Merge branch 'main' into main

run-llama · Jan 9, 2025 · 7b13f78 · 7b13f78
2 parents df7fcc5 + 526d4c1
commit 7b13f78
Show file tree

Hide file tree

Showing 84 changed files with 1,697 additions and 736 deletions.
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -2,8 +2,6 @@
 default_language_version:
   python: python3
 
-exclude: "llama-index-integrations/vector_stores/llama-index-vector-stores-wordlift/manager_client/.*"
-
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
     rev: v4.5.0

diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,5 +1,96 @@
 # ChangeLog
 
+## [2024-12-31]
+
+### `llama-index-core` [0.12.10]
+
+- remove asserts from schema llm extractor (#17425)
+- feat: support typing.Annotated for adding parameter descriptions in FunctionTools (#17411)
+- Guess image_mimetype for ImageNode (#17422)
+
+### `llama-index-embeddings-nvidia` [0.3.1]
+
+- NVIDIA Support for v2 Embedding & Reranking NIMs #(17410)
+
+### `llama-index-embeddings-openvino` [0.5.1]
+
+- update deps of OpenVINO packages (#17419)
+
+### `llama-index-multi-modal-llms-openai` [0.4.2]
+
+- Add support for gpt-4o-2024-08-06 to multi modal llms (#17405)
+
+### `llama-index-packs-raptor` [0.3.1]
+
+- Fix for llama_index.packs.raptor tree_traversal retrieval (#17406)
+
+### `llama-index-postprocessor-openvino-rerank` [0.4.1]
+
+- update deps of OpenVINO packages (#17419)
+
+### `llama-index-readers-file` [0.4.2]
+
+- Remove MarkdownReader from the default loaders in SimpleDirectoryReader (#17412)
+
+### `llama-index-core` [0.12.9]
+
+- clean up type hints in schema extractor (#17394)
+- Fix IndexError in LLM Reranking when handling malformed LLM responses (#17353)
+
+### `llama-index-llms-bedrock-converse` [0.4.3]
+
+- Fix Regression on Tools use for Bedrock Converse (#17364)
+
+### `llama-index-llms-sagemaker-endpoint` [0.3.1]
+
+- Pass `aws_region_name` to `get_aws_service_client()` in SageMakerLLM (#12000)
+
+### `llama-index-postprocessor-voyageai-rerank` [0.3.2]
+
+- VoyageAIRerank constructor fix for truncation (#17343)
+
+### `llama-index-readers-gitlab` [0.3.1]
+
+- Fix: Properly add blob documents from Gitlab Repo (#17392)
+
+### `llama-index-readers-rss` [0.3.2]
+
+- Fix minor issues in rss (#17351)
+
+### `llama-index-readers-web` [0.3.3]
+
+- fix: prevent infinite recursion in `get_article_urls` (#17360)
+
+### `llama-index-vector-stores-azureaisearch` [0.3.2]
+
+- azureaisearch: add semantic search mode support for async queries (#17335)
+
+### `llama-index-vector-stores-azurecosmosnosql` [1.3.1]
+
+- fix storeindex cosmosnosql query issue - (BadRequest) (#17385)
+
+### `llama-index-vector-stores-milvus` [0.5.0]
+
+- feat: milvus async (#17378)
+
+### `llama-index-vector-stores-opensearch` [0.5.2]
+
+- Fix typo in property name (#17365)
+- bugfix when initializing with async aoss vector store (#17340)
+
+### `llama-index-vector-stores-tablestore` [0.2.2]
+
+- TablestoreVectorStore: support hybrid query, modify some documents. (#17366)
+- TablestoreVectorStore check the Dimension of the embedding when writing it to store. (#17321)
+
+### `llama-index-vector-stores-qdrant` [0.4.2]
+
+- qdrant filter fix for `query_str` is None (#17377)
+
+### `llama-index-vector-stores-weaviate` [1.3.1]
+
+- implement `client_kwargs["custom_batch"]` for weaviate (#17347)
+
 ## [2024-12-20]
 
 ### `llama-index-core` [0.12.8]

diff --git a/docs/docs/CHANGELOG.md b/docs/docs/CHANGELOG.md
@@ -1,5 +1,96 @@
 # ChangeLog
 
