1 Release published by 1 person

• v0.12.29

  published Apr 9, 2025

30 Pull requests merged by 14 people

• fix nebula properties get

  #18423 merged Apr 11, 2025

• Connect new phoenix tracing option

  #18415 merged Apr 11, 2025

• use to_thread for async reader methods by default

  #18418 merged Apr 10, 2025

• Actually fix pass-by-reference errors in openai responses

  #18420 merged Apr 10, 2025

• Fix multi-agent state formatting

  #18417 merged Apr 9, 2025

• Smabbler doc update

  #18410 merged Apr 9, 2025

• v0.12.29

  #18408 merged Apr 9, 2025

• fix pass by reference errors with tools in OpenAIResponses

  #18407 merged Apr 9, 2025

• better enforce agent handoffs

  #18399 merged Apr 8, 2025

• fix overwrite vs append logic in LanceDB

  #18405 merged Apr 8, 2025

• add option to toggle progress bars in HuggingFaceEmbedding

  #18404 merged Apr 8, 2025

• fix: isolate event buffers to avoid interferences between steps

  #18351 merged Apr 8, 2025

• WatsonxLLM/WatsonxEmbeddings: persistent_connection configurable

  #18401 merged Apr 8, 2025

• fix: cleanup pyproject.toml

  #18395 merged Apr 8, 2025

• enable openai responses override

  #18402 merged Apr 8, 2025

• Fix/milvus filters

  #18393 merged Apr 8, 2025

• Remove Managed Index ZillizCloudPipelineIndex

  #18391 merged Apr 8, 2025

• update huggingface deps

  #18398 merged Apr 8, 2025

• waiting for events refactor

  #18226 merged Apr 7, 2025

• fix: 🐛 Replace broken and discontinued tree_sitter_languages with tree_sitter_language_pack

  #18387 merged Apr 7, 2025

• Fix docs build for Milvus Async API notebook

  #18389 merged Apr 7, 2025

• Bug Fix: Fixed the broken guide link in OpenLLMetry section of module…

  #18377 merged Apr 7, 2025

• Update to Kuzu 0.9.0

  #18382 merged Apr 7, 2025

• Update rag_cli.md

  #18374 merged Apr 4, 2025

• Add uniprot reader

  #18356 merged Apr 4, 2025

• feature: add multi-modal support for bedrock converse

  #18373 merged Apr 4, 2025

• Fix asyncio dep in tests

  #18367 merged Apr 4, 2025

• Smabbler integration

  #18317 merged Apr 4, 2025

• fill in index pages

  #18365 merged Apr 4, 2025

• Feat/bedrock converse deepseek r1

  #18371 merged Apr 4, 2025

4 Pull requests opened by 4 people

• Build perplexity integration

  #18378 opened Apr 6, 2025

• Fix BedrockConverse token count in usage to match OpenAI's format

  #18383 opened Apr 6, 2025

• Add ApertureDB vector store.

  #18428 opened Apr 10, 2025

• v0.12.30

  #18430 opened Apr 11, 2025

151 Issues closed by 11 people

• [Bug]: ValueError: size must contain 'shortest_edge' and 'longest_edge' keys

  #18268 closed Apr 10, 2025

• [Bug]: Compatibility Error

  #16670 closed Apr 10, 2025

• [Feature Request]: Integrating MatrixOne as a vector store method

  #16594 closed Apr 10, 2025

• [Bug]: NLSQLTableQueryEngine is not working with MS SQL table where there is hyphen in table name

  #16599 closed Apr 10, 2025

• [Feature Request]: Support for BigQuery Vector Store

  #16635 closed Apr 10, 2025

• [Feature Request]: How does milvus_index implement an ”or“ search?

  #16497 closed Apr 10, 2025

• [Question]: About realtime translation and presentation

  #16079 closed Apr 10, 2025

• [Question]: How to Enable simultaneous Handoff to Multiple Agents in AgentWorkflow

  #18426 closed Apr 10, 2025

• [Bug]: Nested lists are not supported.

  #18119 closed Apr 10, 2025

• [Bug]: llama-index-llms-huggingface 0.5.0 does not contain related changes

  #18419 closed Apr 9, 2025

• [Question]: I am getting this error when I am using it

  #18324 closed Apr 9, 2025

• [Question]: Is State Duplication in Chat History Across Workflow Iterations Intended?

