[version] bump to v0.9.26 (#9870)

CHANGELOG.md

 # ChangeLog
 
+## [0.9.26] - 2024-01-05
+
+### New Features
+
+- Added a `BaseChatStore` and `SimpleChatStore` abstraction for dedicated chat memory storage (#9863)
+- Enable custom `tree_sitter` parser to be passed into `CodeSplitter` (#9845)
+- Created a `BaseAutoRetriever` base class, to allow other retrievers to extend to auto modes (#9846)
+- Added support for Nvidia Triton LLM (#9488)
+- Added `DeepEval` one-click observability (#9801)
+
+### Bug Fixes / Nits
+
+- Updated the guidance integration to work with the latest version (#9830)
+- Made text storage optional for doctores/ingestion pipeline (#9847)
+- Added missing `sphinx-automodapi` dependency for docs (#9852)
+- Return actual node ids in weaviate query results (#9854)
+- Added prompt formatting to LangChainLLM (#9844)
+
 ## [0.9.25] - 2024-01-03
 
 ### New Features

llama_index/VERSION

-0.9.25.post1
+0.9.26

llama_index/storage/chat_store/simple_chat_store.py

@@ -72,7 +72,7 @@ class SimpleChatStore(BaseChatStore):
             fs.makedirs(dirpath)
 
         with fs.open(persist_path, "w") as f:
-            f.write(json.dumps(self.store))
+            f.write(json.dumps(self.json()))
 
     @classmethod
     def from_persist_path(
@@ -85,5 +85,5 @@ class SimpleChatStore(BaseChatStore):
         if not fs.exists(persist_path):
             return cls()
         with fs.open(persist_path, "r") as f:
-            store = json.load(f)
-        return cls(store=store)
+            data = json.load(f)
+        return cls.parse_raw(data)

pyproject.toml

@@ -42,7 +42,7 @@ name = "llama-index"
 packages = [{include = "llama_index"}]
 readme = "README.md"
 repository = "https://github.com/run-llama/llama_index"
-version = "0.9.25.post1"
+version = "0.9.26"
 
 [tool.poetry.dependencies]
 SQLAlchemy = {extras = ["asyncio"], version = ">=1.4.49"}