v0.10.35 (#13345)

CHANGELOG.md

@@ -1,5 +1,58 @@
 # ChangeLog
 
+## [2024-05-07]
+
+### `llama-index-agent-introspective` [0.1.0]
+
+- Add CRITIC and reflection agent integrations (#13108)
+
+### `llama-index-core` [0.10.35]
+
+- fix `from_defaults()` erasing summary memory buffer history (#13325)
+- use existing async event loop instead of `asyncio.run()` in core (#13309)
+- fix async streaming from query engine in condense question chat engine (#13306)
+- Handle ValueError in extract_table_summaries in element node parsers (#13318)
+- Handle llm properly for QASummaryQueryEngineBuilder and RouterQueryEngine (#13281)
+- expand instrumentation payloads (#13302)
+- Fix Bug in sql join statement missing schema (#13277)
+
+### `llama-index-embeddings-jinaai` [0.1.5]
+
+- add encoding_type parameters in JinaEmbedding class (#13172)
+- fix encoding type access in JinaEmbeddings (#13315)
+
+### `llama-index-embeddings-nvidia` [0.1.0]
+
+- add nvidia nim embeddings support (#13177)
+
+### `llama-index-llms-mistralai` [0.1.12]
+
+- Fix async issue when streaming with Mistral AI (#13292)
+
+### `llama-index-llms-nvidia` [0.1.0]
+
+- add nvidia nim llm support (#13176)
+
+### `llama-index-postprocessor-nvidia-rerank` [0.1.0]
+
+- add nvidia nim rerank support (#13178)
+
+### `llama-index-readers-file` [0.1.21]
+
+- Update MarkdownReader to parse text before first header (#13327)
+
+### `llama-index-readers-web` [0.1.13]
+
+- feat: Spider Web Loader (#13200)
+
+### `llama-index-vector-stores-vespa` [0.1.0]
+
+- Add VectorStore integration for Vespa (#13213)
+
+### `llama-index-vector-stores-vertexaivectorsearch` [0.1.0]
+
+- Add support for Vertex AI Vector Search as Vector Store (#13186)
+
 ## [2024-05-02]
 
 ### `llama-index-core` [0.10.34]

docs/docs/CHANGELOG.md

@@ -1,5 +1,58 @@
 # ChangeLog
 
+## [2024-05-07]
+
+### `llama-index-agent-introspective` [0.1.0]
+
+- Add CRITIC and reflection agent integrations (#13108)
+
+### `llama-index-core` [0.10.35]
+
+- fix `from_defaults()` erasing summary memory buffer history (#13325)
+- use existing async event loop instead of `asyncio.run()` in core (#13309)
+- fix async streaming from query engine in condense question chat engine (#13306)
+- Handle ValueError in extract_table_summaries in element node parsers (#13318)
+- Handle llm properly for QASummaryQueryEngineBuilder and RouterQueryEngine (#13281)
+- expand instrumentation payloads (#13302)
+- Fix Bug in sql join statement missing schema (#13277)
+
+### `llama-index-embeddings-jinaai` [0.1.5]
+
+- add encoding_type parameters in JinaEmbedding class (#13172)
+- fix encoding type access in JinaEmbeddings (#13315)
+
+### `llama-index-embeddings-nvidia` [0.1.0]
+
+- add nvidia nim embeddings support (#13177)
+
+### `llama-index-llms-mistralai` [0.1.12]
+
+- Fix async issue when streaming with Mistral AI (#13292)
+
+### `llama-index-llms-nvidia` [0.1.0]
+
+- add nvidia nim llm support (#13176)
+
+### `llama-index-postprocessor-nvidia-rerank` [0.1.0]
+
+- add nvidia nim rerank support (#13178)
+
+### `llama-index-readers-file` [0.1.21]
+
+- Update MarkdownReader to parse text before first header (#13327)
+
+### `llama-index-readers-web` [0.1.13]
+
+- feat: Spider Web Loader (#13200)
+
+### `llama-index-vector-stores-vespa` [0.1.0]
+
+- Add VectorStore integration for Vespa (#13213)
+
+### `llama-index-vector-stores-vertexaivectorsearch` [0.1.0]
+
+- Add support for Vertex AI Vector Search as Vector Store (#13186)
+
 ## [2024-05-02]
 