  #18416 closed Apr 9, 2025

• [Bug]: Tool calling broken when LLM responds with both text and tool calls

  #15083 closed Apr 9, 2025

• [Question]: How does WriteAgent access research notes in Multi Agent Workflow example

  #18396 closed Apr 9, 2025

• [Question]: How to get all the nodes from the local Neo4jPropertyGraphStore？

  #16029 closed Apr 9, 2025

• [Bug]: LanceDB get_nodes() method always only returns 10 nodes

  #16016 closed Apr 9, 2025

• [Question]: How to use open source model served with vLLM with Query Pipeline in llama index?

  #15972 closed Apr 9, 2025

• [Bug]: showing errro during import of torch package in python jupyter notebook: verison of torch installed is 2.4.0..and i had also tried for the command "!pip install --upgrade torch", bt still showing the error

  #15799 closed Apr 9, 2025

• [Feature Request]: Qdrant Add batch API support

  #15756 closed Apr 9, 2025

• [Question]: MultiModal (Image support) for AgentWorkflows

  #18284 closed Apr 9, 2025

• [Question]: Is it possible to only update specified node's content and rerun pipeline?

  #18409 closed Apr 9, 2025

• [Question]: How do I get the similarity of the question to the context?

  #15754 closed Apr 9, 2025

• [Question]: [BedrockConverse] astream_chat is not returning token.

  #15875 closed Apr 9, 2025

• [Question]: How to do Sql Filtering in Myscale db , will metadata filtering function different from pure vector db.

  #15741 closed Apr 9, 2025

• [Bug]: Opensearch does not work with TextNode class

  #15736 closed Apr 9, 2025

• [Bug]: llama-index-core 0.11.2 has incorrent dependency set on pydantic version

  #15708 closed Apr 9, 2025

• [Question]: "FaissVectorStore" build to get "vector_store", then use vector_store.add([new_node]), finally query the new added knowledge,but cannot find

  #15707 closed Apr 9, 2025

• [Question]: [BedrockConverse] astream handler for non async iterable

  #15704 closed Apr 9, 2025

• [Bug]: Error using pydantic response with chat engine

  #15694 closed Apr 9, 2025

• [BUG]: the KG BUG, why kg_schema, not the kg_rel_texts?

  #15686 closed Apr 9, 2025

• [Question]: How to Choose Between ReAct Agent and FunctionCallingAgent in LlamaIndex for Building Agentic Workflows?

  #15685 closed Apr 9, 2025

• [Question]: llamaindex bedrock, event_type=<CBEventType.LLM: 'llm'> payload={'exception': NotImplementedError('Use async-for instead')}

  #15666 closed Apr 9, 2025

• [Bug]: BedrockConverse doesn't work with streaming and tool use combined

  #15664 closed Apr 9, 2025

• [Question]: [Workflow]How to use multithreading in send_event function

  #15663 closed Apr 9, 2025

• [Question]: How to deal with images in doc or pdf? Is there a way to ignore these images?

  #15656 closed Apr 9, 2025

• [Question]: How can a VectorStoreIndex be generated via parallel processing?

  #15655 closed Apr 9, 2025

• [Question]: How to Modify Agent Prompt and Query Engine defaults Prompts

  #15646 closed Apr 9, 2025

• [Question]: Is there a workaround to the fixed num_chilidren param in TreeIndex?

  #15611 closed Apr 9, 2025

• [Bug]: error Async Search client not initialized when running azureaisearch with use_async = True

  #15594 closed Apr 9, 2025

• [Question]: Orchestrate multiple workflows.

  #15590 closed Apr 9, 2025

• [Bug]: Docs crashing chrome tabs

  #15536 closed Apr 9, 2025

• [Bug]: HuggingFaceEmbedding with CLIP and other image embeddings

  #15519 closed Apr 9, 2025

• [Bug]: OpenAIAgent as Top Agent with Tool Retriever doesn't work - Multi-Document Agent

  #15515 closed Apr 9, 2025

• [Feature Request]: bedrock converse LLM

  #15510 closed Apr 9, 2025

• [Bug]: TextToCypher Retriever does not work if you pass in a `cypher_validator` without also passing in `allowed_output_fields`

  #15504 closed Apr 9, 2025

• [Question]: Issue with Retrieving Top K Base Nodes Using RecursiveRetriever

  #15487 closed Apr 9, 2025

• Issue found in the Raptor retrieval process in tree_traversal mode.

