cbrkit 1.2.0__tar.gz → 1.3.0__tar.gz

{cbrkit-1.2.0 → cbrkit-1.3.0}/PKG-INFO

@@ -1,16 +1,16 @@
-Metadata-Version: 2.3
+Metadata-Version: 2.4
 Name: cbrkit
-Version: 1.2.0
+Version: 1.3.0
 Summary: Customizable Case-Based Reasoning (CBR) toolkit for Python with a built-in API and CLI
 Keywords: cbr,case-based reasoning,api,similarity,nlp,retrieval,cli,tool,library
 Author: Mirko Lenz
 Author-email: Mirko Lenz <mirko@mirkolenz.com>
+License-Expression: MIT
 Classifier: Development Status :: 4 - Beta
 Classifier: Environment :: Console
 Classifier: Framework :: Pytest
 Classifier: Intended Audience :: Developers
 Classifier: Intended Audience :: Science/Research
-Classifier: License :: OSI Approved :: MIT License
 Classifier: Natural Language :: English
 Classifier: Operating System :: OS Independent
 Classifier: Programming Language :: Python :: 3.13
@@ -41,9 +41,9 @@ Requires-Dist: fastmcp>=3,<4 ; extra == 'api'
 Requires-Dist: bm25s[core,stem,indexing]>=0.3,<1 ; extra == 'bm25'
 Requires-Dist: chromadb>=1,<2 ; extra == 'chromadb'
 Requires-Dist: chonkie>=1,<2 ; extra == 'chunking'
-Requires-Dist: rich>=13,<15 ; extra == 'cli'
-Requires-Dist: typer>=0.9,<1 ; extra == 'cli'
-Requires-Dist: cohere>=5,<6 ; extra == 'cohere'
+Requires-Dist: rich>=14,<16 ; extra == 'cli'
+Requires-Dist: typer>=0.20,<1 ; extra == 'cli'
+Requires-Dist: cohere>=6,<7 ; extra == 'cohere'
 Requires-Dist: ranx>=0.3,<1 ; extra == 'eval'
 Requires-Dist: google-genai>=1,<2 ; extra == 'google'
 Requires-Dist: networkx>=3,<4 ; extra == 'graphs'
@@ -66,6 +66,7 @@ Requires-Dist: sentence-transformers>=4,<6 ; extra == 'transformers'
 Requires-Dist: torch>=2.5,<3 ; extra == 'transformers'
 Requires-Dist: transformers>=4,<6 ; extra == 'transformers'
 Requires-Dist: voyageai>=0.3,<1 ; extra == 'voyageai'
+Requires-Dist: zvec>=0.2,<1 ; extra == 'zvec'
 Requires-Python: >=3.13, <4
 Project-URL: Repository, https://github.com/wi2trier/cbrkit
 Project-URL: Documentation, https://wi2trier.github.io/cbrkit/
@@ -97,6 +98,7 @@ Provides-Extra: sql
 Provides-Extra: timeseries
 Provides-Extra: transformers
 Provides-Extra: voyageai
+Provides-Extra: zvec
 Description-Content-Type: text/markdown
 
 <!-- markdownlint-disable MD033 MD041 -->
@@ -846,17 +848,17 @@ result = cbrkit.retrieval.apply_query(casebase, query, (retriever, reranker))
 
 ### Indexed Retrieval
 
-Some retrievers like `bm25`, `embed`, and `lancedb` support **indexed retrieval**, where the casebase is pre-indexed once and then queried without passing the full casebase each time.
+Retrievers like `bm25`, `embed`, `lancedb`, `chromadb`, and `zvec` support **indexed retrieval**, where the casebase is pre-indexed once and then queried without passing the full casebase each time.
 This is useful for large casebases or when using external search backends.
 
-To use indexed retrieval, first create a retriever and call its `index()` method:
+To use indexed retrieval, first create a retriever and call its `put_index()` method:
 
 ```python
 from frozendict import frozendict
 
 bm25_func = cbrkit.sim.embed.bm25(language="en")
 retriever = cbrkit.retrieval.bm25(conversion_func=bm25_func)
-retriever.create_index(frozendict(casebase))
+retriever.put_index(frozendict(casebase))
 ```
 
 Then pass an empty casebase (`{}`) to signal that the retriever should use its pre-indexed data:
@@ -873,7 +875,7 @@ result = cbrkit.retrieval.apply_query_indexed(query, retriever)
 result = cbrkit.retrieval.apply_queries_indexed(queries, retriever)
 ```
 
-If a retriever receives an empty casebase but has not been indexed yet, a `ValueError` is raised with a message to call `index()` first.
+If a retriever receives an empty casebase but has not been indexed yet, a `ValueError` is raised with a message to call `put_index()` first.
 
 The `System` class also supports indexed retrieval by defaulting the casebase to an empty dict.
 This allows creating a system where all retrievers are pre-indexed and no casebase needs to be provided at query time.

{cbrkit-1.2.0 → cbrkit-1.3.0}/README.md

@@ -745,17 +745,17 @@ result = cbrkit.retrieval.apply_query(casebase, query, (retriever, reranker))
 
 ### Indexed Retrieval
 
-Some retrievers like `bm25`, `embed`, and `lancedb` support **indexed retrieval**, where the casebase is pre-indexed once and then queried without passing the full casebase each time.
+Retrievers like `bm25`, `embed`, `lancedb`, `chromadb`, and `zvec` support **indexed retrieval**, where the casebase is pre-indexed once and then queried without passing the full casebase each time.
 This is useful for large casebases or when using external search backends.
 
-To use indexed retrieval, first create a retriever and call its `index()` method:
+To use indexed retrieval, first create a retriever and call its `put_index()` method:
 
