSUE_TEMPLATE/config.yml b/.github/ISSUE_TEMPLATE/config.yml
new file mode 100644
index 000000000..15850e9dd
--- /dev/null
+++ b/.github/ISSUE_TEMPLATE/config.yml
@@ -0,0 +1,5 @@
+blank_issues_enabled: false
+contact_links:
+ - name: 💬 Ask a question
+ url: https://github.com/Pipelex/pipelex/discussions
+ about: "Please start a Discussion instead of filing a blank issue."
diff --git a/.github/ISSUE_TEMPLATE/feature_request.yml b/.github/ISSUE_TEMPLATE/feature_request.yml
index c42381997..8d1a96695 100644
--- a/.github/ISSUE_TEMPLATE/feature_request.yml
+++ b/.github/ISSUE_TEMPLATE/feature_request.yml
@@ -33,7 +33,7 @@ body:
id: proposal
attributes:
label: "Proposed solution"
- placeholder: "Describe the feature you’d like to see."
+ placeholder: "Describe the feature you'd like to see."
validations:
required: false
@@ -41,7 +41,7 @@ body:
id: alternatives
attributes:
label: "Alternatives considered"
- placeholder: "Any work-arounds you’ve tried or other approaches you considered."
+ placeholder: "Any work-arounds you've tried or other approaches you considered."
validations:
required: false
diff --git a/.github/ISSUE_TEMPLATE/general.yml b/.github/ISSUE_TEMPLATE/general.yml
new file mode 100644
index 000000000..0c90775ee
--- /dev/null
+++ b/.github/ISSUE_TEMPLATE/general.yml
@@ -0,0 +1,50 @@
+name: "📝 General issue"
+description: "Use this for questions, docs tweaks, refactors, or anything that isn't a Bug or Feature request."
+type: Task
+labels:
+ - status:needs-triage
+
+body:
+ - type: markdown
+ attributes:
+ value: |
+ **Thanks for opening an issue!**
+ This form is for ideas or tasks that don't fit the Bug or Feature templates.
+
+ - type: checkboxes
+ id: confirmations
+ attributes:
+ label: "Before submitting"
+ options:
+ - label: "I've checked [open issues](issues?q=is%3Aissue%20state%3Aopen) and found no similar item"
+ required: true
+ - label: "It's not really a bug report or a feature request"
+ required: false
+
+ - type: textarea
+ id: summary
+ attributes:
+ label: "What would you like to discuss or change?"
+ placeholder: |
+ A clear, concise description of the question, enhancement, refactor, or documentation update.
+ validations:
+ required: true
+
+ - type: textarea
+ id: context
+ attributes:
+ label: "Relevant context (optional)"
+ placeholder: |
+ Links, screenshots, or any additional details that will help us understand.
+ validations:
+ required: false
+
+ - type: dropdown
+ id: contribution
+ attributes:
+ label: Would you like to help drive or implement this?
+ options:
+ - "Not at this time"
+ - "Yes, I'd like to contribute"
+ validations:
+ required: false
diff --git a/.github/pipelex_labels.json b/.github/pipelex_labels.json
new file mode 100644
index 000000000..8c690d566
--- /dev/null
+++ b/.github/pipelex_labels.json
@@ -0,0 +1,102 @@
+[
+ {
+ "name": "priority:P0",
+ "color": "B60205",
+ "description": "Critical — stop the line"
+ },
+ {
+ "name": "priority:P1",
+ "color": "D93F0B",
+ "description": "High priority"
+ },
+ {
+ "name": "priority:P2",
+ "color": "E36209",
+ "description": "Normal priority"
+ },
+ {
+ "name": "priority:P3",
+ "color": "FBCA04",
+ "description": "Low priority"
+ },
+ {
+ "name": "status:needs-triage",
+ "color": "A2BFFC",
+ "description": "Awaiting triage"
+ },
+ {
+ "name": "status:needs-info",
+ "color": "1E90FF",
+ "description": "Needs more information"
+ },
+ {
+ "name": "status:blocked",
+ "color": "004385",
+ "description": "Work is blocked"
+ },
+ {
+ "name": "status:in-progress",
+ "color": "0969DA",
+ "description": "Currently being worked on"
+ },
+ {
+ "name": "status:review",
+ "color": "6CA4F8",
+ "description": "Awaiting code review"
+ },
+ {
+ "name": "status:done",
+ "color": "14866D",
+ "description": "Completed / merged"
+ },
+ {
+ "name": "status:duplicate",
+ "color": "6F42C1",
+ "description": "May close as soon as it's verified."