  #15482 closed Apr 9, 2025

• [Question]: multimodal workflows

  #15469 closed Apr 9, 2025

• [Question]: 'HuggingFaceLLM' object has no attribute 'model'. Did you mean: '_model' while passing it to FunctionCallingAgentWorker

  #15468 closed Apr 9, 2025

• [Question]: How to run HuggingFaceEmbedding on multiple available GPUs?

  #15407 closed Apr 9, 2025

• [Feature Request]: Create a stream agent + workflows example

  #15393 closed Apr 9, 2025

• [Question]: Not able to get the content on metadata

  #15362 closed Apr 9, 2025

• [Question]: ValueError: The `model_name` argument must be provided

  #15353 closed Apr 9, 2025

• [Question]: What is the use of page_nodes

  #15326 closed Apr 9, 2025

• [Question]: How to generate `source_nodes` from the response of `astream_chat` engine

  #15323 closed Apr 9, 2025

• [Question]: How can i return page number as source in Rag.

  #15321 closed Apr 9, 2025

• [Question]: Want to reduce the context memory token size

  #15320 closed Apr 9, 2025

• [Bug]: Unintended Modification of built_in_tools in OpenAIResponses

  #18406 closed Apr 9, 2025

• [Question]: 使用·PropertyGraphIndex.from_documents()方法报错

  #15053 closed Apr 9, 2025

• [Bug]: Stop at "Generating embeddings: 0it [00:00, ?it/s]" when use SchemaLLMPathExtractor

  #15065 closed Apr 8, 2025

• [Question]: Need help: Retrieval and generation not working well

  #15075 closed Apr 8, 2025

• [Bug]: FunctionCallingAgentWorker does not support streaming

  #15653 closed Apr 8, 2025

• [Question]: Tools with streaming

  #15079 closed Apr 8, 2025

• [Bug]: Facing error with SubQuestionQueryEngine using microsoft/Phi-3-mini-4k-instruct

  #15080 closed Apr 8, 2025

• [Bug]: Hybrid search for Milvus vector store fails

  #15081 closed Apr 8, 2025

• [Question]: Index created from a LanceDBVectorStore is not returning all nodes?

  #14435 closed Apr 8, 2025

• How to add new document embeddings to existing embeddings in chromadb

  #15082 closed Apr 8, 2025

• [Question]: Complex PDF Parsing

  #15113 closed Apr 8, 2025

• [Question]: SQLTableRetrieverQueryEngine does not support streaming in async mode

  #15114 closed Apr 8, 2025

• [Question]: ImportError: cannot import name 'Trainer' from partially initialized module 'span_marker.trainer'

  #15155 closed Apr 8, 2025

• [Feature Request]: Add Support for Llama 3.1 in Bedrock

  #15162 closed Apr 8, 2025

• [Question]: nlsql table query engine keep the conversation going ( chat history)

  #15174 closed Apr 8, 2025

• [Question]: How to use Azure Table Storage for indexing large files

  #15258 closed Apr 8, 2025

• [Question]: How do I update my Postgres Vector database with the updated documents

  #15283 closed Apr 8, 2025

• [Question]: Why is PropertyGraphIndex with and use_async=True with OllamaEmbedding errorring out?

  #15292 closed Apr 8, 2025

• [Question]: OpenAILike chat have a problem.

  #15298 closed Apr 8, 2025

• [Question]: Is there any way to support the deployment of a local embedding API and a reranker API?

  #15303 closed Apr 8, 2025

• How can we pass hybrid_top_k as a parameter to VectorIndexRetriever

  #15304 closed Apr 8, 2025

• [Bug]: Conflicting versions

  #15317 closed Apr 8, 2025

• [Question]: There is issue regarding the get_content() from rag.

  #15318 closed Apr 8, 2025

• [Question]: NebulaGraphStore

  #15043 closed Apr 8, 2025

• @logan-markewich Mixture of agents issue

  #15038 closed Apr 8, 2025

• [Question]: Session Manangement using Redis Chat Store with ChatMemoryBuffer guide

  #15035 closed Apr 8, 2025

• [OOM]: Runs out of memory when creating index for large documents

  #15013 closed Apr 8, 2025

• [Question]: Router Query Engine Examples

  #14994 closed Apr 8, 2025

• [Question]: How does `RagDatasetGenerator` work?

