v0.10.47

CHANGELOG.md

@@ -1,5 +1,89 @@
 # ChangeLog
 
+## [2024-06-19]
+
+### `llama-index-core` [0.10.47]
+
+- added average precision as a retrieval metric (#14189)
+- added `.show_jupyter_graph()` method visualizing default simple graph_store in jupyter notebooks (#14104)
+- corrected the behaviour of nltk file lookup (#14040)
+- Added helper args to generate_qa_pairs (#14054)
+- Add new chunking semantic chunking method: double-pass merging (#13629)
+- enable stepwise execution of query pipelines (#14117)
+- Replace tenacity upper limit by only rejecting 8.4.0 (#14218)
+- propagate error_on_no_tool_call kwarg in `llm.predict_and_call()` (#14253)
+- in query pipeline, avoid casting nodes as strings and use `get_content()` instead (#14242)
+- Fix NLSQLTableQueryEngine response metadata (#14169)
+- do not overwrite relations in default simple property graph (#14244)
+
+### `llama-index-embeddings-ipex-llm` [0.1.5]
+
+- Enable selecting Intel GPU for ipex embedding integrations (#14214)
+
+### `llama-index-embeddings-mixedbreadai` [0.1.0]
+
+- add mixedbread ai integration (#14161)
+
+### `llama-index-graph-stores-neo4j` [0.2.5]
+
+- Add default node property to neo4j upsert relations (#14095)
+
+### `llama-index-indices-managed-postgresml` [0.3.0]
+
+- Added re-ranking into the PostgresML Managed Index (#14134)
+
+### `llama-index-llms-ai21` [0.3.0]
+
+- use async AI21 client for async methods (#14193)
+
+### `llama-index-llms-bedrock-converse` [0.1.2]
+
+- Added (fake) async calls to avoid errors (#14241)
+
+### `llama-index-llms-deepinfra` [0.1.3]
+
+- Add function calling to deep infra llm (#14127)
+
+### `llama-index-llms-ipex-llm` [0.1.8]
+
+- Enable selecting Intel GPU for ipex embedding integrations (#14214)
+
+### `llama-index-llms-oci-genai` [0.1.1]
+
+- add command r support oci genai (#14080)
+
+### `llama-index-llms-premai` [0.1.7]
+
+- Prem AI Templates Llama Index support (#14105)
+
+### `llama-index-llms-you` [0.1.0]
+
+- Integrate You.com conversational APIs (#14207)
+
+### `llama-index-readers-mongodb` [0.1.8]
+
+- Add metadata field "collection_name" to SimpleMongoReader (#14245)
+
+### `llama-index-readers-pdf-marker` [0.1.0]
+
+- add marker-pdf reader (#14099)
+
+### `llama-index-readers-upstage` [0.1.0]
+
+- Added upstage as a reader (#13415)
+
+### `llama-index-postprocessor-mixedbreadai-rerank` [0.1.0]
+
+- add mixedbread ai integration (#14161)
+
+### `llama-index-vector-stores-lancedb` [0.1.6]
+
+- LanceDB: code cleanup, minor updates (#14077)
+
+### `llama-index-vector-stores-opensearch` [0.1.12]
+
+- add option to customize default OpenSearch Client and Engine (#14249)
+
 ## [2024-06-17]
 
