2 Releases published by 1 person

• v0.10.54post1

  published Jul 11, 2024

• v0.10.55

  published Jul 12, 2024

31 Pull requests merged by 24 people

• feat: add nested filters for azureaisearch

  #14795 merged Jul 17, 2024

• feat: Add NOT IN filter for Qdrant vector store

  #14791 merged Jul 17, 2024

• feat: add azureaisearch supported conditions

  #14787 merged Jul 16, 2024

• feat: azureaisearch support collection string

  #14712 merged Jul 16, 2024

• docs: Fix wrong Qdrant_metadata_filter doc

  #14773 merged Jul 16, 2024

• Fix OpenWeatherMapToolSpec.forecast_tommorrow_at_location

  #14745 merged Jul 15, 2024

• Remove double curly replacing from output parser utils

  #14735 merged Jul 15, 2024

• Chore: restrict the scipy verstion to 1.12.0 to fix the error cannot import name triu from scipy.linalg

  #14761 merged Jul 15, 2024

• 📃 docs(examples): fix KnowledgeGraphDemo link error

  #14764 merged Jul 15, 2024

• Bump setuptools from 69.5.1 to 70.0.0 in /llama-index-integrations/embeddings/llama-index-embeddings-upstage

  #14771 merged Jul 15, 2024

• [FIX] Issues with llama-index-readers-box pyproject.toml

  #14770 merged Jul 15, 2024

• 📃 docs(Learn): Loading Data

  #14762 merged Jul 15, 2024

• follow odata.nextLink

  #14708 merged Jul 15, 2024

• update docs for OpenAI/AzureOpenAI additional_kwargs

  #14749 merged Jul 14, 2024

• Add GraphRAG Implementation

  #14752 merged Jul 14, 2024

• Adds Quantization option to QdrantVectorStore

  #14740 merged Jul 13, 2024

• feat: improve azureai search deleting

  #14693 merged Jul 12, 2024

• Update simple_summarize.py

  #14714 merged Jul 12, 2024

• fix: tools are required for attachments in openai api

  #14609 merged Jul 12, 2024

• remove flakey and unhelpful tests

  #14737 merged Jul 12, 2024

• Box reader

  #14685 merged Jul 12, 2024

• fix fastembed python version

  #14710 merged Jul 12, 2024

• v0.10.55

  #14709 merged Jul 12, 2024

• feat(ci): cache poetry in CI

  #14485 merged Jul 12, 2024

• Add a sample notebook to show llamaindex agents used for managed vertex ai index

  #14704 merged Jul 12, 2024

• changes to Exa search tool getting started and example notebook

  #14690 merged Jul 11, 2024

• These docs have been supplanted by the full llamaparse docs site

  #14688 merged Jul 11, 2024

• update observability docs

  #14692 merged Jul 11, 2024

• Upgrade llama-cloud client to 0.0.9 and support retrieval_mode and files_top_k

  #14696 merged Jul 11, 2024

• Documentation: update huggingface.ipynb

  #14697 merged Jul 11, 2024

• [version] bump version to v0.10.54post1 (fixes 0.10.54 release with mismatch llama-index-core version)

  #14699 merged Jul 11, 2024

12 Pull requests opened by 10 people

• add property extraction for KGs

  #14707 opened Jul 11, 2024

• chore: read AZURE_POOL_MANAGEMENT_ENDPOINT from env vars

  #14732 opened Jul 12, 2024

• bug in reading files from sharepoint (windows)

  #14738 opened Jul 12, 2024

• fix: llamaindex agent chat function will lose external args

  #14742 opened Jul 13, 2024

• WIP: update structured outputs syntax

  #14747 opened Jul 13, 2024

• [very WIP] add streaming for tool calling / structured extraction

  #14759 opened Jul 15, 2024

• Add a notebook to show llamaindex agent works with graphRAG and Vertex AI

  #14774 opened Jul 16, 2024

• Fix PineconeRetriever: remove usage of global variables, check embeddings - Init Pinecone properly

