v0.10.68 (#15557)

CHANGELOG.md

@@ -1,5 +1,77 @@
 # ChangeLog
 
+## [2024-08-21]
+
+### `llama-index-core` [0.10.68]
+
+- remove nested progress bars in base element node parser (#15550)
+- Adding exhaustive docs for workflows (#15556)
+- Adding multi-strategy workflow with reflection notebook example (#15445)
+- remove openai dep from core (#15527)
+- Improve token counter to handle more response types (#15501)
+- feat: Allow using step decorator without parentheses (#15540)
+- feat: workflow services (aka nested workflows) (#15325)
+- Remove requirement to specify "allowed_query_fields" parameter when using "cypher_validator" in TextToCypher retriever (#15506)
+
+### `llama-index-embeddings-mistralai` [0.1.6]
+
+- fix mistral embeddings usage (#15508)
+
+### `llama-index-embeddings-ollama` [0.2.0]
+
+- use ollama client for embeddings (#15478)
+
+### `llama-index-embeddings-openvino` [0.2.1]
+
+- support static input shape for openvino embedding and reranker (#15521)
+
+### `llama-index-graph-stores-neptune` [0.1.8]
+
+- Added code to expose structured schema for Neptune (#15507)
+
+### `llama-index-llms-ai21` [0.3.2]
+
+- Integration: AI21 Tools support (#15518)
+
+### `llama-index-llms-bedrock` [0.1.13]
+
+- Support token counting for llama-index integration with bedrock (#15491)
+
+### `llama-index-llms-cohere` [0.2.2]
+
+- feat: add tool calling support for achat cohere (#15539)
+
+### `llama-index-llms-gigachat` [0.1.0]
+
+- Adding gigachat LLM support (#15313)
+
+### `llama-index-llms-openai` [0.1.31]
+
+- Fix incorrect type in OpenAI token usage report (#15524)
+- allow streaming token counts for openai (#15548)
+
+### `llama-index-postprocessor-nvidia-rerank` [0.2.1]
+
+- add truncate support (#15490)
+- Update to 0.2.0, remove old code (#15533)
+- update default model to nvidia/nv-rerankqa-mistral-4b-v3 (#15543)
+
+### `llama-index-readers-bitbucket` [0.1.4]
+
+- Fixing the issues in loading file paths from bitbucket (#15311)
+
+### `llama-index-readers-google` [0.3.1]
+
+- enhance google drive reader for improved functionality and usability (#15512)
+
+### `llama-index-readers-remote` [0.1.6]
+
+- check and sanitize remote reader urls (#15494)
+
+### `llama-index-vector-stores-qdrant` [0.2.17]
+
+- fix: setting IDF modifier in QdrantVectorStore for sparse vectors (#15538)
+
 ## [2024-08-18]
 
 ### `llama-index-core` [0.10.67]

docs/docs/CHANGELOG.md

@@ -1,5 +1,77 @@
 # ChangeLog
 
+## [2024-08-21]
+
+### `llama-index-core` [0.10.68]
+
+- remove nested progress bars in base element node parser (#15550)
+- Adding exhaustive docs for workflows (#15556)
+- Adding multi-strategy workflow with reflection notebook example (#15445)
+- remove openai dep from core (#15527)
+- Improve token counter to handle more response types (#15501)
+- feat: Allow using step decorator without parentheses (#15540)
+- feat: workflow services (aka nested workflows) (#15325)
+- Remove requirement to specify "allowed_query_fields" parameter when using "cypher_validator" in TextToCypher retriever (#15506)
+
+### `llama-index-embeddings-mistralai` [0.1.6]
+
+- fix mistral embeddings usage (#15508)
+
+### `llama-index-embeddings-ollama` [0.2.0]
+
+- use ollama client for embeddings (#15478)
+
+### `llama-index-embeddings-openvino` [0.2.1]
+
+- support static input shape for openvino embedding and reranker (#15521)
+
+### `llama-index-graph-stores-neptune` [0.1.8]
+
+- Added code to expose structured schema for Neptune (#15507)
+
+### `llama-index-llms-ai21` [0.3.2]
+
+- Integration: AI21 Tools support (#15518)
+
+### `llama-index-llms-bedrock` [0.1.13]
+
+- Support token counting for llama-index integration with bedrock (#15491)
+
+### `llama-index-llms-cohere` [0.2.2]
+
+- feat: add tool calling support for achat cohere (#15539)
+
+### `llama-index-llms-gigachat` [0.1.0]
+
+- Adding gigachat LLM support (#15313)
+
+### `llama-index-llms-openai` [0.1.31]
+
+- Fix incorrect type in OpenAI token usage report (#15524)
+- allow streaming token counts for openai (#15548)
+
+### `llama-index-postprocessor-nvidia-rerank` [0.2.1]
+
+- add truncate support (#15490)
+- Update to 0.2.0, remove old code (#15533)
+- update default model to nvidia/nv-rerankqa-mistral-4b-v3 (#15543)
+
+### `llama-index-readers-bitbucket` [0.1.4]
+
+- Fixing the issues in loading file paths from bitbucket (#15311)
+
+### `llama-index-readers-google` [0.3.1]
+
+- enhance google drive reader for improved functionality and usability (#15512)
+
+### `llama-index-readers-remote` [0.1.6]
+
+- check and sanitize remote reader urls (#15494)
+
+### `llama-index-vector-stores-qdrant` [0.2.17]
+
+- fix: setting IDF modifier in QdrantVectorStore for sparse vectors (#15538)
+
 ## [2024-08-18]
 
