v0.12.12 (run-llama#17561)

logan-markewich · web-flow · commit 1183f72f83e1 · 2025-01-20T10:59:26.000-06:00
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,5 +1,40 @@
 # ChangeLog
 
+## [2025-01-20]
+
+### `llama-index-core` [0.12.12]
+
+- feat: add AgentWorkflow system to support single and multi-agent workflows (#17237)
+- Fix image-path validation in ImageNode (#17558)
+
+### `llama-index-indices-managed-vectara` [0.4.0]
+
+- (breaking change) API Migration (#17545)
+
+### `llama-index-llms-anthropic` [0.6.4]
+
+- feat: support direct PDF handling for Anthropic (#17506)
+
+### `llama-index-llms-fireworks` [0.3.1]
+
+- Deepseek-v3 is now supported by fireworks (#17518)
+
+### `llama-index-llms-stepfun` [1.0.0]
+
+- feat: add stepfun integrations (#17514)
+
+### `llama-index-multi-modal-llms-gemini` [0.5.0]
+
+- refact: make GeminiMultiModal a thin wrapper around Gemini (#17501)
+
+### `llama-index-postprocessor-longllmlingua` [0.4.0]
+
+- Add longllmlingua2 integration (#17531)
+
+### `llama-index-readers-web` [0.3.4]
+
+- feat: Hyperbrowser Web Reader (#17489)
+
 ## [2025-01-15]
 
 ### `llama-index-core` [0.12.11]
diff --git a/docs/docs/CHANGELOG.md b/docs/docs/CHANGELOG.md
@@ -1,5 +1,40 @@
 # ChangeLog
 
+## [2025-01-20]
+
+### `llama-index-core` [0.12.12]
+
+- feat: add AgentWorkflow system to support single and multi-agent workflows (#17237)
+- Fix image-path validation in ImageNode (#17558)
+
+### `llama-index-indices-managed-vectara` [0.4.0]
+
+- (breaking change) API Migration (#17545)
+
+### `llama-index-llms-anthropic` [0.6.4]
+
+- feat: support direct PDF handling for Anthropic (#17506)
+
+### `llama-index-llms-fireworks` [0.3.1]
+
+- Deepseek-v3 is now supported by fireworks (#17518)
+
+### `llama-index-llms-stepfun` [1.0.0]
+
+- feat: add stepfun integrations (#17514)
+
+### `llama-index-multi-modal-llms-gemini` [0.5.0]
+
+- refact: make GeminiMultiModal a thin wrapper around Gemini (#17501)
+
+### `llama-index-postprocessor-longllmlingua` [0.4.0]
+
+- Add longllmlingua2 integration (#17531)
+
+### `llama-index-readers-web` [0.3.4]
+
+- feat: Hyperbrowser Web Reader (#17489)
+
 ## [2025-01-15]
 
 ### `llama-index-core` [0.12.11]
diff --git a/llama-index-core/llama_index/core/__init__.py b/llama-index-core/llama_index/core/__init__.py
@@ -1,6 +1,6 @@
 """Init file of LlamaIndex."""
 
-__version__ = "0.12.11"
+__version__ = "0.12.12"
 
 import logging
 from logging import NullHandler
diff --git a/llama-index-core/pyproject.toml b/llama-index-core/pyproject.toml
@@ -46,7 +46,7 @@ name = "llama-index-core"
 packages = [{include = "llama_index"}]
 readme = "README.md"
 repository = "https://github.com/run-llama/llama_index"
-version = "0.12.11"
+version = "0.12.12"
 
 [tool.poetry.dependencies]
 SQLAlchemy = {extras = ["asyncio"], version = ">=1.4.49"}
diff --git a/llama-index-integrations/llms/llama-index-llms-gemini/pyproject.toml b/llama-index-integrations/llms/llama-index-llms-gemini/pyproject.toml
@@ -27,13 +27,13 @@ exclude = ["**/BUILD"]
 license = "MIT"
 name = "llama-index-llms-gemini"
 readme = "README.md"
-version = "0.4.3"
+version = "0.4.4"
 
 [tool.poetry.dependencies]
 python = ">=3.9,<4.0"
 pillow = "^10.2.0"
 google-generativeai = ">=0.5.2"
-llama-index-core = "^0.12.0"
+llama-index-core = "^0.12.12"
 
 [tool.poetry.group.dev.dependencies]
 ipython = "8.10.0"
diff --git a/llama-index-integrations/llms/llama-index-llms-ibm/pyproject.toml b/llama-index-integrations/llms/llama-index-llms-ibm/pyproject.toml
@@ -34,7 +34,7 @@ readme = "README.md"
 version = "0.3.1"
 