  #14799 opened Jul 17, 2024

• Implements `delete_nodes()` and `clear()` for Weviate, Opensearch, Milvus, Postgres, and Pinecone Vector Stores

  #14800 opened Jul 17, 2024

• Add filter to get_triples in neo4j

  #14811 opened Jul 18, 2024

• Fix bug when sanitize is used in neo4j property graph

  #14812 opened Jul 18, 2024

• Fix output format system prompt in ReAct agent

  #14814 opened Jul 18, 2024

46 Issues closed by 14 people

• I wonder how to use llama_index to retrieve the Milvus collection after it is created and indexed using the MilvusVectorStore.

  #14790 closed Jul 18, 2024

• [Bug]: PromptLayer Callback does not work with OpenAIPydanticProgram

  #12710 closed Jul 17, 2024

• [Feature Request]: Batch asynchronous text embedding for LangchainEmbedding

  #12709 closed Jul 17, 2024

• [Question]: How to create a retriever from pgvector store

  #12707 closed Jul 17, 2024

• Convert ChatResponse to Response (e.g. for use in BatchEvalRunner)?

  #12701 closed Jul 17, 2024

• Embedding getting saved as "number" datatype in Elastic Search Store, instead of "dense_vector". What can be the reason behind it?

  #12698 closed Jul 17, 2024

• [Question]: Multiple Index for one doc OR query with multiple indices

  #12694 closed Jul 17, 2024

• [Bug]: Error: NotFoundError - Resource not found while implementing llama index with Azure OpenAI for fine-tuning

  #12685 closed Jul 17, 2024

• [Question]: Why node scores are so small and in scientific notation ? How to make it some more meaningful normalized number ?

  #12677 closed Jul 17, 2024

• [Bug]: can elasticsearchstore accept https url and a pem ssl certificate?

  #12656 closed Jul 17, 2024

• [Bug]: Output from tool calls are not very observable

  #9770 closed Jul 17, 2024

• How should the dim parameter value of MilvusVectorStore be calculated?

  #14781 closed Jul 17, 2024

• Indexes cannot be created correctly using the MilvusVectorStore.

  #14779 closed Jul 17, 2024

• [Feature Request]: Version pinning for sub packages

  #14788 closed Jul 17, 2024

• [Bug]: OpenWeatherMapToolSpec throws error when called for weather forecast

  #14744 closed Jul 16, 2024

• [Bug]: [OpenAILike] Cannot use llm_chat_callback on an instance without a callback_manager attribute

  #14786 closed Jul 16, 2024

• [Bug]: Query on MilvusVectorStore with node_ids populated, but filters empty will fail

  #12673 closed Jul 16, 2024

• [Bug]: finetuning_handler.save_finetuning_events("finetuning_events.jsonl") fails

  #12668 closed Jul 16, 2024

• [Question]: Query on Multi-Tenancy Support with HNSW Index via PGVector in LlamaIndex

  #12666 closed Jul 16, 2024

• [Bug]: Sec Filing Downloader Error

  #12651 closed Jul 15, 2024

• [Question]: exclude auto-generated code from pre-commit

  #12648 closed Jul 15, 2024

• [Question]: prevent max token error after retrieval

  #12633 closed Jul 15, 2024

• [Question]: llama_index.embeddings.huggingface -> ImportError: cannot import name 'AsyncInferenceClient'

  #11019 closed Jul 15, 2024

• [Bug]: SharePointReader does not follow @odata.nextLink links

  #14702 closed Jul 15, 2024

• [Documentation]: GitHubRepositoryReader Demo notebook has unsupported code

  #12629 closed Jul 13, 2024

• [Feature Request]: Quantize dense embeddings with QdrantVectorStore

  #12316 closed Jul 13, 2024

• [Bug]: IngestionPipeline Parallel Processing for HuggingFaceEmbedding

  #13956 closed Jul 13, 2024

• [Bug]: keyword_index.as_retriever seems it cannot be set similarity_top_K = int , it is doesnt worked

  #14724 closed Jul 13, 2024

• [Bug]: LlamaCloud validation error on "Project" model

  #14723 closed Jul 13, 2024

• [Bug]: openai assistant agent has incorrect or outdated syntax for attaching files

  #14517 closed Jul 12, 2024

• [Question]: neo4j - Failed to write data to connection

  #14731 closed Jul 12, 2024

• [Question]: How to make a agent process to two index to answer?