+ },
+ {
+ "name": "status:not-planned",
+ "color": "6A737D",
+ "description": "Signals a likely won't-fix before formal closure."
+ },
+ {
+ "name": "status:invalid",
+ "color": "E4E669",
+ "description": "Needs more info or out of scope."
+ },
+ {
+ "name": "area:api",
+ "color": "0E8A16",
+ "description": "Backend & public API"
+ },
+ {
+ "name": "area:cli",
+ "color": "1A7F37",
+ "description": "Command-line interface"
+ },
+ {
+ "name": "area:core",
+ "color": "005630",
+ "description": "Core library logic"
+ },
+ {
+ "name": "area:docs",
+ "color": "28A745",
+ "description": "Documentation"
+ },
+ {
+ "name": "area:tests",
+ "color": "7FDA9E",
+ "description": "Unit / integration / e2e tests"
+ },
+ {
+ "name": "good first issue",
+ "color": "FFD33D",
+ "description": "Great for new contributors"
+ },
+ {
+ "name": "help wanted",
+ "color": "FFEA7F",
+ "description": "Maintainers would love help"
+ }
+]
\ No newline at end of file
diff --git a/.github/workflows/deploy-doc.yml b/.github/workflows/deploy-docs.yml
similarity index 95%
rename from .github/workflows/deploy-doc.yml
rename to .github/workflows/deploy-docs.yml
index 6e10897fb..34a42ff7a 100644
--- a/.github/workflows/deploy-doc.yml
+++ b/.github/workflows/deploy-docs.yml
@@ -33,4 +33,4 @@ jobs:
run: uv pip install -e ".[docs]"
- name: Deploy documentation
- run: make doc-deploy
+ run: make docs-deploy
diff --git a/Makefile b/Makefile
index cfd69f9ec..d90a8d64a 100644
--- a/Makefile
+++ b/Makefile
@@ -82,12 +82,19 @@ make to - Shorthand -> test-ocr
make test-imgg - Run unit tests only for imgg (with prints)
make test-g - Shorthand -> test-imgg
+make check-unused-imports - Check for unused imports without fixing
+make fix-unused-imports - Fix unused imports with ruff
+make fui - Shorthand -> fix-unused-imports
+make check-TODOs - Check for TODOs
+
+make docs - Serve documentation with mkdocs
+make docs-check - Check documentation build with mkdocs
+make docs-deploy - Deploy documentation with mkdocs
+
make check - Shorthand -> format lint mypy
make c - Shorthand -> check
make cc - Shorthand -> cleanderived check
make li - Shorthand -> lock install
-make check-unused-imports - Check for unused imports without fixing
-make fix-unused-imports - Fix unused imports with ruff
endef
export HELP
@@ -101,7 +108,7 @@ export HELP
run-all-tests run-manual-trigger-gha-tests run-gha_disabled-tests \
validate v check c cc \
merge-check-ruff-lint merge-check-ruff-format merge-check-mypy merge-check-pyright \
- li check-unused-imports fix-unused-imports check-uv check-TODOs doc doc-check
+ li check-unused-imports fix-unused-imports check-uv check-TODOs docs docs-check docs-deploy
all help:
@echo "$$HELP"
@@ -390,45 +397,59 @@ merge-check-mypy: env
$(VENV_MYPY) --config-file pyproject.toml
##########################################################################################
-### SHORTHANDS
+### MISCELLANEOUS
##########################################################################################
check-unused-imports: env
$(call PRINT_TITLE,"Checking for unused imports without fixing")
$(VENV_RUFF) check --select=F401 --no-fix .
-c: init format lint pyright mypy
- @echo "> done: c = check"
-
-cc: init cleanderived c
- @echo "> done: cc = init cleanderived init format lint pyright mypy"
-
-check: cc check-unused-imports
- @echo "> done: check"
-
-v: init validate
- @echo "> done: v = validate"
+fix-unused-imports: env
+ $(call PRINT_TITLE,"Fixing unused imports")
+ $(VENV_RUFF) check --select=F401 --fix .