+## [2024-12-31]
+
+### `llama-index-core` [0.12.10]
+
+- remove asserts from schema llm extractor (#17425)
+- feat: support typing.Annotated for adding parameter descriptions in FunctionTools (#17411)
+- Guess image_mimetype for ImageNode (#17422)
+
+### `llama-index-embeddings-nvidia` [0.3.1]
+
+- NVIDIA Support for v2 Embedding & Reranking NIMs #(17410)
+
+### `llama-index-embeddings-openvino` [0.5.1]
+
+- update deps of OpenVINO packages (#17419)
+
+### `llama-index-multi-modal-llms-openai` [0.4.2]
+
+- Add support for gpt-4o-2024-08-06 to multi modal llms (#17405)
+
+### `llama-index-packs-raptor` [0.3.1]
+
+- Fix for llama_index.packs.raptor tree_traversal retrieval (#17406)
+
+### `llama-index-postprocessor-openvino-rerank` [0.4.1]
+
+- update deps of OpenVINO packages (#17419)
+
+### `llama-index-readers-file` [0.4.2]
+
+- Remove MarkdownReader from the default loaders in SimpleDirectoryReader (#17412)
+
+### `llama-index-core` [0.12.9]
+
+- clean up type hints in schema extractor (#17394)
+- Fix IndexError in LLM Reranking when handling malformed LLM responses (#17353)
+
+### `llama-index-llms-bedrock-converse` [0.4.3]
+
+- Fix Regression on Tools use for Bedrock Converse (#17364)
+
+### `llama-index-llms-sagemaker-endpoint` [0.3.1]
+
+- Pass `aws_region_name` to `get_aws_service_client()` in SageMakerLLM (#12000)
+
+### `llama-index-postprocessor-voyageai-rerank` [0.3.2]
+
+- VoyageAIRerank constructor fix for truncation (#17343)
+
+### `llama-index-readers-gitlab` [0.3.1]
+
+- Fix: Properly add blob documents from Gitlab Repo (#17392)
+
+### `llama-index-readers-rss` [0.3.2]
+
+- Fix minor issues in rss (#17351)
+
+### `llama-index-readers-web` [0.3.3]
+
+- fix: prevent infinite recursion in `get_article_urls` (#17360)
+
+### `llama-index-vector-stores-azureaisearch` [0.3.2]
+
+- azureaisearch: add semantic search mode support for async queries (#17335)
+
+### `llama-index-vector-stores-azurecosmosnosql` [1.3.1]
+
+- fix storeindex cosmosnosql query issue - (BadRequest) (#17385)
+
+### `llama-index-vector-stores-milvus` [0.5.0]
+
+- feat: milvus async (#17378)
+
+### `llama-index-vector-stores-opensearch` [0.5.2]
+
+- Fix typo in property name (#17365)
+- bugfix when initializing with async aoss vector store (#17340)
+
+### `llama-index-vector-stores-tablestore` [0.2.2]
+
+- TablestoreVectorStore: support hybrid query, modify some documents. (#17366)
+- TablestoreVectorStore check the Dimension of the embedding when writing it to store. (#17321)
+
+### `llama-index-vector-stores-qdrant` [0.4.2]
+
+- qdrant filter fix for `query_str` is None (#17377)
+
+### `llama-index-vector-stores-weaviate` [1.3.1]
+
+- implement `client_kwargs["custom_batch"]` for weaviate (#17347)
+
 ## [2024-12-20]
 
 ### `llama-index-core` [0.12.8]

diff --git a/docs/docs/api_reference/storage/docstore/azurecosmosnosql.md b/docs/docs/api_reference/storage/docstore/azurecosmosnosql.md
@@ -0,0 +1,4 @@
+::: llama_index.storage.docstore.azurecosmosnosql
+    options:
+      members:
+        - AzureCosmosNoSqlIndexStore
diff --git a/docs/docs/community/integrations/vector_stores.md b/docs/docs/community/integrations/vector_stores.md
@@ -47,6 +47,7 @@ as the storage backend for `VectorStoreIndex`.
 - Upstash (`UpstashVectorStore`). [Quickstart](https://upstash.com/docs/vector/overall/getstarted)
 - Vertex AI Vector Search (`VertexAIVectorStore`). [Quickstart](https://cloud.google.com/vertex-ai/docs/vector-search/quickstart)
 - Weaviate (`WeaviateVectorStore`). [Installation](https://weaviate.io/developers/weaviate/installation). [Python Client](https://weaviate.io/developers/weaviate/client-libraries/python).
+- WordLift (`WordliftVectorStore`). [Python Client](https://pypi.org/project/wordlift-client/).
 - Zep (`ZepVectorStore`). [Installation](https://docs.getzep.com/deployment/quickstart/). [Python Client](https://docs.getzep.com/sdk/).
 - Zilliz (`MilvusVectorStore`). [Quickstart](https://zilliz.com/doc/quick_start)
 