  #12601 closed Jul 12, 2024

• [Question]: What is the difference between vector store and storage context in terms of storing embeddings that are generated while creating a vector index?

  #12571 closed Jul 12, 2024

• llama-index-vector-stores-weaviate pypi version

  #14721 closed Jul 12, 2024

• [Bug]: PropertyGraphIndex._build_index_from_nodes() got an unexpected keyword argument 'possible_entities'

  #14715 closed Jul 12, 2024

• Can RecursiveRetriever be used with QueryFusionRetriever?

  #14713 closed Jul 12, 2024

• [Feature Request]: Add a sample notebook to show llamaindex agents used for managed vertex ai index

  #14703 closed Jul 12, 2024

• [Bug]: Groq is giving `Error`

  #14701 closed Jul 11, 2024

• [Question]: Content not loading after package updates.

  #14684 closed Jul 11, 2024

• [Question]: Can SQLTableRetrieverQueryEngine or NLSQLTableQueryEngine filter specific value ?

  #12569 closed Jul 11, 2024

• Llama Hub Chain_of_Table pack issue

  #12568 closed Jul 11, 2024

• Using_to_llama_similarities() normalization technique may lead to low quality retrieved documents / chunks.

  #12567 closed Jul 11, 2024

• [Question]: In a RAG pipeline, made using llamaindex, where is "llm" used while where is "embed model" used ?

  #12553 closed Jul 11, 2024

• [Bug]: ValueError: Tool with name functions not found

  #12483 closed Jul 11, 2024

• [Feature Request]: Create MLFlow Callback handler

  #6617 closed Jul 11, 2024

• [Bug]: ClientResponseError when using KeywordExtractor

  #14698 closed Jul 11, 2024

54 Issues opened by 54 people

• [Feature Request]: Support ollama's keep_alive request parameter

  #14813 opened Jul 18, 2024

• [Documentation]: DOI is invalid

  #14810 opened Jul 18, 2024

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

  #14809 opened Jul 18, 2024

• [Question]: similarity_top_k not clear

  #14808 opened Jul 18, 2024

• [Question]: Why is pydantic v1 used as default?

  #14807 opened Jul 18, 2024

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

  #14806 opened Jul 18, 2024

• [Question]: Sentence Splitter with hyperlinks

  #14805 opened Jul 18, 2024

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

  #14804 opened Jul 18, 2024

• [Question]: supported -- https://github.com/microsoft/graphrag ？

  #14803 opened Jul 18, 2024

• [Question]: Query-time metadata filtering

  #14802 opened Jul 18, 2024

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

  #14801 opened Jul 18, 2024

• [Bug]: CUDA error: device-side assert triggered when calling index.refresh_ref_docs(documents=documents, batch_size=5)

  #14798 opened Jul 17, 2024

• [Bug]: Can't create Neo4jGraphStore using latest Neo4j docker container due to old cipher syntax

  #14797 opened Jul 17, 2024

• [Question]: Retrieving All Nodes from VectorStoreIndex Only Returns 36 Results

  #14796 opened Jul 17, 2024

• [Question]: Error

  #14793 opened Jul 17, 2024

• [Bug]: Failed to load file using s3Reader and SimpleDirectoryReader with aws s3

  #14792 opened Jul 17, 2024

• [Bug]: No module named 'llama_index.llms.openai.base

  #14785 opened Jul 16, 2024

• How to deploy open-source embedding models in auto-merging retriever: ValueError: shapes (1024,) and (384,) not aligned: 1024 (dim 0) != 384 (dim 0)