 ### `llama-index-core`[0.10.46]

docs/docs/CHANGELOG.md

@@ -1,5 +1,89 @@
 # ChangeLog
 
+## [2024-06-19]
+
+### `llama-index-core` [0.10.47]
+
+- added average precision as a retrieval metric (#14189)
+- added `.show_jupyter_graph()` method visualizing default simple graph_store in jupyter notebooks (#14104)
+- corrected the behaviour of nltk file lookup (#14040)
+- Added helper args to generate_qa_pairs (#14054)
+- Add new chunking semantic chunking method: double-pass merging (#13629)
+- enable stepwise execution of query pipelines (#14117)
+- Replace tenacity upper limit by only rejecting 8.4.0 (#14218)
+- propagate error_on_no_tool_call kwarg in `llm.predict_and_call()` (#14253)
+- in query pipeline, avoid casting nodes as strings and use `get_content()` instead (#14242)
+- Fix NLSQLTableQueryEngine response metadata (#14169)
+- do not overwrite relations in default simple property graph (#14244)
+
+### `llama-index-embeddings-ipex-llm` [0.1.5]
+
+- Enable selecting Intel GPU for ipex embedding integrations (#14214)
+
+### `llama-index-embeddings-mixedbreadai` [0.1.0]
+
+- add mixedbread ai integration (#14161)
+
+### `llama-index-graph-stores-neo4j` [0.2.5]
+
+- Add default node property to neo4j upsert relations (#14095)
+
+### `llama-index-indices-managed-postgresml` [0.3.0]
+
+- Added re-ranking into the PostgresML Managed Index (#14134)
+
+### `llama-index-llms-ai21` [0.3.0]
+
+- use async AI21 client for async methods (#14193)
+
+### `llama-index-llms-bedrock-converse` [0.1.2]
+
+- Added (fake) async calls to avoid errors (#14241)
+
+### `llama-index-llms-deepinfra` [0.1.3]
+
+- Add function calling to deep infra llm (#14127)
+
+### `llama-index-llms-ipex-llm` [0.1.8]
+
+- Enable selecting Intel GPU for ipex embedding integrations (#14214)
+
+### `llama-index-llms-oci-genai` [0.1.1]
+
+- add command r support oci genai (#14080)
+
+### `llama-index-llms-premai` [0.1.7]
+
+- Prem AI Templates Llama Index support (#14105)
+
+### `llama-index-llms-you` [0.1.0]
+
+- Integrate You.com conversational APIs (#14207)
+
+### `llama-index-readers-mongodb` [0.1.8]
+
+- Add metadata field "collection_name" to SimpleMongoReader (#14245)
+
+### `llama-index-readers-pdf-marker` [0.1.0]
+
+- add marker-pdf reader (#14099)
+
+### `llama-index-readers-upstage` [0.1.0]
+
+- Added upstage as a reader (#13415)
+
+### `llama-index-postprocessor-mixedbreadai-rerank` [0.1.0]
+
+- add mixedbread ai integration (#14161)
+
+### `llama-index-vector-stores-lancedb` [0.1.6]
+
+- LanceDB: code cleanup, minor updates (#14077)
+
+### `llama-index-vector-stores-opensearch` [0.1.12]
+
+- add option to customize default OpenSearch Client and Engine (#14249)
+
 ## [2024-06-17]
 
 ### `llama-index-core`[0.10.46]

docs/docs/api_reference/embeddings/mixedbreadai.md

@@ -0,0 +1,4 @@
+::: llama_index.embeddings.mixedbreadai
+    options:
+      members:
+        - MixedbreadAIEmbedding

docs/docs/api_reference/llms/you.md

@@ -0,0 +1,4 @@
+::: llama_index.llms.you
+    options:
+      members:
+        - You

docs/docs/api_reference/postprocessor/mixedbreadai_rerank.md

@@ -0,0 +1,4 @@
+::: llama_index.postprocessor.mixedbreadai_rerank
+    options:
+      members:
+        - MixedbreadAIRerank

docs/docs/api_reference/readers/pdf_marker.md

@@ -0,0 +1,4 @@
+::: llama_index.readers.pdf_marker
+    options:
+      members:
+        - PDFMarkerReader