-li: lock install
- @echo "> done: lock install"
+fui: fix-unused-imports
+ @echo "> done: fui = fix-unused-imports"
check-TODOs: env
$(call PRINT_TITLE,"Checking for TODOs")
- $(VENV_RUFF) check --select=TD .
+ @$(VENV_RUFF) check --select=TD -v .
-fix-unused-imports: env
- $(call PRINT_TITLE,"Fixing unused imports")
- $(VENV_RUFF) check --select=F401 --fix .
+##########################################################################################
+### DOCUMENTATION
+##########################################################################################
-doc: env
+docs: env
$(call PRINT_TITLE,"Serving documentation with mkdocs")
$(VENV_MKDOCS) serve
-doc-check: env
+docs-check: env
$(call PRINT_TITLE,"Checking documentation build with mkdocs")
$(VENV_MKDOCS) build --strict
-doc-deploy: env
+docs-deploy: env
$(call PRINT_TITLE,"Deploying documentation with mkdocs")
$(VENV_MKDOCS) gh-deploy --force --clean
-
\ No newline at end of file
+
+##########################################################################################
+### SHORTHANDS
+##########################################################################################
+
+check-unused-imports: env
+ $(call PRINT_TITLE,"Checking for unused imports without fixing")
+ $(VENV_RUFF) check --select=F401 --no-fix .
+
+c: init format lint pyright mypy
+ @echo "> done: c = check"
+
+cc: init cleanderived c
+ @echo "> done: cc = init cleanderived init format lint pyright mypy"
+
+check: cc check-unused-imports
+ @echo "> done: check"
+
+v: init validate
+ @echo "> done: v = validate"
+
+li: lock install
+ @echo "> done: lock install"
\ No newline at end of file
diff --git a/docs/pages/build-reliable-ai-workflows-with-pipelex/configure-ai-llm-to-optimize-workflows.md b/docs/pages/build-reliable-ai-workflows-with-pipelex/configure-ai-llm-to-optimize-workflows.md
index cd431f7ac..931f1ba31 100644
--- a/docs/pages/build-reliable-ai-workflows-with-pipelex/configure-ai-llm-to-optimize-workflows.md
+++ b/docs/pages/build-reliable-ai-workflows-with-pipelex/configure-ai-llm-to-optimize-workflows.md
@@ -22,7 +22,7 @@ An LLM handle is a unique identifier that maps to a specific LLM configuration.
```toml
[llm_handles]
-gpt-4o-2024-08-06 = { llm_name = "gpt-4o", llm_version = "2024-08-06" }
+gpt-4o-2024-11-20 = { llm_name = "gpt-4o", llm_version = "2024-11-20" }
```
There's a much simpler syntax if you want a handle to the latest version and default platform:
diff --git a/pipelex/cogt/content_generation/content_generator_dry.py b/pipelex/cogt/content_generation/content_generator_dry.py
index 338a540b8..0c2bbecf7 100644
--- a/pipelex/cogt/content_generation/content_generator_dry.py
+++ b/pipelex/cogt/content_generation/content_generator_dry.py
@@ -61,6 +61,7 @@ class ContentGeneratorDry(ContentGeneratorProtocol):
class ObjectFactory(ModelFactory[object_class]): # type: ignore
__model__ = object_class
+ __check_model__ = True
__use_examples__ = True
__allow_none_optionals__ = False # Ensure Optional fields always get values
diff --git a/pipelex/core/working_memory_factory.py b/pipelex/core/working_memory_factory.py
index 329cb05e5..ec2befcae 100644
--- a/pipelex/core/working_memory_factory.py
+++ b/pipelex/core/working_memory_factory.py
@@ -146,6 +146,7 @@ class WorkingMemoryFactory(BaseModel):
# Create mock object using polyfactory
class MockFactory(ModelFactory[structure_class]): # type: ignore
__model__ = structure_class
+ __check_model__ = True
__use_examples__ = True
__allow_none_optionals__ = False # Ensure Optional fields always get values
diff --git a/pipelex/libraries/llm_deck/base_llm_deck.toml b/pipelex/libraries/llm_deck/base_llm_deck.toml
index 8a61500b0..bdb6d43c9 100644
--- a/pipelex/libraries/llm_deck/base_llm_deck.toml
+++ b/pipelex/libraries/llm_deck/base_llm_deck.toml
@@ -10,7 +10,7 @@ llm_external_handles = []
# Match a llm_handle with either just and llm_name
# or a complete blueprint including llm_version (defaulting to "latest") and llm_platform_choice (defaulting to "default").