  #14784 opened Jul 16, 2024

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

  #14782 opened Jul 16, 2024

• [Bug]: Error in initializing neo4j

  #14778 opened Jul 16, 2024

• [Question]: Access LLM's response object CompleteResponse() attribute `additional_kwarg` in RAG

  #14777 opened Jul 16, 2024

• [Question]: How to enable "Calling function" print out after querying from Multi-Document Agent example

  #14776 opened Jul 16, 2024

• [Bug]: File rename error in llama-index-finetuning/llama_index/finetuning/mistralai/utils.py

  #14775 opened Jul 16, 2024

• [Feature Request]: Add a notebook to show llamaindex agent works with graphRAG and Vertex AI

  #14772 opened Jul 16, 2024

• [Documentation]: Broken 'Examples' Link

  #14769 opened Jul 15, 2024

• [Question]: Unable to understand how document storage works in case nodes are deleted

  #14767 opened Jul 15, 2024

• [Documentation]: Some of the URL Not Working

  #14765 opened Jul 15, 2024

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

  #14763 opened Jul 15, 2024

• [Question]: AttributeError: 'property' object has no attribute 'context_window'

  #14758 opened Jul 15, 2024

• Compatibility issue between Qdrant and DSPy when Qdrant is used as the VectorStoreIndex's storage context

  #14757 opened Jul 15, 2024

• [Question]: How to insert/delete document to/from VectorStoreIndex when using IngestionPipeline?

  #14756 opened Jul 15, 2024

• [Bug]: FaithfulnessEvaluator Current PrompTemplate not good enough

  #14753 opened Jul 14, 2024

• [Bug]: Missing !pip install llama-index-readers-file

  #14751 opened Jul 14, 2024

• [Question]: name 'np' is not defined while using PandasAgent

  #14750 opened Jul 14, 2024

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

  #14748 opened Jul 14, 2024

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

  #14746 opened Jul 13, 2024

• [Question]: TokenCountingHandler doesn't work with VectorMemory loaded from the disk

  #14743 opened Jul 13, 2024

• [Bug]: llama_index core calls the huggingface integration in a deprecated manner (llama_index.embeddings.huggingface not found)

  #14741 opened Jul 13, 2024

• [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 opened Jul 13, 2024

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

  #14736 opened Jul 12, 2024

• [Bug]: An error occurred while accessing SharePoint: 'name'

  #14734 opened Jul 12, 2024

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

  #14730 opened Jul 12, 2024

• [Bug]: Scores in the retrieved nodes are in reversed order in the Weaviate integration

  #14728 opened Jul 12, 2024

• [Feature Request]: LlamaCPP - Allow the default context window from the model

  #14727 opened Jul 12, 2024

• [Bug]: openai Rate Limit Error

  #14725 opened Jul 12, 2024

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

  #14722 opened Jul 12, 2024

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

  #14720 opened Jul 12, 2024

• [Feature Request]: AI application buliding

  #14719 opened Jul 12, 2024

• [Question]: llamaindex支持mysql储存文档和索引吗

  #14718 opened Jul 12, 2024

• [Question]: Custom callback handler

  #14717 opened Jul 12, 2024

• [Bug]: No available version integration of NvidiaTriton

  #14716 opened Jul 12, 2024

• [Bug]: RAPTOR failed due to duplicated Document ID, chromadb.errors.DuplicateIDError: Expected IDs to be unique, found duplicates of: 17ab7f1d-***********

  #14711 opened Jul 12, 2024

• [Question]: ChromaDB Setup Error

  #14705 opened Jul 11, 2024

• [Bug]: LLMTextCompletionProgram outputs correct answer, but causes ValueError

  #14700 opened Jul 11, 2024

59 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.

