v0.10.26 (#12452)

CHANGELOG.md

@@ -1,5 +1,82 @@
 # ChangeLog
 
+## [2024-03-31]
+
+### `llama-index-core` [0.10.26]
+
+- pass proper query bundle in QueryFusionRetriever (#12387)
+- Update llama_parse_json_element.py to fix error on lists (#12402)
+- Add node postprocessors to retriever tool (#12415)
+- Fix bug where user specified llm is not respected in fallback logic in element node parsers(#12403)
+- log proper LLM response key for async callback manager events (#12421)
+- Deduplicate the two built-in react system prompts; Also make it read from a Markdown file (#12307)
+- fix bug in BatchEvalRunner for multi-evaluator eval_kwargs_lists (#12418)
+- add the callback manager event for vector store index insert_nodes (#12443)
+- fixes an issue with serializing chat messages into chat stores when they contain pydantic API objects (#12394)
+- fixes an issue with slow memory.get() operation (caused by multiple calls to get_all()) (#12394)
+- fixes an issue where an agent+tool message pair is cut from the memory (#12394)
+- Added `FnNodeMapping` for object index (#12391)
+- Make object mapping optional / hidden for object index (#12391)
+- Make object index easier to create from existing vector db (#12391)
+- When LLM failed to follow the react response template, tell it so #12300
+
+### `llama-index-embeddings-cohere` [0.1.5]
+
+- Bump cohere version to 5.1.1 (#12279)
+
+### `llama-index-embeddings-itrex` [0.1.0]
+
+- add Intel Extension for Transformers embedding model (#12410)
+
+### `llama-index-graph-stores-neo4j` [0.1.4]
+
+- make neo4j query insensitive (#12337)
+
+### `llama-index-llms-cohere` [0.1.5]
+
+- Bump cohere version to 5.1.1 (#12279)
+
+### `llama-index-llms-ipex-llm` [0.1.0]
+
+- add ipex-llm integration (#12322)
+
+### `llama-index-llms-litellm` [0.1.4]
+
+- Fix litellm ChatMessage role validation error (#12449)
+
+### `llama-index-llms-openai` [0.1.14]
+
+- Use `FunctionCallingLLM` base class in OpenAI (#12227)
+
+### `llama-index-packs-self-rag` [0.1.4]
+
+- Fix llama-index-core dep (#12374)
+
+### `llama-index-postprocessor-cohere-rerank` [0.1.4]
+
+- Bump cohere version to 5.1.1 (#12279)
+
+### `llama-index-postprocessor-rankllm-rerank` [0.1.1]
+
+- Added RankLLM rerank (#12296)
+- RankLLM fixes (#12399)
+
+### `llama-index-readers-papers` [0.1.4]
+
+- Fixed bug with path names (#12366)
+
+### `llama-index-vector-stores-analyticdb` [0.1.1]
+
+- Add AnalyticDB VectorStore (#12230)
+
+### `llama-index-vector-stores-kdbai` [0.1.4]
+
+- Fixed typo in imports/readme (#12370)
+
+### `llama-index-vector-stores-qdrant` [0.1.5]
+
+- add `in` filter operator for qdrant (#12376)
+
 ## [2024-03-27]
 