@@ -967,4 +968,5 @@ documents = reader.load_data(
 - [Upstash](../../examples/vector_stores/UpstashVectorDemo.ipynb)
 - [Weaviate](../../examples/vector_stores/WeaviateIndexDemo.ipynb)
 - [Weaviate Hybrid Search](../../examples/vector_stores/WeaviateIndexDemo-Hybrid.ipynb)
+- [WordLift](../../examples/vector_stores/WordLiftDemo.ipynb)
 - [Zep](../../examples/vector_stores/ZepIndexDemo.ipynb)
diff --git a/docs/docs/examples/agent/nvidia_document_research_assistant_for_blog_creation.ipynb b/docs/docs/examples/agent/nvidia_document_research_assistant_for_blog_creation.ipynb
diff --git a/docs/docs/examples/cookbooks/GraphRAG_v1.ipynb b/docs/docs/examples/cookbooks/GraphRAG_v1.ipynb
@@ -996,7 +996,7 @@
     "- entity_name: Name of the entity, capitalized\n",
     "- entity_type: Type of the entity\n",
     "- entity_description: Comprehensive description of the entity's attributes and activities\n",
-    "Format each entity as (\"entity\"$$$$<entity_name>$$$$<entity_type>$$$$<entity_description>)\n",
+    "Format each entity as (\"entity\"$$$$\"<entity_name>\"$$$$\"<entity_type>\"$$$$\"<entity_description>\")\n",
     "\n",
     "2. From the entities identified in step 1, identify all pairs of (source_entity, target_entity) that are *clearly related* to each other.\n",
     "For each pair of related entities, extract the following information:\n",
@@ -1005,7 +1005,7 @@
     "- relation: relationship between source_entity and target_entity\n",
     "- relationship_description: explanation as to why you think the source entity and the target entity are related to each other\n",
     "\n",
-    "Format each relationship as (\"relationship\"$$$$<source_entity>$$$$<target_entity>$$$$<relation>$$$$<relationship_description>)\n",
+    "Format each relationship as (\"relationship\"$$$$\"<source_entity>\"$$$$\"<target_entity>\"$$$$\"<relation>\"$$$$\"<relationship_description>\")\n",
     "\n",
     "3. When finished, output.\n",
     "\n",

diff --git a/docs/docs/examples/cookbooks/GraphRAG_v2.ipynb b/docs/docs/examples/cookbooks/GraphRAG_v2.ipynb
@@ -778,7 +778,7 @@
     "- entity_name: Name of the entity, capitalized\n",
     "- entity_type: Type of the entity\n",
     "- entity_description: Comprehensive description of the entity's attributes and activities\n",
-    "Format each entity as (\"entity\"$$$$<entity_name>$$$$<entity_type>$$$$<entity_description>)\n",
+    "Format each entity as (\"entity\"$$$$\"<entity_name>\"$$$$\"<entity_type>\"$$$$\"<entity_description>\")\n",
     "\n",
     "2. From the entities identified in step 1, identify all pairs of (source_entity, target_entity) that are *clearly related* to each other.\n",
     "For each pair of related entities, extract the following information:\n",
@@ -787,7 +787,7 @@
     "- relation: relationship between source_entity and target_entity\n",
     "- relationship_description: explanation as to why you think the source entity and the target entity are related to each other\n",
     "\n",
-    "Format each relationship as (\"relationship\"$$$$<source_entity>$$$$<target_entity>$$$$<relation>$$$$<relationship_description>)\n",
+    "Format each relationship as (\"relationship\"$$$$\"<source_entity>\"$$$$\"<target_entity>\"$$$$\"<relation>\"$$$$\"<relationship_description>\")\n",
     "\n",
     "3. When finished, output.\n",
     "\n",