 ### `llama-index-core` [0.10.34]

docs/docs/api_reference/embeddings/nvidia.md

@@ -0,0 +1,4 @@
+::: llama_index.embeddings.nvidia
+    options:
+      members:
+        - NVIDIA

docs/docs/api_reference/llms/nvidia.md

@@ -0,0 +1,4 @@
+::: llama_index.llms.nvidia
+    options:
+      members:
+        - NVIDIA

docs/docs/api_reference/postprocessor/nvidia_rerank.md

@@ -0,0 +1,4 @@
+::: llama_index.postprocessor.nvidia_rerank
+    options:
+      members:
+        - NVIDIA

docs/docs/api_reference/readers/web.md

@@ -11,6 +11,7 @@
         - RssReader
         - SimpleWebPageReader
         - SitemapReader
+        - SpiderReader
         - TrafilaturaWebReader
         - UnstructuredURLLoader
         - WholeSiteReader

docs/docs/api_reference/storage/vector_store/vertexaivectorsearch.md

@@ -0,0 +1,4 @@
+::: llama_index.vector_stores.vertexaivectorsearch
+    options:
+      members:
+        - VertexAIVectorStore

docs/docs/api_reference/storage/vector_store/vespa.md

@@ -0,0 +1,4 @@
+::: llama_index.vector_stores.vespa
+    options:
+      members:
+        - VespaVectorStore

docs/mkdocs.yml

@@ -197,6 +197,7 @@ nav:
           - ./examples/embeddings/ipex_llm.ipynb
           - ./examples/embeddings/octoai.ipynb
           - ./examples/embeddings/ipex_llm_gpu.ipynb
+          - ./examples/embeddings/nvidia.ipynb
       - Evaluation:
           - ./examples/evaluation/TonicValidateEvaluators.ipynb
           - ./examples/evaluation/semantic_similarity_eval.ipynb
@@ -311,6 +312,7 @@ nav:
           - ./examples/llm/openvino.ipynb
           - ./examples/llm/octoai.ipynb
           - ./examples/llm/mistral_rs.ipynb
+          - ./examples/llm/nvidia.ipynb
       - Low Level:
           - ./examples/low_level/oss_ingestion_retrieval.ipynb
           - ./examples/low_level/fusion_retriever.ipynb
@@ -373,6 +375,7 @@ nav:
           - ./examples/node_postprocessor/JinaRerank.ipynb
           - ./examples/node_postprocessor/rankLLM.ipynb
           - ./examples/node_postprocessor/openvino_rerank.ipynb
+          - ./examples/node_postprocessor/NVIDIARerank.ipynb
       - Object Stores:
           - ./examples/objects/object_index.ipynb
       - Output Parsers:
@@ -461,6 +464,7 @@ nav:
       - Tools:
           - ./examples/tools/OnDemandLoaderTool.ipynb
           - ./examples/tools/eval_query_engine_tool.ipynb
+          - ./examples/tools/azure_dynamic_sessions.ipynb
       - Transforms:
           - ./examples/transforms/TransformsEval.ipynb
       - Use Cases:
@@ -547,6 +551,8 @@ nav:
           - ./examples/vector_stores/AWSDocDBDemo.ipynb
           - ./examples/vector_stores/MilvusHybridIndexDemo.ipynb
           - ./examples/vector_stores/FirestoreVectorStore.ipynb
+          - ./examples/vector_stores/VespaIndexDemo.ipynb
+          - ./examples/vector_stores/VertexAIVectorSearchDemo.ipynb
   - Component Guides:
       - ./module_guides/index.md
       - Models:
@@ -722,6 +728,7 @@ nav:
           - ./api_reference/embeddings/llm_rails.md
           - ./api_reference/embeddings/mistralai.md
           - ./api_reference/embeddings/nomic.md
+          - ./api_reference/embeddings/nvidia.md
           - ./api_reference/embeddings/octoai.md
           - ./api_reference/embeddings/ollama.md
           - ./api_reference/embeddings/openai.md
@@ -804,6 +811,7 @@ nav:
           - ./api_reference/llms/monsterapi.md
           - ./api_reference/llms/mymagic.md
           - ./api_reference/llms/neutrino.md
+          - ./api_reference/llms/nvidia.md
           - ./api_reference/llms/nvidia_tensorrt.md
           - ./api_reference/llms/nvidia_triton.md
           - ./api_reference/llms/octoai.md
@@ -946,6 +954,7 @@ nav:
           - ./api_reference/postprocessor/long_context_reorder.md
           - ./api_reference/postprocessor/longllmlingua.md
           - ./api_reference/postprocessor/metadata_replacement.md
+          - ./api_reference/postprocessor/nvidia_rerank.md
           - ./api_reference/postprocessor/openvino_rerank.md
           - ./api_reference/postprocessor/presidio.md
           - ./api_reference/postprocessor/prev_next.md
@@ -1289,6 +1298,8 @@ nav:
               - ./api_reference/storage/vector_store/typesense.md
               - ./api_reference/storage/vector_store/upstash.md
               - ./api_reference/storage/vector_store/vearch.md
+              - ./api_reference/storage/vector_store/vertexaivectorsearch.md
+              - ./api_reference/storage/vector_store/vespa.md
               - ./api_reference/storage/vector_store/weaviate.md
               - ./api_reference/storage/vector_store/zep.md
       - Tools:
@@ -1850,6 +1861,11 @@ plugins:
             - ../llama-index-integrations/readers/llama-index-readers-youtube-metadata
             - ../llama-index-integrations/llms/llama-index-llms-mistral-rs
             - ../llama-index-integrations/agent/llama-index-agent-introspective
+            - ../llama-index-integrations/vector_stores/llama-index-vector-stores-vertexaivectorsearch
+            - ../llama-index-integrations/vector_stores/llama-index-vector-stores-vespa
+            - ../llama-index-integrations/embeddings/llama-index-embeddings-nvidia
+            - ../llama-index-integrations/postprocessor/llama-index-postprocessor-nvidia-rerank
+            - ../llama-index-integrations/llms/llama-index-llms-nvidia
   - 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__ = "0.10.34"
+__version__ = "0.10.35"
 
