2 Releases published by 1 person

• v0.10.57 2024-07-22 (v0.10.57)

  published Jul 23, 2024

• v0.10.58

  published Jul 24, 2024

45 Pull requests merged by 29 people

• Jimmy/disable embeddings for sparse strategy

  #15032 merged Jul 30, 2024

• Adds option to construct PGVectorStore with a HNSW index

  #15024 merged Jul 29, 2024

• Add extra_info to metadata field on document in RTFReader

  #15025 merged Jul 29, 2024

• initial implementation FalkorDBPropertyGraphStore

  #14936 merged Jul 29, 2024

• Update default sparse encoder for Hybrid search

  #15019 merged Jul 29, 2024

• bump fastembed dep

  #15029 merged Jul 29, 2024

• Dashscope updates

  #15028 merged Jul 29, 2024

• Adds a LlamaPack that implements LongRAG

  #14916 merged Jul 28, 2024

• Feat: expand span coverage for query pipeline

  #14997 merged Jul 27, 2024

• docs: update TiDB Cloud links to public beta!

  #14976 merged Jul 26, 2024

• integration[embedding]: support textembed embedding

  #14968 merged Jul 26, 2024

• honor exclusion keys when creating the index nodes

  #14911 merged Jul 25, 2024

• undo incompatible kwarg in elasticsearch vector store

  #14973 merged Jul 25, 2024

• make re-raising error skip constructor

  #14970 merged Jul 25, 2024

• toggle for ollama function calling

  #14972 merged Jul 25, 2024

• Docs updates

  #14941 merged Jul 25, 2024

• Feature/azure ai search hotfix

  #14949 merged Jul 25, 2024

• Fix/confluence reader sort auth parameters priority

  #14905 merged Jul 25, 2024

• restrict python version to enable publish of pandasai reader

  #14966 merged Jul 25, 2024

• UnstructuredReader fixes V2.

  #14946 merged Jul 25, 2024

• breaking: update to OpenLLM 0.6

  #14935 merged Jul 25, 2024

• Feature/azure docstore hotfix

  #14950 merged Jul 25, 2024

• fireworks 3.12 support

  #14964 merged Jul 25, 2024

• use proper stemmer in bm25 tokenize

  #14965 merged Jul 25, 2024

• add back kwargs to Ollama

  #14963 merged Jul 25, 2024

• Fix None type error when using Neo4jPropertyGraphStore

  #14957 merged Jul 25, 2024

• fix: organization id

  #14961 merged Jul 25, 2024

• Fixed Import Error in PandasAIReader

  #14915 merged Jul 25, 2024

• Add function calling for Ollama

  #14948 merged Jul 25, 2024

• add organization_id param to LlamaCloudIndex.from_documents

  #14947 merged Jul 24, 2024

• v0.10.58

  #14944 merged Jul 24, 2024

• structured extraction docs + bug fixes

  #14925 merged Jul 24, 2024

• 🐞 fix(integrations): BM25Retriever persist missing arg similarity_top_k

  #14933 merged Jul 24, 2024

• Fix: Token counter expecting response.raw as dict, got ChatCompletionChunk

  #14937 merged Jul 24, 2024

• Llamaindex retriever for Vertex AI Search

  #14913 merged Jul 24, 2024

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

  #14623 merged Jul 24, 2024

• Add claude 3.5 sonnet to multi modal llms

  #14932 merged Jul 24, 2024

• feat: allow to limit how many elements retrieve (qdrant)

  #14904 merged Jul 24, 2024

• Bugfix: Don't pass empty list of embeddings to elasticsearch store when using sparse strategy

  #14918 merged Jul 24, 2024

• Improved deeplake.get_nodes() performance

  #14920 merged Jul 24, 2024

• fix the initialization of Pinecone in the low-level ingestion notebook.