 [tool.poetry.dependencies]
-python = ">=3.10,<4.0"
+python = ">=3.10,<3.13"
 ibm-watsonx-ai = ">=1.1.24"
 pyarrow = "*"
 llama-index-core = "^0.12.0"
diff --git a/llama-index-integrations/multi_modal_llms/llama-index-multi-modal-llms-gemini/pyproject.toml b/llama-index-integrations/multi_modal_llms/llama-index-multi-modal-llms-gemini/pyproject.toml
@@ -27,13 +27,13 @@ exclude = ["**/BUILD"]
 license = "MIT"
 name = "llama-index-multi-modal-llms-gemini"
 readme = "README.md"
-version = "0.4.1"
+version = "0.5.0"
 
 [tool.poetry.dependencies]
 python = ">=3.9,<4.0"
-llama-index-llms-gemini = "^0.4.0"
+llama-index-llms-gemini = "^0.4.4"
 pillow = "^10.2.0"
-llama-index-core = "^0.12.0"
+llama-index-core = "^0.12.12"
 
 [tool.poetry.group.dev.dependencies]
 ipython = "8.10.0"
diff --git a/llama-index-integrations/retrievers/llama-index-retrievers-bm25/llama_index/retrievers/bm25/base.py b/llama-index-integrations/retrievers/llama-index-retrievers-bm25/llama_index/retrievers/bm25/base.py
@@ -33,7 +33,7 @@
 
 
 class BM25Retriever(BaseRetriever):
-    """A BM25 retriever that uses the BM25 algorithm to retrieve nodes.
+    r"""A BM25 retriever that uses the BM25 algorithm to retrieve nodes.
 
     Args:
         nodes (List[BaseNode], optional):
@@ -52,6 +52,10 @@ class BM25Retriever(BaseRetriever):
             The objects to retrieve. Defaults to None.
         object_map (dict, optional):
             A map of object IDs to nodes. Defaults to None.
+        token_pattern (str, optional):
+            The token pattern to use. Defaults to (?u)\\b\\w\\w+\\b.
+        skip_stemming (bool, optional):
+            Whether to skip stemming. Defaults to False.
         verbose (bool, optional):
             Whether to show progress. Defaults to False.
     """
@@ -67,9 +71,13 @@ def __init__(
         objects: Optional[List[IndexNode]] = None,
         object_map: Optional[dict] = None,
         verbose: bool = False,
+        skip_stemming: bool = False,
+        token_pattern: str = r"(?u)\b\w\w+\b",
     ) -> None:
         self.stemmer = stemmer or Stemmer.Stemmer("english")
         self.similarity_top_k = similarity_top_k
+        self.token_pattern = token_pattern
+        self.skip_stemming = skip_stemming
 
         if existing_bm25 is not None:
             self.bm25 = existing_bm25
@@ -83,7 +91,8 @@ def __init__(
             corpus_tokens = bm25s.tokenize(
                 [node.get_content(metadata_mode=MetadataMode.EMBED) for node in nodes],
                 stopwords=language,
-                stemmer=self.stemmer,
+                stemmer=self.stemmer if not skip_stemming else None,
+                token_pattern=self.token_pattern,
                 show_progress=verbose,
             )
             self.bm25 = bm25s.BM25()
@@ -105,6 +114,8 @@ def from_defaults(
         language: str = "en",
         similarity_top_k: int = DEFAULT_SIMILARITY_TOP_K,
         verbose: bool = False,
+        skip_stemming: bool = False,
+        token_pattern: str = r"(?u)\b\w\w+\b",
         # deprecated
         tokenizer: Optional[Callable[[str], List[str]]] = None,
     ) -> "BM25Retriever":
@@ -134,6 +145,8 @@ def from_defaults(
             language=language,
             similarity_top_k=similarity_top_k,
             verbose=verbose,
+            skip_stemming=skip_stemming,
+            token_pattern=token_pattern,
         )
 
     def get_persist_args(self) -> Dict[str, Any]:
@@ -161,7 +174,10 @@ def from_persist_dir(cls, path: str, **kwargs: Any) -> "BM25Retriever":
     def _retrieve(self, query_bundle: QueryBundle) -> List[NodeWithScore]:
         query = query_bundle.query_str
         tokenized_query = bm25s.tokenize(
-            query, stemmer=self.stemmer, show_progress=self._verbose
+            query,
+            stemmer=self.stemmer if not self.skip_stemming else None,
+            token_pattern=self.token_pattern,
+            show_progress=self._verbose,
         )
         indexes, scores = self.bm25.retrieve(
             tokenized_query, k=self.similarity_top_k, show_progress=self._verbose
diff --git a/llama-index-integrations/retrievers/llama-index-retrievers-bm25/pyproject.toml b/llama-index-integrations/retrievers/llama-index-retrievers-bm25/pyproject.toml
@@ -27,7 +27,7 @@ exclude = ["**/BUILD"]
 license = "MIT"
 name = "llama-index-retrievers-bm25"
 readme = "README.md"
-version = "0.5.0"
+version = "0.5.1"
 
 [tool.poetry.dependencies]
 python = ">=3.9,<4.0"
diff --git a/poetry.lock b/poetry.lock
diff --git a/pyproject.toml b/pyproject.toml