  #14974 closed Apr 8, 2025

• not able use colbert embeddings with llamaindex

  #14953 closed Apr 8, 2025

• `response.message` in `query_pipeline_memory` example

  #14952 closed Apr 8, 2025

• [Question]: Can I create the RAG for Urdu dataset using the same pattern as for English dateset. And I am using Openai latest multilanguage model for embeddings

  #14927 closed Apr 8, 2025

• [Bug]: Smart PDF Loader - Failed to establish a new connection

  #14902 closed Apr 8, 2025

• [Question]: Are there anyway to have Node Postprocessor into Function Calling Agent

  #14891 closed Apr 8, 2025

• [Feature Request]: Update DSPy integration

  #14890 closed Apr 8, 2025

• [Bug]: RAGAS integration with llamindex issue

  #14873 closed Apr 8, 2025

• [Question]: Chat engine goes to internet to provide answer. How to restrict it strictly to the vector space?

  #14870 closed Apr 8, 2025

• [Question]: Getting error "KeyError: 'multi_tool_use.parallel'" while using StructuredPlannerAgent with FunctionCallingAgentWorker

  #14846 closed Apr 8, 2025

• [Bug]: KeyError: 'context_str' in query_engine.image_query(image_path, query_str)

  #14730 closed Apr 8, 2025

• [Question]: Connecting llamaindex to aoss opensearch on aws

  #14133 closed Apr 8, 2025

• [Bug]: Qdrant Vector Store - Collection Name not found while trying to generate answer

  #13642 closed Apr 8, 2025

• [Bug]: When using llamaIndex to access a Ollama local LLM service in windows, there will be error .

  #13526 closed Apr 8, 2025

• [Bug]: "POST /generate HTTP/1.1" 404 Not Found

  #13041 closed Apr 8, 2025

• llamaindex vllm error

  #12955 closed Apr 8, 2025

• [Feature Request]: Remove progress bar in HuggingFaceEmbedding

  #18388 closed Apr 8, 2025

• [Bug]: Naming of `@step`s in a `Workflow` affect whether the execution will halt

  #18337 closed Apr 8, 2025

• [Feature Request]: IBM WatsonxLLM doesn't support `persistent_connection` configurable

  #18400 closed Apr 8, 2025

• [Feature Request]: Security concern CVE-2024-3924 - To update llama-index-llms-huggingface dependencies text-generation to >= v2.0.0

  #18384 closed Apr 8, 2025

• [Question]: Cannot update Document attributes data

  #18397 closed Apr 8, 2025

• [Question]: Add tool function in VectorStoreIndex

  #18394 closed Apr 8, 2025

• [Question]: How to set system prompt words in BaseChatEngine?

  #18385 closed Apr 8, 2025

• [Question]: Parallel Human in Loop with Agent Workflow Issues

  #18220 closed Apr 7, 2025

• [Question]: Clarification on Context vs. ChatStore for Chat History Persistence

  #18386 closed Apr 7, 2025

• [Bug]: Unexpected keyword argument for run_transformations() method

  #14809 closed Apr 7, 2025

• [Question]: similarity_top_k not clear

  #14808 closed Apr 7, 2025

• After I retrieve the desired node using QueryFusionRetriever, how do I retrieve the previous and next nodes of the node?

  #14806 closed Apr 7, 2025

• [Question]: Pandas Query Engine does not give proper response( Especially when exposed via API, works well in local jupyter notebook)

  #14804 closed Apr 7, 2025

• [Question]: Query-time metadata filtering

  #14802 closed Apr 7, 2025

• [Bug]: ERROR: Failed building wheel for pystemmer

  #14782 closed Apr 7, 2025

• [Bug]: Error in initializing neo4j

  #14778 closed Apr 7, 2025

• [Question]: The created knowledge graph does not have edge relationships neo4j

  #14763 closed Apr 7, 2025

• [Bug]: Query Pipeline with Async/Parallel Execution Broken

  #14746 closed Apr 7, 2025

• [Question]: Why do some llama-index integrations not allow the 'api key' and the 'base url' to be passed in as an initialization parameter?