 ### `llama-index-core` [0.10.67]

docs/docs/api_reference/embeddings/gigachat.md

@@ -0,0 +1,4 @@
+::: llama_index.embeddings.gigachat
+    options:
+      members:
+        - GigaChatEmbedding

docs/docs/api_reference/llms/gigachat.md

@@ -0,0 +1,4 @@
+::: llama_index.llms.gigachat
+    options:
+      members:
+        - GigaChatLLM

docs/mkdocs.yml

@@ -169,6 +169,7 @@ nav:
           - ./examples/data_connectors/ObsidianReaderDemo.ipynb
           - ./examples/data_connectors/PathwayReaderDemo.ipynb
           - ./examples/data_connectors/PineconeDemo.ipynb
+          - ./examples/data_connectors/PreprocessReaderDemo.ipynb
           - ./examples/data_connectors/PsychicDemo.ipynb
           - ./examples/data_connectors/QdrantDemo.ipynb
           - ./examples/data_connectors/SlackDemo.ipynb
@@ -206,6 +207,7 @@ nav:
           - ./examples/embeddings/fastembed.ipynb
           - ./examples/embeddings/fireworks.ipynb
           - ./examples/embeddings/gemini.ipynb
+          - ./examples/embeddings/gigachat.ipynb
           - ./examples/embeddings/google_palm.ipynb
           - ./examples/embeddings/gradient.ipynb
           - ./examples/embeddings/huggingface.ipynb
@@ -648,6 +650,7 @@ nav:
           - ./examples/workflow/corrective_rag_pack.ipynb
           - ./examples/workflow/function_calling_agent.ipynb
           - ./examples/workflow/long_rag_pack.ipynb
+          - ./examples/workflow/multi_strategy_workflow.ipynb
           - ./examples/workflow/parallel_execution.ipynb
           - ./examples/workflow/rag.ipynb
           - ./examples/workflow/react_agent.ipynb
@@ -823,6 +826,7 @@ nav:
           - ./api_reference/embeddings/fastembed.md
           - ./api_reference/embeddings/fireworks.md
           - ./api_reference/embeddings/gemini.md
+          - ./api_reference/embeddings/gigachat.md
           - ./api_reference/embeddings/google.md
           - ./api_reference/embeddings/gradient.md
           - ./api_reference/embeddings/huggingface.md
@@ -920,6 +924,7 @@ nav:
           - ./api_reference/llms/fireworks.md
           - ./api_reference/llms/friendli.md
           - ./api_reference/llms/gemini.md
+          - ./api_reference/llms/gigachat.md
           - ./api_reference/llms/gradient.md
           - ./api_reference/llms/groq.md
           - ./api_reference/llms/huggingface.md
@@ -2122,6 +2127,8 @@ plugins:
             - ../llama-index-integrations/indices/llama-index-indices-managed-bge-m3
             - ../llama-index-integrations/tools/llama-index-tools-box
             - ../llama-index-integrations/llms/llama-index-llms-sambanova
+            - ../llama-index-integrations/embeddings/llama-index-embeddings-gigachat
+            - ../llama-index-integrations/llms/llama-index-llms-gigachat
   - redirects:
       redirect_maps:
         ./api/llama_index.vector_stores.MongoDBAtlasVectorSearch.html: api_reference/storage/vector_store/mongodb.md

llama-index-core/llama_index/core/__init__.py

@@ -1,6 +1,6 @@
 """Init file of LlamaIndex."""
 
-__version__ = "0.10.67"
+__version__ = "0.10.68.post1"
 
 import logging
 from logging import NullHandler

llama-index-core/llama_index/core/postprocessor/optimizer.py

@@ -79,9 +79,9 @@ def __init__(
                 )
 
         if tokenizer_fn is None:
-            import nltk.data
+            import nltk
 
-            tokenizer = nltk.data.load("tokenizers/punkt/english.pickle")
+            tokenizer = nltk.tokenize.PunktSentenceTokenizer()
             tokenizer_fn = tokenizer.tokenize
         self._tokenizer_fn = tokenizer_fn
 

llama-index-core/llama_index/core/utils.py

@@ -62,9 +62,9 @@ def __init__(self) -> None:
             nltk.download("stopwords", download_dir=self._nltk_data_dir)
 
         try:
-            nltk.data.find("tokenizers/punkt")
+            nltk.data.find("tokenizers/punkt_tab")
         except LookupError:
-            nltk.download("punkt", download_dir=self._nltk_data_dir)
+            nltk.download("punkt_tab", download_dir=self._nltk_data_dir)
 
     @property
     def stopwords(self) -> List[str]:

llama-index-core/pyproject.toml

@@ -43,7 +43,7 @@ name = "llama-index-core"
 packages = [{include = "llama_index"}]
 readme = "README.md"
 repository = "https://github.com/run-llama/llama_index"
-version = "0.10.67"
+version = "0.10.68.post1"
 
 [tool.poetry.dependencies]
 SQLAlchemy = {extras = ["asyncio"], version = ">=1.4.49"}
@@ -55,6 +55,7 @@ nest-asyncio = "^1.5.8"
 nltk = ">=3.8.1,!=3.9"  # Should be >= 3.8.2 but nltk removed 3.8.2 from pypi, 3.9 is broken
 numpy = "<2.0.0"  # Pin until we adapt to Numpy v2
 pandas = "*"
+pydantic = "<3.0"
 python = ">=3.8.1,<4.0"
 tenacity = ">=8.2.0,!=8.4.0,<9.0.0"  # Avoid 8.4.0 which lacks tenacity.asyncio
 tiktoken = ">=0.3.3"