 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 = "0.10.34"
+version = "0.10.35"
 
 [tool.poetry.dependencies]
 SQLAlchemy = {extras = ["asyncio"], version = ">=1.4.49"}

llama-index-integrations/agent/llama-index-agent-openai-legacy/llama_index/agent/openai_legacy/openai_agent.py

@@ -228,9 +228,9 @@ def _get_stream_ai_response(
         )
         thread.start()
         # Wait for the event to be set
-        chat_stream_response._is_function_not_none_thread_event.wait()
+        chat_stream_response.is_function_not_none_thread_event.wait()
         # If it is executing an openAI function, wait for the thread to finish
-        if chat_stream_response._is_function:
+        if chat_stream_response.is_function:
             thread.join()
 
         # if it's false, return the answer (to stream)
@@ -249,7 +249,7 @@ async def _get_async_stream_ai_response(
         )
         # wait until openAI functions stop executing
         chat_stream_response._ensure_async_setup()
-        await chat_stream_response._is_function_false_event.wait()
+        await chat_stream_response.is_function_false_event.wait()
 
         # return response stream
         return chat_stream_response

llama-index-integrations/agent/llama-index-agent-openai-legacy/pyproject.toml

@@ -28,11 +28,11 @@ exclude = ["**/BUILD"]
 license = "MIT"
 name = "llama-index-agent-openai-legacy"
 readme = "README.md"
-version = "0.1.3"
+version = "0.1.4"
 
 [tool.poetry.dependencies]
 python = ">=3.8.1,<4.0"
-llama-index-core = "^0.10.1"
+llama-index-core = "^0.10.35"
 llama-index-llms-openai = "^0.1.1"
 