  #14739 closed Apr 7, 2025

• [Bug]: ReAct Agent ending prematurely and returning the Thoughts to the user as a response

  #14736 closed Apr 7, 2025

• [Question]: Custom callback handler

  #14717 closed Apr 7, 2025

• [Bug]: No available version integration of NvidiaTriton

  #14716 closed Apr 7, 2025

• [Bug]: OpenAIAgentWorkers `get_all_messages` Function may go outside of content window

  #14660 closed Apr 7, 2025

• [Question]: NebulaGraph RAG

  #14649 closed Apr 7, 2025

• [Bug]: KnowledgeGraphIndex._build_index_from_nodes() got an unexpected keyword argument 'space_name'

  #14629 closed Apr 7, 2025

• [Bug]: QueryFusionRetriever doesn't work asynchronously with custom http_client

  #14544 closed Apr 7, 2025

• [Question]: Can we use Langchain Tools with LlamaIndex agents? I know we can use it reverse way.

  #14476 closed Apr 7, 2025

• [Question]: How to use Bedrock Claude 3.5 Sonnet with LlamaIndex

  #14455 closed Apr 7, 2025

• [Bug]: Example for JSONalyze Query Engine fails with OperationalError: near "sql": syntax error

  #14416 closed Apr 7, 2025

• [Question]: Can ReAct Agent reasoning without tools

  #14343 closed Apr 7, 2025

• [Documentation]:

  #14276 closed Apr 7, 2025

• [Question]: Defining Prompt Template for OpenAIAgent

  #14273 closed Apr 7, 2025

• [Bug]: Getting deprecation message for Neo4jPropertyGraphStore

  #14093 closed Apr 7, 2025

• [Documentation]: Document the pipeline used by NLSQLTableQueryEngine (and potentially other query engines)

  #14050 closed Apr 7, 2025

• [Bug]: VectorIndexAutoRetriever run fail with gpt-4o

  #14047 closed Apr 7, 2025

• [Bug]: `QueryPipeline` only using the `query_str` of the query transform output `QueryBundle`

  #14044 closed Apr 7, 2025

• Enable Gpu when Generating Sparse vectors with Qdrant hybrid Mode.

  #14020 closed Apr 7, 2025

• [Bug]: Documentation for guidance_pydantic is out of date

  #13962 closed Apr 7, 2025

• [Question]: How to count token in Anthropic models?

  #13952 closed Apr 7, 2025

• [Question]: how to use the llamaindex+vllm correctly?

  #13925 closed Apr 7, 2025

• [Bug]: Pandas Output: There was an error running the output as Python code. Error message: name 'p' is not defined

  #13800 closed Apr 7, 2025

• EntityExtractor

  #13774 closed Apr 7, 2025

• [Bug]:<MilvusException:(code=1100,message=the length (79145) of dynamic field exceeds max length (65536): invalid parameter[expected=valid length dynamic field][actual=length exceeds max length

  #13752 closed Apr 7, 2025

• [Question]: Can we apply the Retry Agent for the Query Time Sample Row Retrieval with chunk based indexing of tables.

  #13722 closed Apr 7, 2025

• [Bug]: OpenSearch Vector Store have a lot of connection problem after #11513

  #13692 closed Apr 7, 2025

• [Documentation]: Broken link for `OpenLLMetry`

  #18332 closed Apr 7, 2025

• [Question]: OpenAI Agent Always Returns First Holiday Instead of Next Upcoming Holiday

  #18375 closed Apr 6, 2025

• [Question]: 'NoneType' object has no attribute 'generate' using vllm

  #18181 closed Apr 4, 2025

• [Bug]: FunctionAgent responce is a tool call and not the answer

  #18363 closed Apr 4, 2025

• [Question]: Why is handler.stream_events not working

  #18370 closed Apr 4, 2025

13 Issues opened by 12 people

• [Feature Request]: Add support for SQLite chat store?