 ### `llama-index-core` [0.10.25]

docs/docs/CHANGELOG.md

@@ -1,5 +1,82 @@
 # ChangeLog
 
+## [2024-03-31]
+
+### `llama-index-core` [0.10.26]
+
+- pass proper query bundle in QueryFusionRetriever (#12387)
+- Update llama_parse_json_element.py to fix error on lists (#12402)
+- Add node postprocessors to retriever tool (#12415)
+- Fix bug where user specified llm is not respected in fallback logic in element node parsers(#12403)
+- log proper LLM response key for async callback manager events (#12421)
+- Deduplicate the two built-in react system prompts; Also make it read from a Markdown file (#12307)
+- fix bug in BatchEvalRunner for multi-evaluator eval_kwargs_lists (#12418)
+- add the callback manager event for vector store index insert_nodes (#12443)
+- fixes an issue with serializing chat messages into chat stores when they contain pydantic API objects (#12394)
+- fixes an issue with slow memory.get() operation (caused by multiple calls to get_all()) (#12394)
+- fixes an issue where an agent+tool message pair is cut from the memory (#12394)
+- Added `FnNodeMapping` for object index (#12391)
+- Make object mapping optional / hidden for object index (#12391)
+- Make object index easier to create from existing vector db (#12391)
+- When LLM failed to follow the react response template, tell it so #12300
+
+### `llama-index-embeddings-cohere` [0.1.5]
+
+- Bump cohere version to 5.1.1 (#12279)
+
+### `llama-index-embeddings-itrex` [0.1.0]
+
+- add Intel Extension for Transformers embedding model (#12410)
+
+### `llama-index-graph-stores-neo4j` [0.1.4]
+
+- make neo4j query insensitive (#12337)
+
+### `llama-index-llms-cohere` [0.1.5]
+
+- Bump cohere version to 5.1.1 (#12279)
+
+### `llama-index-llms-ipex-llm` [0.1.0]
+
+- add ipex-llm integration (#12322)
+
+### `llama-index-llms-litellm` [0.1.4]
+
+- Fix litellm ChatMessage role validation error (#12449)
+
+### `llama-index-llms-openai` [0.1.14]
+
+- Use `FunctionCallingLLM` base class in OpenAI (#12227)
+
+### `llama-index-packs-self-rag` [0.1.4]
+
+- Fix llama-index-core dep (#12374)
+
+### `llama-index-postprocessor-cohere-rerank` [0.1.4]
+
+- Bump cohere version to 5.1.1 (#12279)
+
+### `llama-index-postprocessor-rankllm-rerank` [0.1.1]
+
+- Added RankLLM rerank (#12296)
+- RankLLM fixes (#12399)
+
+### `llama-index-readers-papers` [0.1.4]
+
+- Fixed bug with path names (#12366)
+
+### `llama-index-vector-stores-analyticdb` [0.1.1]
+
+- Add AnalyticDB VectorStore (#12230)
+
+### `llama-index-vector-stores-kdbai` [0.1.4]
+
+- Fixed typo in imports/readme (#12370)
+
+### `llama-index-vector-stores-qdrant` [0.1.5]
+
+- add `in` filter operator for qdrant (#12376)
+
 ## [2024-03-27]
 
 ### `llama-index-core` [0.10.25]

docs/docs/api_reference/embeddings/huggingface_itrex.md

@@ -0,0 +1,4 @@
+::: llama_index.embeddings.huggingface_itrex
+    options:
+      members:
+        - QuantizedBgeEmbedding

docs/docs/api_reference/llms/ipex_llm.md

@@ -0,0 +1,4 @@
+::: llama_index.llms.ipex_llm
+    options:
+      members:
+        - IpexLLM

docs/docs/api_reference/postprocessor/rankllm_rerank.md

@@ -0,0 +1,4 @@
+::: llama_index.postprocessor.rankllm_rerank
+    options:
+      members:
+        - CLASS

docs/docs/api_reference/storage/vector_store/analyticdb.md

@@ -0,0 +1,4 @@
+::: llama_index.vector_stores.analyticdb
+    options:
+      members:
+        - AnalyticDBVectorStore