 ```python
 from frozendict import frozendict
 
 bm25_func = cbrkit.sim.embed.bm25(language="en")
 retriever = cbrkit.retrieval.bm25(conversion_func=bm25_func)
-retriever.create_index(frozendict(casebase))
+retriever.put_index(frozendict(casebase))
 ```
 
 Then pass an empty casebase (`{}`) to signal that the retriever should use its pre-indexed data:
@@ -772,7 +772,7 @@ result = cbrkit.retrieval.apply_query_indexed(query, retriever)
 result = cbrkit.retrieval.apply_queries_indexed(queries, retriever)
 ```
 
-If a retriever receives an empty casebase but has not been indexed yet, a `ValueError` is raised with a message to call `index()` first.
+If a retriever receives an empty casebase but has not been indexed yet, a `ValueError` is raised with a message to call `put_index()` first.
 
 The `System` class also supports indexed retrieval by defaulting the casebase to an empty dict.
 This allows creating a system where all retrievers are pre-indexed and no casebase needs to be provided at query time.

{cbrkit-1.2.0 → cbrkit-1.3.0}/pyproject.toml

@@ -1,9 +1,10 @@
 [project]
 name = "cbrkit"
-version = "1.2.0"
+version = "1.3.0"
 description = "Customizable Case-Based Reasoning (CBR) toolkit for Python with a built-in API and CLI"
 authors = [{ name = "Mirko Lenz", email = "mirko@mirkolenz.com" }]
 readme = "README.md"
+license = "MIT"
 keywords = [
     "cbr",
     "case-based reasoning",
@@ -21,7 +22,6 @@ classifiers = [
     "Framework :: Pytest",
     "Intended Audience :: Developers",
     "Intended Audience :: Science/Research",
-    "License :: OSI Approved :: MIT License",
     "Natural Language :: English",
     "Operating System :: OS Independent",
     "Programming Language :: Python :: 3.13",
@@ -49,7 +49,7 @@ dependencies = [
 [project.optional-dependencies]
 # LLM providers
 anthropic = ["anthropic>=0.40,<1"]
-cohere = ["cohere>=5,<6"]
+cohere = ["cohere>=6,<7"]
 google = ["google-genai>=1,<2"]
 instructor = ["instructor>=1,<2"]
 ollama = ["ollama>=0.3,<1"]
@@ -77,10 +77,10 @@ chromadb = ["chromadb>=1,<2"]
 lancedb = ["lancedb>=0.20,<1"]
 pandas = ["pandas>=2,<4"]
 sql = ["sqlalchemy>=2,<3"]
-# zvec = ["zvec>=0.2,<1"]
+zvec = ["zvec>=0.2,<1"]
 
 # Tools
-cli = ["rich>=13,<15", "typer>=0.9,<1"]
+cli = ["rich>=14,<16", "typer>=0.20,<1"]
 eval = ["ranx>=0.3,<1"]
 timeseries = ["minineedle>=3,<4"]
 

{cbrkit-1.2.0 → cbrkit-1.3.0}/src/cbrkit/api.py

@@ -189,7 +189,7 @@ def synthesize(
     )
 
 
-def openapi_generator():
+def openapi_generator() -> dict[str, Any]:
     """Generate and cache the OpenAPI schema for the CBRKit API."""
     if not app.openapi_schema:
         app.openapi_schema = get_openapi(
@@ -203,4 +203,4 @@ def openapi_generator():
     return app.openapi_schema
 
 
-app.openapi = openapi_generator  # type: ignore[assignment]
+app.openapi = openapi_generator  # type: ignore[assignment]  # ty: ignore[invalid-assignment]

{cbrkit-1.2.0 → cbrkit-1.3.0}/src/cbrkit/eval/common.py

@@ -487,15 +487,18 @@ def generate_metrics(
         >>> generate_metrics(["precision", "recall"], ks=5)
         ['precision@5', 'recall@5']
     """
-    if not isinstance(ks, Iterable):
-        ks = [ks]
-
-    if not isinstance(relevance_levels, Iterable):
-        relevance_levels = [relevance_levels]
+    ks_list: list[int | None] = [ks] if ks is None or isinstance(ks, int) else list(ks)
+    relevance_levels_list: list[int | None] = (
+        [relevance_levels]
+        if relevance_levels is None or isinstance(relevance_levels, int)
+        else list(relevance_levels)
+    )
 
     return [
-        generate_metric(*args)
-        for args in itertools.product(metrics, ks, relevance_levels)
+        generate_metric(metric, k, relevance_level)
+        for metric, k, relevance_level in itertools.product(
+            metrics, ks_list, relevance_levels_list
+        )
     ]
 
 

{cbrkit-1.2.0 → cbrkit-1.3.0}/src/cbrkit/helpers.py

@@ -244,7 +244,7 @@ def singleton[T](x: Mapping[Any, T] | Collection[T]) -> T:
     if isinstance(x, Mapping):
         return cast(T, next(iter(x.values())))
     elif isinstance(x, Collection):
-        return cast(T, next(iter(x)))
+        return next(iter(x))
 
     raise TypeError(f"Expected a Mapping or Collection, but got {type(x)}")
 
@@ -390,7 +390,7 @@ def is_factory[T](obj: MaybeFactory[T]) -> TypeIs[Factory[T]]:
 def produce_factory[T](obj: MaybeFactory[T]) -> T:
     """Resolve a factory by calling it, or return the value as-is."""
     if is_factory(obj):
-        return obj()
+        return cast(T, obj())
 
     return cast(T, obj)