  #14919 merged Jul 24, 2024

• Fix TaskStepOutput sources bug

  #14885 merged Jul 23, 2024

• Update-mappings

  #14917 merged Jul 23, 2024

• fireworks ai llama3.1

  #14914 merged Jul 23, 2024

• v0.10.57

  #14893 merged Jul 23, 2024

9 Pull requests opened by 9 people

• MLflow Integration doc Update

  #14977 opened Jul 26, 2024

• Add LLM for AlibabaCloud PaiEas

  #14983 opened Jul 26, 2024

• fix(sql_wrapper): dont mention foreign keys when theres none

  #14998 opened Jul 28, 2024

• fixed import error regarding OpenAIAgent in the code_interpreter example notebook

  #14999 opened Jul 28, 2024

• Fix: Gemini 1.0 Pro Vision has been official deprecated, switch default model to gemini-1.5-flash

  #15000 opened Jul 28, 2024

• Removes gradient.ai integration

  #15022 opened Jul 29, 2024

• docs(literalai): add Literal AI integration to documentation

  #15023 opened Jul 29, 2024

• GitLab reader integration

  #15030 opened Jul 29, 2024

• Add py.typed file to vector store packages

  #15031 opened Jul 29, 2024

83 Issues closed by 15 people

• [Feature Request]: llama-index-embeddings-fastembed should use latest fastembed that is 0.3.4

  #15001 closed Jul 29, 2024

• [Bug]: llama-index-embeddings-fastembed should use latest fastembed that is 0.3.4 but it is using 0.2.7

  #15002 closed Jul 29, 2024

• [Bug]: DashScopeRerank missing model_name

  #15016 closed Jul 29, 2024

• [Feature Request]: dashscope add a new emembedding

  #15015 closed Jul 29, 2024

• No module named 'llama_index.tools'

  #13024 closed Jul 29, 2024

• Raw response content: b'{"status":{"error":"Wrong input: Not existing vector name error: "},"time":0.030060406}'

  #13020 closed Jul 29, 2024

• [Question]: Gemma Issue with "query_engine = SQLAutoVectorQueryEngine(sql_tool, vector_tool )"

  #11523 closed Jul 29, 2024

• [Question]: Langchain integration demo notebook

  #10334 closed Jul 29, 2024

• Starter Tutorial (Local Models): TypeError

  #15017 closed Jul 29, 2024

• [Feature Request]: I want to use Langchain agents with llamaindex's index

  #13731 closed Jul 29, 2024

• [Question]: How to print Llamadebughandler and tokencount handler logs IN A LOG FILE for rag chatbot using llamaindex and streamlit

  #15012 closed Jul 29, 2024

• [Question]: {'message': 'Failed to send 1 objects in a batch of 1. Please inspect client.batch.failed_objects or collection.batch.failed_objects for the failed objects.'}

  #15006 closed Jul 29, 2024

• Unusual errors

  #15004 closed Jul 28, 2024

• [Question]: Firestore Demo: Fails for Auth with Google API

  #12988 closed Jul 28, 2024

• [Bug]: VectorStoreInfo with unreasonable error

  #12984 closed Jul 27, 2024

• [Bug]: CodeHierarchyQuery Engine doing redundant operations & not finding heirarchical nodes

  #12981 closed Jul 27, 2024

• [Question]: Error: Statement "{sql query}" is invalid SQL

  #12979 closed Jul 27, 2024

• [Feature Request]: Support Modal integration

  #12976 closed Jul 27, 2024

• [Question]: MetadataReplacementPostProcessor - giving irrelavant output

  #12972 closed Jul 27, 2024

• [Feature Request]: Support Bedrock Titan Multimodal Embedding Generation

  #12969 closed Jul 27, 2024

• [Question]: How to create index if I already have sqlite file that contains the embeddings?

  #12966 closed Jul 27, 2024

• [Bug]: parsing glossary across pages in pdf breaks up definition

  #14991 closed Jul 26, 2024

• [Bug]: MultiModalVectorStoreIndex image_to_image_retireve on Google Cloud Platform

  #14887 closed Jul 26, 2024

• [Feature Request]: ReplicateMultiModal Supporting More Models

  #12965 closed Jul 26, 2024

• [Question]: I can't stream output asynchronously, bug a coroutine was expected

  #12949 closed Jul 26, 2024

• [Bug]: Qdrant SparseVector won't work (root:Batch upload failed) when we use Qdrant on Docker.