docs/mkdocs.yml

@@ -201,6 +201,7 @@ nav:
           - ./examples/embeddings/llamafile.ipynb
           - ./examples/embeddings/llm_rails.ipynb
           - ./examples/embeddings/mistralai.ipynb
+          - ./examples/embeddings/mixedbreadai.ipynb
           - ./examples/embeddings/nomic.ipynb
           - ./examples/embeddings/nvidia.ipynb
           - ./examples/embeddings/oci_genai.ipynb
@@ -387,6 +388,7 @@ nav:
           - ./examples/multi_tenancy/multi_tenancy_rag.ipynb
       - Node Parsers & Text Splitters:
           - ./examples/node_parsers/semantic_chunking.ipynb
+          - ./examples/node_parsers/semantic_double_merging_chunking.ipynb
       - Node Postprocessors:
           - ./examples/node_postprocessor/CohereRerank.ipynb
           - ./examples/node_postprocessor/ColbertRerank.ipynb
@@ -397,6 +399,7 @@ nav:
           - ./examples/node_postprocessor/LLMReranker-Lyft-10k.ipynb
           - ./examples/node_postprocessor/LongContextReorder.ipynb
           - ./examples/node_postprocessor/MetadataReplacementDemo.ipynb
+          - ./examples/node_postprocessor/MixedbreadAIRerank.ipynb
           - ./examples/node_postprocessor/NVIDIARerank.ipynb
           - ./examples/node_postprocessor/OptimizerDemo.ipynb
           - ./examples/node_postprocessor/PII.ipynb
@@ -776,6 +779,7 @@ nav:
           - ./api_reference/embeddings/llamafile.md
           - ./api_reference/embeddings/llm_rails.md
           - ./api_reference/embeddings/mistralai.md
+          - ./api_reference/embeddings/mixedbreadai.md
           - ./api_reference/embeddings/nomic.md
           - ./api_reference/embeddings/nvidia.md
           - ./api_reference/embeddings/oci_genai.md
@@ -900,6 +904,7 @@ nav:
           - ./api_reference/llms/vllm.md
           - ./api_reference/llms/watsonx.md
           - ./api_reference/llms/xinference.md
+          - ./api_reference/llms/you.md
       - Llama Datasets:
           - ./api_reference/llama_dataset/index.md
       - Llama Packs:
@@ -1025,6 +1030,7 @@ nav:
           - ./api_reference/postprocessor/long_context_reorder.md
           - ./api_reference/postprocessor/longllmlingua.md
           - ./api_reference/postprocessor/metadata_replacement.md
+          - ./api_reference/postprocessor/mixedbreadai_rerank.md
           - ./api_reference/postprocessor/nvidia_rerank.md
           - ./api_reference/postprocessor/openvino_rerank.md
           - ./api_reference/postprocessor/presidio.md
@@ -1202,6 +1208,7 @@ nav:
           - ./api_reference/readers/patentsview.md
           - ./api_reference/readers/pathway.md
           - ./api_reference/readers/pdb.md
+          - ./api_reference/readers/pdf_marker.md
           - ./api_reference/readers/pdf_table.md
           - ./api_reference/readers/pebblo.md
           - ./api_reference/readers/pinecone.md
@@ -1990,6 +1997,10 @@ plugins:
             - ../llama-index-integrations/llms/llama-index-llms-bedrock-converse
             - ../llama-index-integrations/llms/llama-index-llms-ibm
             - ../llama-index-integrations/readers/llama-index-readers-upstage
+            - ../llama-index-integrations/embeddings/llama-index-embeddings-mixedbreadai
+            - ../llama-index-integrations/postprocessor/llama-index-postprocessor-mixedbreadai-rerank
+            - ../llama-index-integrations/readers/llama-index-readers-pdf-marker
+            - ../llama-index-integrations/llms/llama-index-llms-you
   - 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__ = "0.10.46"
+__version__ = "0.10.47"
 
 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 = "0.10.46"
+version = "0.10.47"
 
 [tool.poetry.dependencies]
 SQLAlchemy = {extras = ["asyncio"], version = ">=1.4.49"}

llama-index-integrations/embeddings/llama-index-embeddings-mixedbreadai/pyproject.toml

@@ -51,5 +51,5 @@ types-Deprecated = ">=0.1.0"
 types-PyYAML = "^6.0.12.12"
 types-protobuf = "^4.24.0.4"
 types-redis = "4.5.5.0"
-types-requests = "2.28.11.8"
+types-requests = ">=2.28.11.8"
 types-setuptools = "67.1.0.0"

llama-index-integrations/llms/llama-index-llms-premai/pyproject.toml

@@ -27,7 +27,7 @@ exclude = ["**/BUILD"]
 license = "MIT"
 name = "llama-index-llms-premai"
 readme = "README.md"
-version = "0.1.6"
+version = "0.1.7"
 
 [tool.poetry.dependencies]
 python = ">=3.8.1,<4.0"

llama-index-integrations/postprocessor/llama-index-postprocessor-mixedbreadai-rerank/pyproject.toml

@@ -53,5 +53,5 @@ types-Deprecated = ">=0.1.0"
 types-PyYAML = "^6.0.12.12"
 types-protobuf = "^4.24.0.4"
 types-redis = "4.5.5.0"
-types-requests = "2.28.11.8"
+types-requests = ">=2.28.11.8"
 types-setuptools = "67.1.0.0"

llama-index-integrations/readers/llama-index-readers-confluence/pyproject.toml

@@ -28,7 +28,7 @@ license = "MIT"
 maintainers = ["zywilliamli"]
 name = "llama-index-readers-confluence"
 readme = "README.md"
-version = "0.1.5"
+version = "0.1.6"
 
 [tool.poetry.dependencies]
 python = ">=3.8.1,<4.0"

llama-index-integrations/readers/llama-index-readers-pdf-marker/pyproject.toml

@@ -33,7 +33,7 @@ readme = "README.md"
 version = "0.1.0"
 
 [tool.poetry.dependencies]
-python = ">=3.8.1,<4.0"
+python = ">=3.9,<4.0"
 llama-index-core = "^0.10.0"
 marker-pdf = "^0.2.0"