  #18427 opened Apr 10, 2025

• [Documentation]: Bedrock reranking - empty page

  #18425 opened Apr 10, 2025

• [Feature Request]: Universal Tool Call Format Adapter for AgentWorkflow Multi-Provider Compatibility

  #18424 opened Apr 10, 2025

• [Bug]: Encoding error when local loading storage_context

  #18422 opened Apr 10, 2025

• [Bug]: `self.search_messages()` missing 1 required positional argument: 'query'

  #18414 opened Apr 9, 2025

• [Feature Request]: Structured Output for AgentWorkflow

  #18412 opened Apr 9, 2025

• [Feature Request]: Add structured output for Bedrcok Converse and Gemini

  #18392 opened Apr 8, 2025

• [Feature Request]: CodeHierarchyAgentPack support for `.scm`

  #18390 opened Apr 7, 2025

• [Feature Request]: VertexAI AChat_Complete to use with new ReActAgent Workflow

  #18381 opened Apr 6, 2025

• [Bug]: Recreate a vector store of milvus

  #18380 opened Apr 6, 2025

• [Bug]: Document Summary Index gives KeyError

  #18379 opened Apr 6, 2025

• [Question]: Trying to implement LlamaIndex Graphrag V2 with ollama model hugging face model

  #18376 opened Apr 5, 2025

• [Bug] NeptuneAnalyticsGraphStore' object has no attribute 'supports_vector_queries'

  #18372 opened Apr 4, 2025

83 Unresolved conversations

Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.

• [Bug]: FunctionAgent Incremental Response Handling in astream_chat Method

  #18361 commented on Apr 4, 2025 • 0 new comments

• [Bug]: MongoDB pymongo.errors.OperationFailure (Size larger than 16MB)

  #17768 commented on Apr 4, 2025 • 0 new comments

• [Bug]: GraphRAG implementation Cookbook V2 not working

  #16120 commented on Apr 4, 2025 • 0 new comments

• [Feature Request]: Support for OpenSearch as a chat store

  #15926 commented on Apr 4, 2025 • 0 new comments

• [Bug]: MultiModalLLMCompletionProgram (Ollama:Llava) raises AttributeError: 'GenerateResponse' object has no attribute 'items'

  #17105 commented on Apr 4, 2025 • 0 new comments

• [Bug]: VectorStoreIndex.insert method failed when working with lancedb

  #16180 commented on Apr 5, 2025 • 0 new comments

• [Bug]: 2024-09-23 00:06:33,027 - WARNING - Retrying llama_index.llms.openai.base.OpenAI._achat in 0.6544275664914755 seconds as it raised APIConnectionError: Connection error.. 2024-09-23 00:06:54,743 - WARNING - Retrying llama_index.llms.openai.base.OpenAI._achat in 0.10014551963451379 seconds as it raised APIConnectionError: Connection error.. Observation: Error: Connection error.

  #16155 commented on Apr 5, 2025 • 0 new comments

• [Question]:How to Implement Data Access Control in Text-to-SQL

  #16122 commented on Apr 5, 2025 • 0 new comments

• [Question]: access metadata like author in prompt

  #16132 commented on Apr 5, 2025 • 0 new comments

• [Question]: How to use guardrails with the query engine

  #16162 commented on Apr 5, 2025 • 0 new comments

• [Bug]: Incorrect Return Type in EarningsCallTranscript.load_data()

  #16121 commented on Apr 5, 2025 • 0 new comments

• [Feature Request]: Support for MultiModalLLM and MultiModalEmbedding with AzureAICompletionsModel

  #16716 commented on Apr 6, 2025 • 0 new comments

• [Feature Request]: llama-index-vector-stores-milvus Support for batch operations

  #16727 commented on Apr 6, 2025 • 0 new comments

• [Feature Request]: Expose Sparse Embeddings in Query/Node

  #16717 commented on Apr 6, 2025 • 0 new comments

• [Bug]: llama-index-llms-qianfan's chat method return value not contain the token usage

  #16181 commented on Apr 6, 2025 • 0 new comments

• [Feature Request]: CodeHierarchyNodeParser - add open source llm support

  #16205 commented on Apr 6, 2025 • 0 new comments

• [Question]: Response Synthesizer

  #16228 commented on Apr 6, 2025 • 0 new comments

• [Bug]: A `Workflow` runs properly when `.run()`, but not when `.run(stepwise=True)`

  #18334 commented on Apr 6, 2025 • 0 new comments

• [Bug]: model_name vs. model in BedrockEmbedding doesn't throw an error

  #14401 commented on Apr 7, 2025 • 0 new comments

• [Bug]: Duplicate Loop Over ref_doc_kv_pairs.items()

  #16280 commented on Apr 7, 2025 • 0 new comments

• [Bug]: `redirect_uri_mismatch` in GoogleDocsReader

  #16326 commented on Apr 7, 2025 • 0 new comments

• [Question]: How can I use SimpleDirectoryReader and StorageContext

  #16343 commented on Apr 7, 2025 • 0 new comments

• [Question]: How to specify chat template when using LlamaCPP

  #15862 commented on Apr 7, 2025 • 0 new comments

• [Question]: i follow the example of llamaindex Nebula, the error ocurr as this:

  #16274 commented on Apr 7, 2025 • 0 new comments

• [Bug]: SimpleDirectoryReader reads "once" and then says no files

  #15858 commented on Apr 7, 2025 • 0 new comments

• [Bug]: Neo4j Property Graph Index doesn't seem to be working?