docs/mkdocs.yml

@@ -182,6 +182,7 @@ nav:
           - ./examples/embeddings/llamafile.ipynb
           - ./examples/embeddings/premai.ipynb
           - ./examples/embeddings/alephalpha.ipynb
+          - ./examples/embeddings/itrex.ipynb
       - Evaluation:
           - ./examples/evaluation/TonicValidateEvaluators.ipynb
           - ./examples/evaluation/semantic_similarity_eval.ipynb
@@ -291,6 +292,7 @@ nav:
           - ./examples/llm/premai.ipynb
           - ./examples/llm/solar.ipynb
           - ./examples/llm/alephalpha.ipynb
+          - ./examples/llm/ipex_llm.ipynb
       - Low Level:
           - ./examples/low_level/oss_ingestion_retrieval.ipynb
           - ./examples/low_level/fusion_retriever.ipynb
@@ -351,6 +353,7 @@ nav:
           - ./examples/node_postprocessor/OptimizerDemo.ipynb
           - ./examples/node_postprocessor/TimeWeightedPostprocessorDemo.ipynb
           - ./examples/node_postprocessor/JinaRerank.ipynb
+          - ./examples/node_postprocessor/rankLLM.ipynb
       - Object Stores:
           - ./examples/objects/object_index.ipynb
       - Output Parsers:
@@ -676,6 +679,7 @@ nav:
           - ./api_reference/embeddings/google.md
           - ./api_reference/embeddings/gradient.md
           - ./api_reference/embeddings/huggingface.md
+          - ./api_reference/embeddings/huggingface_itrex.md
           - ./api_reference/embeddings/huggingface_optimum.md
           - ./api_reference/embeddings/huggingface_optimum_intel.md
           - ./api_reference/embeddings/index.md
@@ -750,6 +754,7 @@ nav:
           - ./api_reference/llms/groq.md
           - ./api_reference/llms/huggingface.md
           - ./api_reference/llms/index.md
+          - ./api_reference/llms/ipex_llm.md
           - ./api_reference/llms/konko.md
           - ./api_reference/llms/langchain.md
           - ./api_reference/llms/litellm.md
@@ -904,6 +909,7 @@ nav:
           - ./api_reference/postprocessor/presidio.md
           - ./api_reference/postprocessor/prev_next.md
           - ./api_reference/postprocessor/rankgpt_rerank.md
+          - ./api_reference/postprocessor/rankllm_rerank.md
           - ./api_reference/postprocessor/sbert_rerank.md
           - ./api_reference/postprocessor/sentence_optimizer.md
           - ./api_reference/postprocessor/similarity.md
@@ -1185,6 +1191,7 @@ nav:
           - Storage:
               - ./api_reference/storage/storage_context.md
           - Vector Store:
+              - ./api_reference/storage/vector_store/analyticdb.md
               - ./api_reference/storage/vector_store/astra_db.md
               - ./api_reference/storage/vector_store/awadb.md
               - ./api_reference/storage/vector_store/azureaisearch.md
@@ -1763,6 +1770,9 @@ plugins:
             - ../llama-index-integrations/postprocessor/llama-index-postprocessor-voyageai-rerank
             - ../llama-index-integrations/readers/llama-index-readers-gcs
             - ../llama-index-integrations/readers/llama-index-readers-readme
+            - ../llama-index-integrations/embeddings/llama-index-embeddings-huggingface-itrex
+            - ../llama-index-integrations/postprocessor/llama-index-postprocessor-rankllm-rerank
+            - ../llama-index-integrations/llms/llama-index-llms-ipex-llm
   - 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__ = "0.10.25.post3"
+__version__ = "0.10.26"
 
 import logging
 from logging import NullHandler

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 = "0.10.25.post3"
+version = "0.10.26"
 
 [tool.poetry.dependencies]
 SQLAlchemy = {extras = ["asyncio"], version = ">=1.4.49"}

llama-index-integrations/vector_stores/llama-index-vector-stores-kdbai/pyproject.toml

@@ -30,7 +30,6 @@ exclude = ["**/BUILD"]
 license = "MIT"
 name = "llama-index-vector-stores-kdbai"
 readme = "README.md"
-version = "0.1.3"
 
 [tool.poetry.dependencies]
 python = ">=3.8.1,<4.0"