[llm_handles]
-gpt-4o-2024-08-06 = { llm_name = "gpt-4o", llm_version = "2024-08-06" }
+gpt-4o-2024-11-20 = { llm_name = "gpt-4o", llm_version = "2024-11-20" }
best-claude = "claude-4-opus"
best-gemini = "gemini-2.5-pro"
best-mistral = "mistral-large"
diff --git a/pipelex/libraries/llm_integrations/openai.toml b/pipelex/libraries/llm_integrations/openai.toml
index 748794a1a..9225e8665 100644
--- a/pipelex/libraries/llm_integrations/openai.toml
+++ b/pipelex/libraries/llm_integrations/openai.toml
@@ -1,9 +1,7 @@
-
-
["gpt-3.5"."gpt-3.5-turbo".latest]
is_gen_object_supported = true
cost_per_million_tokens_usd = { input = 0.5, output = 1.5 }
-platform_llm_id = { azure_openai = "gpt-35-turbo-16k", openai = "gpt-3.5-turbo-1106" }
+platform_llm_id = { openai = "gpt-3.5-turbo-1106" }
default_platform = "openai"
[gpt-4.gpt-4.latest]
@@ -28,29 +26,25 @@ platform_llm_id = { openai = "gpt-4-1106-preview" }
is_gen_object_supported = true
is_vision_supported = false
cost_per_million_tokens_usd = { input = 10.0, output = 30.0 }
-platform_llm_id = { azure_openai = "gpt-4-turbo", openai = "gpt-4-turbo-2024-04-09" }
-default_platform = "openai"
+platform_llm_id = { openai = "gpt-4-turbo-2024-04-09" }
[gpt-4.gpt-4-turbo.latest]
is_gen_object_supported = true
is_vision_supported = false
cost_per_million_tokens_usd = { input = 10.0, output = 30.0 }
-platform_llm_id = { azure_openai = "gpt-4-turbo", openai = "gpt-4-turbo" }
-default_platform = "openai"
+platform_llm_id = { openai = "gpt-4-turbo" }
[gpt-4o.gpt-4o."2024-05-13"]
is_gen_object_supported = true
is_vision_supported = true
cost_per_million_tokens_usd = { input = 5.0, output = 15.0 }
-platform_llm_id = { azure_openai = "gpt-4o", openai = "gpt-4o-2024-05-13" }
-default_platform = "openai"
+platform_llm_id = { openai = "gpt-4o-2024-05-13" }
[gpt-4.gpt-4o."2024-08-06"]
is_gen_object_supported = true
is_vision_supported = true
cost_per_million_tokens_usd = { input = 2.5, output = 10.0 }
-platform_llm_id = { azure_openai = "gpt-4o-2024-08-06", openai = "gpt-4o-2024-08-06" }
-default_platform = "openai"
+platform_llm_id = { openai = "gpt-4o-2024-08-06" }
[gpt-4.gpt-4o."2024-11-20"]
is_gen_object_supported = true
@@ -70,61 +64,54 @@ default_platform = "openai"
is_gen_object_supported = true
is_vision_supported = true
cost_per_million_tokens_usd = { input = 0.15, output = 0.6 }
-platform_llm_id = { azure_openai = "gpt-4o-mini", openai = "gpt-4o-mini-2024-07-18" }
+platform_llm_id = { azure_openai = "gpt-4o-mini-2024-07-18", openai = "gpt-4o-mini-2024-07-18" }
default_platform = "openai"
[gpt-4o.gpt-4o-mini.latest]
is_gen_object_supported = true
is_vision_supported = true
cost_per_million_tokens_usd = { input = 0.15, output = 0.6 }
-platform_llm_id = { azure_openai = "gpt-4o-mini", openai = "gpt-4o-mini" }
+platform_llm_id = { azure_openai = "gpt-4o-mini-2024-07-18", openai = "gpt-4o-mini" }
default_platform = "openai"
-["gpt-4.5"."gpt-4.5-preview".latest]
-is_gen_object_supported = true
-is_vision_supported = true
-cost_per_million_tokens_usd = { input = 75, output = 150 }
-platform_llm_id = { openai = "gpt-4.5-preview" }
-
["gpt-4.1"."gpt-4.1".latest]
is_gen_object_supported = true
is_vision_supported = true
cost_per_million_tokens_usd = { input = 2, output = 8}
-platform_llm_id = { azure_openai = "gpt-4.1", openai = "gpt-4.1" }