  #16352 commented on Apr 7, 2025 • 0 new comments

• [Feature Request]: BM25 with OpenSearch

  #16748 commented on Apr 7, 2025 • 0 new comments

• [Question]: Am I able to add metadata to KnowledgeGraphIndex?

  #15762 commented on Apr 7, 2025 • 0 new comments

• [Question]: Response syntheszier

  #16257 commented on Apr 7, 2025 • 0 new comments

• [Feature Request]: Support ADC with VertexTextEmbedding

  #16846 commented on Apr 8, 2025 • 0 new comments

• [Question]: Indexing a nested dictionary dosu

  #15967 commented on Apr 8, 2025 • 0 new comments

• [Question]: How to add history and memory functionality to multi modal rag setup

  #16808 commented on Apr 8, 2025 • 0 new comments

• [Feature Request]: Better HTML Chunking

  #15974 commented on Apr 8, 2025 • 0 new comments

• [Question]: Custom Composable Graph Query Engine

  #15966 commented on Apr 8, 2025 • 0 new comments

• [Feature Request]: Support for Asynchronous Processing in llms.watsonx

  #16124 commented on Apr 8, 2025 • 0 new comments

• [Bug]: PineconeVectorStore Metadata always empty

  #15898 commented on Apr 8, 2025 • 0 new comments

• [Bug]: `llama_index` retries `openai.AuthenticationError`

  #11989 commented on Apr 8, 2025 • 0 new comments

• [Bug]: Cannot use TextToCypherRetriever in Property Graph

  #14536 commented on Apr 8, 2025 • 0 new comments

• [Bug]: from cohere.custom_model_dataset import JsonlDataset cann't find

  #14720 commented on Apr 8, 2025 • 0 new comments

• [Bug]: DashScope default setting cause prompt repack issue

  #14722 commented on Apr 8, 2025 • 0 new comments

• [Question]: Ways to limit my max request per minute?

  #14801 commented on Apr 8, 2025 • 0 new comments

• [Feature Request]: Add an optional id parameter to the ChatMessage object.

  #14881 commented on Apr 8, 2025 • 0 new comments

• [Documentation]: OpenSearch Metadata Filtering doesn't work

  #15166 commented on Apr 8, 2025 • 0 new comments

• [Question]: `SimpleChatStore` encoding for `persist`.

  #15055 commented on Apr 9, 2025 • 0 new comments

• [Bug]: `SimpleDocumentStore.docs` should return documents, but returns nodes?

  #15489 commented on Apr 9, 2025 • 0 new comments

• [Question]: How to update a RedisVectorStore?

  #15522 commented on Apr 9, 2025 • 0 new comments

• [Bug]: Indexing hit rate limit error and keeps endless retrying

  #15649 commented on Apr 9, 2025 • 0 new comments

• [Feature Request]: Update Context Chat Engines to work with MultiModal LLMs

  #15667 commented on Apr 9, 2025 • 0 new comments

• [Bug]: SimpleDirectoryReader fails to find files if recursive=True is set

  #15705 commented on Apr 9, 2025 • 0 new comments

• [Bug]: IPYNBReader does not parse jupyter notebooks that contain Markdown text sections

  #16184 commented on Apr 9, 2025 • 0 new comments

• [Feature Request]: raise RuntimeError(f"Input {texts[i]} is too long for context length {context_length}")

  #16937 commented on Apr 9, 2025 • 0 new comments

• [Bug]: additional_kwargs in ChatMessage messes up token limit in CondensePlusContextChatEngine

  #16125 commented on Apr 9, 2025 • 0 new comments

• [Bug]: Failed to load persisted PropertyGraph data with ValueError

  #15798 commented on Apr 9, 2025 • 0 new comments

• [Question]: Sub question and router query engine

  #16255 commented on Apr 9, 2025 • 0 new comments

• [Bug]: Elasticsearch Query Parameter Configuration Error: window_size Less Than size