• Adding vector store for Azure Cosmos DB NoSql

  #14158 commented on Jul 12, 2024 • 6 new comments

• Add vector store integration of lindorm, including knn search, …

  #14623 commented on Jul 17, 2024 • 3 new comments

• feat: ✨ Implement async functionality in `BedrockConverse`

  #14326 commented on Jul 15, 2024 • 3 new comments

• Azure AI Inference integration

  #14672 commented on Jul 18, 2024 • 2 new comments

• Add default model for the nvidia classes in local NIM mode

  #14652 commented on Jul 17, 2024 • 1 new comment

• [Question]: Does PandasQueryEngine support multiple DataFrames?How to make it possible

  #12885 commented on Jul 17, 2024 • 0 new comments

• [Feature Request]: Make IngestionPipeline compatible with HierarchicalNodeParser

  #12893 commented on Jul 17, 2024 • 0 new comments

• [Bug]: Querying by specific doc_ids in the vector db not working properly

  #14121 commented on Jul 17, 2024 • 0 new comments

• [Question]: QA with PDF using Dense X Retrieval

  #12871 commented on Jul 16, 2024 • 0 new comments

• [Bug]: data_generator.generate_questions_from_nodes() does not generate questions. Progress bar does not move

  #12859 commented on Jul 16, 2024 • 0 new comments

• [Question]: RAG implementation using Llama Index

  #12870 commented on Jul 16, 2024 • 0 new comments

• [Bug]: Metadata keys are being removed automatically when using auto_retriever

  #12843 commented on Jul 16, 2024 • 0 new comments

• [Bug]: Failed to load file gcs-bucke-name/folder-name/myfile.pdf with error: 'GCSFile' object has no attribute 'name'. Skipping...

  #12840 commented on Jul 16, 2024 • 0 new comments

• [Question]: Joint QA Summary Query Engine no openAI

  #12749 commented on Jul 16, 2024 • 0 new comments

• [Bug]: [Llamafile integration] Server disconnected without sending a response

  #12866 commented on Jul 16, 2024 • 0 new comments

• [Bug]: VectorStoreIndex.from_documents() with Elasticsearch storage context does not terminate asyncio threads

  #12876 commented on Jul 16, 2024 • 0 new comments

• [Bug]: Input should be a valid dictionary or instance of SentenceSimilarityInputsCheck: received `Context information is below.

  #12873 commented on Jul 16, 2024 • 0 new comments

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

  #14660 commented on Jul 11, 2024 • 0 new comments

• [Bug]: Encountered exception writing response to history: list index out of range

  #12890 commented on Jul 17, 2024 • 0 new comments

• [Bug]: RAFT dataset generation stops if context is too big

  #12883 commented on Jul 17, 2024 • 0 new comments

• [Bug]: Response Streaming Using Llama Index enters an endeless loop

  #12886 commented on Jul 17, 2024 • 0 new comments

• [Question]: Encountered exception writing response to history: list index out of range

  #12887 commented on Jul 17, 2024 • 0 new comments

• [Bug]: Error loading Composable Graph from persist directory

  #12478 commented on Jul 17, 2024 • 0 new comments

• [Question]: Is it possible to get the text from Node id?

  #12901 commented on Jul 17, 2024 • 0 new comments

• [Bug]: Node Parsing error with Qdrant and Llama Index query engine

  #12891 commented on Jul 17, 2024 • 0 new comments

• [Question]: VectorStoreIndex.as_query_engine() with OpenAI compatible API

  #12888 commented on Jul 17, 2024 • 0 new comments

• [Feature Request]: KnowledgeGraph metadata extractors

  #12600 commented on Jul 17, 2024 • 0 new comments

• [Feature Request]: Additional embedding fine-tuning features

  #10003 commented on Jul 17, 2024 • 0 new comments

• [Bug]: Cannot use TextToCypherRetriever in Property Graph

  #14536 commented on Jul 18, 2024 • 0 new comments

• [Core] Omni-Modal Embedding, Vector Index and Retriever

  #13551 commented on Jul 18, 2024 • 0 new comments

• [Feature Request]: VectorIndexAutoRetriever does not support partial matching

  #12760 commented on Jul 11, 2024 • 0 new comments

• [Feature Request]: Support hybrid semantic search with partial match in Milvus

  #12759 commented on Jul 11, 2024 • 0 new comments

• [Question]: Recommended persistence pattern for SummaryIndex at scale in a web service?