-default_platform = "openai" # TODO: make it work with azure_openai by using automatically the right azure resource
+platform_llm_id = { azure_openai = "gpt-4.1-2025-04-14", openai = "gpt-4.1" }
+default_platform = "openai"
["gpt-4.1"."gpt-4.1-mini".latest]
is_gen_object_supported = true
is_vision_supported = true
cost_per_million_tokens_usd = { input = 0.4, output = 1.6 }
-platform_llm_id = { azure_openai = "gpt-4.1-mini", openai = "gpt-4.1-mini" }
-default_platform = "openai" # TODO: make it work with azure_openai by using automatically the right azure resource
+platform_llm_id = { azure_openai = "gpt-4.1-mini-2025-04-14", openai = "gpt-4.1-mini" }
+default_platform = "openai"
["gpt-4.1"."gpt-4.1-nano".latest]
is_gen_object_supported = true
is_vision_supported = true
cost_per_million_tokens_usd = { input = 0.1, output = 0.4 }
-platform_llm_id = { azure_openai = "gpt-4.1-nano", openai = "gpt-4.1-nano" }
-default_platform = "openai" # TODO: make it work with azure_openai by using automatically the right azure resource
+platform_llm_id = { azure_openai = "gpt-4.1-nano-2025-04-14", openai = "gpt-4.1-nano" }
+default_platform = "openai"
[o.o1-mini.latest]
is_gen_object_supported = false
is_vision_supported = false
cost_per_million_tokens_usd = { input = 3.0, output = 12.0 }
-platform_llm_id = { openai = "o1-mini" }
+platform_llm_id = { azure_openai = "o1-mini-2024-09-12", openai = "o1-mini" }
[o.o1.latest]
is_gen_object_supported = true
is_vision_supported = true
cost_per_million_tokens_usd = { input = 15.0, output = 60.0 }
-platform_llm_id = { openai = "o1" }
+platform_llm_id = { azure_openai = "o1-2024-12-17", openai = "o1" }
[o.o3-mini.latest]
is_gen_object_supported = true
cost_per_million_tokens_usd = { input = 1.1, output = 4.4 }
-# platform_llm_id = { openai = "o3-mini", azure_openai = "o3-mini" }
-platform_llm_id = { openai = "o3-mini"}
-default_platform = "openai" # TODO: make it work with azure_openai by using automatically the right azure resource
+platform_llm_id = { azure_openai = "o3-mini-2025-01-31", openai = "o3-mini"}
+default_platform = "openai"
[o.o3.latest]
is_gen_object_supported = true
diff --git a/tests/integration/pipelex/conftest.py b/tests/integration/pipelex/conftest.py
index e541ec21d..248c359fb 100644
--- a/tests/integration/pipelex/conftest.py
+++ b/tests/integration/pipelex/conftest.py
@@ -124,11 +124,11 @@ def llm_creator(request: pytest.FixtureRequest) -> LLMCreator:
@pytest.fixture(
params=[
# LLMPlatform.ANTHROPIC,
- # LLMPlatform.AZURE_OPENAI,
+ LLMPlatform.AZURE_OPENAI,
# LLMPlatform.BEDROCK,
# LLMPlatform.BEDROCK_ANTHROPIC,
# LLMPlatform.MISTRAL,
- LLMPlatform.OPENAI,
+ # LLMPlatform.OPENAI,
# LLMPlatform.PERPLEXITY,
# LLMPlatform.VERTEXAI,
# LLMPlatform.CUSTOM_LLM,
diff --git a/tests/integration/pipelex/plugins/test_external_plugin.py b/tests/integration/pipelex/plugins/test_external_plugin.py
index 8dc670b01..def57eaec 100644
--- a/tests/integration/pipelex/plugins/test_external_plugin.py
+++ b/tests/integration/pipelex/plugins/test_external_plugin.py
@@ -52,6 +52,7 @@ class MockExternalLLMWorker(LLMWorkerAbstract):
) -> BaseModelTypeVar:
class ObjectFactory(ModelFactory[schema]): # type: ignore
__model__ = schema
+ __check_model__ = True
__use_examples__ = True
__allow_none_optionals__ = False # Ensure Optional fields always get values