  #16293 commented on Apr 9, 2025 • 0 new comments

• [Feature Request]: Support candidate generations

  #16166 commented on Apr 9, 2025 • 0 new comments

• [Bug]: AttributeError: 'GenerateContentResponse' object has no attribute 'usage_metadata'

  #16555 commented on Apr 9, 2025 • 0 new comments

• [Bug]: NeptuneDatabasePropertyGraphStore connection timed out while loading the graphs

  #15977 commented on Apr 9, 2025 • 0 new comments

• [Question]: How to migrate index by changing the storage context

  #16514 commented on Apr 9, 2025 • 0 new comments

• [Question]: BM25 Retriever Accessing All Documents in Document Store Instead of VectorStore Index

  #16588 commented on Apr 9, 2025 • 0 new comments

• [Bug]: Callback called twice for Anthropic integration of llama-index on finishing complete()

  #16449 commented on Apr 9, 2025 • 0 new comments

• [Feature Request]: Support for counting reasoning tokens for openai o1 models

  #17023 commented on Apr 9, 2025 • 0 new comments

• [Feature Request]: Consistently allow the use of `Path` where a file or directory is specified

  #16941 commented on Apr 9, 2025 • 0 new comments

• [Feature Request]: Add support for FalkorDB vector indexing

  #16943 commented on Apr 10, 2025 • 0 new comments

• [Bug]: token_counting.get_tokens_from_response dies trying to convert response.raw (None) to dict

  #15787 commented on Apr 10, 2025 • 0 new comments

• [Bug]: A MCQ generated becomes multiple question instead of single question

  #16622 commented on Apr 10, 2025 • 0 new comments

• [Question]: Got following error after deleting document from index and doing new query on index raise ValueError(f"doc_id {doc_id} not found.") ValueError: doc_id fd17f519-5e80-4364-a1ac-be2ebf8187f5 not found.

  #16195 commented on Apr 10, 2025 • 0 new comments

• [Bug]: Infinite ReAct loop when setting max_iterations as 1

  #16499 commented on Apr 10, 2025 • 0 new comments

• [Question]:Token indices sequence length error when generating VectorStore.from_documents and inaccurate responses afterwards

  #15839 commented on Apr 10, 2025 • 0 new comments

• [Feature Request]: NodePostprocessors could benefit from an async equivalent to postprocess_nodes

  #16911 commented on Apr 10, 2025 • 0 new comments

• [Bug]: PGVectorStore incorrectly handles string metadata that resembles numbers

  #15962 commented on Apr 10, 2025 • 0 new comments

• [Bug]: `structured_predict` -> silently failing `function_tool.FunctionTool.call()` invocation

  #16419 commented on Apr 10, 2025 • 0 new comments

• [Question]: ModuleNotFoundError: No module named 'llama_index.core.llms.function_calling'

  #15999 commented on Apr 10, 2025 • 0 new comments

• [Bug]: TypeError: construct_payload() got an unexpected keyword argument 'formatted'

  #16119 commented on Apr 10, 2025 • 0 new comments

• [Question]: OpensearchVectorStore Metadata

  #16438 commented on Apr 10, 2025 • 0 new comments

• [Feature Request]: mmr_threshold for QdrantVectorStore

  #17048 commented on Apr 10, 2025 • 0 new comments

• [Bug]: LlamaIndexInstrumentor not working propely for BaseEmbeddings.get_text_embedding_batch

  #15591 commented on Apr 10, 2025 • 0 new comments

• [Question]: How to ask questions on particular document in VectorDB?

  #15844 commented on Apr 10, 2025 • 0 new comments

• REBEL - new node postprocessor

  #17590 commented on Apr 10, 2025 • 0 new comments

• Aquery ivfflat fix

  #17922 commented on Apr 9, 2025 • 0 new comments

• Add support for providing optional logits processors to HuggingFace text-only LLM and MLLM models for output control

  #18086 commented on Apr 10, 2025 • 0 new comments

• add cachePoint to messages

  #18130 commented on Apr 4, 2025 • 0 new comments

• ZepMemory implementation for LlamaIndex

  #18199 commented on Apr 9, 2025 • 0 new comments