  #12754 commented on Jul 11, 2024 • 0 new comments

• [Bug]: Using qdrant as vectorstore with RaptorRetriever

  #12756 commented on Jul 11, 2024 • 0 new comments

• [Bug]: pydantic.v1.error_wrappers.ValidationError: 2 validation errors for LLMChain. Langchain Agents

  #12744 commented on Jul 11, 2024 • 0 new comments

• [Bug]: LLM evaluated with Llamaindex don't provide scores for certain metrics.

  #11567 commented on Jul 11, 2024 • 0 new comments

• [Question]: How to effectively summarize large documents using SummaryIndex or similar?

  #11779 commented on Jul 11, 2024 • 0 new comments

• [Bug]: GoogleDemo.ipynb notebook seems to be requiring OpenAI API key

  #12753 commented on Jul 11, 2024 • 0 new comments

• Role 'tool' must be a response to a preceding message with 'tool_calls'

  #13715 commented on Jul 11, 2024 • 0 new comments

• [Feature Request]: Google Photos

  #12799 commented on Jul 12, 2024 • 0 new comments

• [Feature Request]: default to pydantic v2

  #13477 commented on Jul 12, 2024 • 0 new comments

• [Bug]: How to fix this error No module named 'llama_index.llms.llama_cpp'

  #12502 commented on Jul 12, 2024 • 0 new comments

• [Feature Request]: Allow SSL Connections to Postgress DB (PGVectorStore)

  #12795 commented on Jul 13, 2024 • 0 new comments

• [Question]: Load pre-existing graph as knowledge graph index

  #12815 commented on Jul 13, 2024 • 0 new comments

• [Question]: Can I use llama-index , but use my custom nodes

  #12733 commented on Jul 13, 2024 • 0 new comments

• [Feature Request]: Postgres relational docstore

  #12820 commented on Jul 14, 2024 • 0 new comments

• [Bug]: llama-index-embeddings-google and llama-index-vector-stores-google need package bump.

  #12811 commented on Jul 14, 2024 • 0 new comments

• [Feature Request]: Redact Tokens for LLMs

  #12853 commented on Jul 15, 2024 • 0 new comments

• [Question]: i want to implement the llama index by default on our pdf files but error occur ConnectError: [WinError 10061] No connection could be made because the target machine actively refused it

  #12822 commented on Jul 15, 2024 • 0 new comments

• [Bug]: the separator used to split text is prepended to the head of generated sentences. I think it should be appended to tail of generated sentences.

  #12828 commented on Jul 15, 2024 • 0 new comments

• [Documentation]: Milvus写入字段如何自定义

  #12832 commented on Jul 15, 2024 • 0 new comments

• [Feature Request]: Return agents thoughts and observations as part of chat response

  #11705 commented on Jul 15, 2024 • 0 new comments

• [Bug]: SimpleFileNodeParser() KeyError: 'extension'

  #11547 commented on Jul 15, 2024 • 0 new comments

• [Question]: How to speed up loading&creating VectorStoreIndex?

  #12786 commented on Jul 15, 2024 • 0 new comments

• RAG with Neo4j nodes and relationships as context for query generation

  #12614 commented on Jul 15, 2024 • 0 new comments

• llamaindex vllm error

  #12955 commented on Jul 15, 2024 • 0 new comments

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

  #14047 commented on Jul 15, 2024 • 0 new comments

• [Feature Request]: retrievers from up-to-date data

  #12851 commented on Jul 16, 2024 • 0 new comments

• [Feature Request]: AgentRunner should support multiple session

  #12858 commented on Jul 16, 2024 • 0 new comments