 [tool.poetry.group.dev.dependencies]

llama-index-integrations/agent/llama-index-agent-openai/llama_index/agent/openai/step.py

@@ -389,9 +389,9 @@ def _get_stream_ai_response(
         )
         thread.start()
         # Wait for the event to be set
-        chat_stream_response._is_function_not_none_thread_event.wait()
+        chat_stream_response.is_function_not_none_thread_event.wait()
         # If it is executing an openAI function, wait for the thread to finish
-        if chat_stream_response._is_function:
+        if chat_stream_response.is_function:
             thread.join()
 
         # if it's false, return the answer (to stream)
@@ -414,7 +414,7 @@ async def _get_async_stream_ai_response(
         chat_stream_response._ensure_async_setup()
 
         # wait until openAI functions stop executing
-        await chat_stream_response._is_function_false_event.wait()
+        await chat_stream_response.is_function_false_event.wait()
 
         # return response stream
         return chat_stream_response

llama-index-integrations/agent/llama-index-agent-openai/pyproject.toml

@@ -28,11 +28,11 @@ exclude = ["**/BUILD"]
 license = "MIT"
 name = "llama-index-agent-openai"
 readme = "README.md"
-version = "0.2.3"
+version = "0.2.4"
 
 [tool.poetry.dependencies]
 python = ">=3.8.1,<4.0"
-llama-index-core = "^0.10.30"
+llama-index-core = "^0.10.35"
 llama-index-llms-openai = "^0.1.5"
 openai = ">=1.14.0"
 

llama-index-packs/llama-index-packs-cohere-citation-chat/llama_index/packs/cohere_citation_chat/citations_context_chat_engine.py

@@ -72,7 +72,7 @@ def write_response_to_history(
             final_text = ""
             for chat in self.chat_stream:
                 # LLM response queue
-                self._is_function = is_function(chat.message)
+                self.is_function = is_function(chat.message)
                 self.put_in_queue(chat.delta)
                 final_text += chat.delta or ""
                 if chat.raw is not None:
@@ -92,7 +92,7 @@ def write_response_to_history(
                         self.documents += convert_chat_response_to_documents(
                             chat, self.citations_settings
                         )
-            if self._is_function is not None:  # if loop has gone through iteration
+            if self.is_function is not None:  # if loop has gone through iteration
                 # NOTE: this is to handle the special case where we consume some of the
                 # chat stream, but not all of it (e.g. in react agent)
                 chat.message.content = final_text.strip()  # final message
@@ -105,10 +105,10 @@ def write_response_to_history(
             else:
                 raise
 
-        self._is_done = True
+        self.is_done = True
 
         # This act as is_done events for any consumers waiting
-        self._is_function_not_none_thread_event.set()
+        self.is_function_not_none_thread_event.set()
 
     async def awrite_response_to_history(
         self,
@@ -124,11 +124,11 @@ async def awrite_response_to_history(
             final_text = ""
             async for chat in self.achat_stream:
                 # Chat response queue
-                self._is_function = is_function(chat.message)
+                self.is_function = is_function(chat.message)
                 self.aput_in_queue(chat.delta)
                 final_text += chat.delta or ""
-                if self._is_function is False:
-                    self._is_function_false_event.set()
+                if self.is_function is False:
+                    self.is_function_false_event.set()
                 if chat.raw is not None:
                     # Citations stream event
                     if (
@@ -146,15 +146,15 @@ async def awrite_response_to_history(
                         self.documents += convert_chat_response_to_documents(
                             chat, self.citations_settings
                         )
-                self._new_item_event.set()
-            if self._is_function is not None:  # if loop has gone through iteration
+                self.new_item_event.set()
+            if self.is_function is not None:  # if loop has gone through iteration
                 # NOTE: this is to handle the special case where we consume some of the
                 # chat stream, but not all of it (e.g. in react agent)
                 chat.message.content = final_text.strip()  # final message
                 memory.put(chat.message)
         except Exception as e:
             logger.warning(f"Encountered exception writing response to history: {e}")
-        self._is_done = True
+        self.is_done = True
 
 
 class ChatModeCitations(str, Enum):