diff --git a/docs/docs/examples/embeddings/upstage.ipynb b/docs/docs/examples/embeddings/upstage.ipynb
@@ -68,7 +68,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Using Upstage `solar-1-mini-embedding`\n",
+    "## Using Upstage Embeddings\n",
     "\n",
     "Note, you may have to update your openai client: `pip install -U openai`"
    ]

diff --git a/docs/docs/examples/llm/upstage.ipynb b/docs/docs/examples/llm/upstage.ipynb
@@ -72,7 +72,7 @@
     "from llama_index.llms.upstage import Upstage\n",
     "\n",
     "llm = Upstage(\n",
-    "    model=\"solar-1-mini-chat\",\n",
+    "    model=\"solar-mini\",\n",
     "    # api_key=\"YOUR_API_KEY\"  # uses UPSTAGE_API_KEY env var by default\n",
     ")\n",
     "\n",

diff --git a/docs/docs/module_guides/indexing/lpg_index_guide.md b/docs/docs/module_guides/indexing/lpg_index_guide.md
@@ -446,7 +446,7 @@ index = PropertyGraphIndex.from_existing(
 
 ### Using the Property Graph Store Directly
 
-The base storage class for property graphs is the `PropertyGraphStore`. These property graph stores are constructured using different types of `LabeledNode` objects, and connected using `Relation` objects.
+The base storage class for property graphs is the `PropertyGraphStore`. These property graph stores are constructed using different types of `LabeledNode` objects, and connected using `Relation` objects.
 
 We can create these ourselves, and also insert ourselves!
 

diff --git a/docs/docs/module_guides/storing/vector_stores.md b/docs/docs/module_guides/storing/vector_stores.md
@@ -14,9 +14,9 @@ LlamaIndex supports over 20 different vector store options.
 We are actively adding more integrations and improving feature coverage for each.
 
 | Vector Store             | Type                    | Metadata Filtering | Hybrid Search | Delete | Store Documents | Async |
-| ------------------------ | ----------------------- | ------------------ | ------------- | ------ | --------------- | ----- |
+|--------------------------|-------------------------| ------------------ | ------------- | ------ | --------------- | ----- |
 | Alibaba Cloud OpenSearch | cloud                   | ✓                  |               | ✓      | ✓               | ✓     |
-| Apache Cassandra®       | self-hosted / cloud     | ✓                  |               | ✓      | ✓               |       |
+| Apache Cassandra®        | self-hosted / cloud     | ✓                  |               | ✓      | ✓               |       |
 | Astra DB                 | cloud                   | ✓                  |               | ✓      | ✓               |       |
 | Azure AI Search          | cloud                   | ✓                  | ✓             | ✓      | ✓               |       |
 | Azure CosmosDB MongoDB   | cloud                   |                    |               | ✓      | ✓               |       |
@@ -62,6 +62,7 @@ We are actively adding more integrations and improving feature coverage for each
 | Vespa                    | self-hosted / cloud     | ✓                  | ✓             | ✓      | ✓               |       |
 | Vertex AI Vector Search  | cloud                   | ✓                  |               | ✓      | ✓               |       |
 | Weaviate                 | self-hosted / cloud     | ✓                  | ✓             | ✓      | ✓               |       |
+| WordLift                 | cloud                   | ✓                  | ✓             | ✓      | ✓               | ✓     |
 
 For more details, see [Vector Store Integrations](../../community/integrations/vector_stores.md).
 

diff --git a/docs/mkdocs.yml b/docs/mkdocs.yml
@@ -1492,6 +1492,7 @@ nav:
               - ./api_reference/storage/chat_store/upstash.md
           - Docstore:
               - ./api_reference/storage/docstore/azure.md
+              - ./api_reference/storage/docstore/azurecosmosnosql.md
               - ./api_reference/storage/docstore/couchbase.md
               - ./api_reference/storage/docstore/dynamodb.md
               - ./api_reference/storage/docstore/elasticsearch.md

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__ = "0.12.8"
+__version__ = "0.12.10"
 
 import logging
 from logging import NullHandler