  #12397 closed Jul 26, 2024

• [Bug]: Llama-index ChatSummaryBuffer didn't summarise the chat history

  #14958 closed Jul 26, 2024

• [Feature Request]: Llamaindex retriever for Vertex AI Search

  #14910 closed Jul 26, 2024

• [Bug]: TypeError: Can't instantiate abstract class Groq with abstract method _prepare_chat_with_tools

  #14969 closed Jul 25, 2024

• [Bug]: Can find 4o-mini after upgrade

  #14894 closed Jul 25, 2024

• [Bug]: Keep getting 'Current user not permitted to use Confluence' but able to connect with the Confluence SDK

  #14836 closed Jul 25, 2024

• [Feature Request]: Can llama-index-llms-fireworks support python 3.12 ?

  #14951 closed Jul 25, 2024

• [Bug]: BM25Retriever __init__ is using wrong stemmer

  #14960 closed Jul 25, 2024

• [Question]: Will the extra_info be concatenated with the text content and then encoded using the embedding model?

  #14956 closed Jul 25, 2024

• [Question]: mixture of Agents inside React Agent

  #14962 closed Jul 25, 2024

• [Feature Request]: Support for NVIDIA NIM Models

  #12944 closed Jul 25, 2024

• [Question]: How to extend metadata when using SimpleDirectoryReader

  #12925 closed Jul 25, 2024

• [Question]: Help needed with CondenseQuestionChatEngine in llama index

  #12918 closed Jul 25, 2024

• [Question]:How do I customize the search workflow

  #12917 closed Jul 25, 2024

• [Feature Request]: The supporting of "Retrieve in embedding mode" in KnowledgeGraphRAGRetriever

  #12914 closed Jul 25, 2024

• [Bug]: ValidationError: 1 validation error for EmbeddingEndEvent embeddings -> 0 value is not a valid list (type=type_error.list)

  #12913 closed Jul 25, 2024

• [Question]:

  #12912 closed Jul 25, 2024

• [Question]: How to fix Only one root is supported issue?

  #12911 closed Jul 25, 2024

• [Feature Request]:

  #12909 closed Jul 25, 2024

• [Question]: Difference between longcontextreorder and flagembeddingreranker

  #12908 closed Jul 25, 2024

• how can I change the path to the hugging face download path?

  #12907 closed Jul 25, 2024

• [Bug]: The graph_query_synthesis_prompt parameter of KnowledgeGraphRAGRetriever

  #12905 closed Jul 25, 2024

• [Bug]: The verbose parameter bug of KnowledgeGraphRAGRetriever

  #12904 closed Jul 25, 2024

• Import Error in PandasAIReader[Bug]:

  #14878 closed Jul 25, 2024

• [Bug]: Can't instantiate abstract class AzureOpenAI with abstract method _prepare_chat_with_tools

  #14942 closed Jul 24, 2024

• [Bug]: BM25Retriever failed to restore arguments defined before persistence

  #14909 closed Jul 24, 2024

• [Bug]: TypeError: Can't instantiate abstract class AzureAICompletionsModel with abstract method _prepare_chat_with_tools

  #14930 closed Jul 24, 2024

• [Bug]: token_counting.py fails with 0.10.57

  #14908 closed Jul 24, 2024

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

  #12901 closed Jul 24, 2024

• [Feature Request]: Make IngestionPipeline compatible with HierarchicalNodeParser

  #12893 closed Jul 24, 2024

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

  #12891 closed Jul 24, 2024

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

  #12890 closed Jul 24, 2024

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

  #12888 closed Jul 24, 2024

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

  #12887 closed Jul 24, 2024

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

  #12886 closed Jul 24, 2024

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

  #12885 closed Jul 24, 2024

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

  #12883 closed Jul 24, 2024

• [Feature Request]: KnowledgeGraph metadata extractors

  #12600 closed Jul 24, 2024

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

  #12478 closed Jul 24, 2024

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

  #10003 closed Jul 24, 2024

• [Question]: Why the IngestionPipeline's _handle_upserts method use ref_doc_id rather than node.id?

  #14931 closed Jul 24, 2024

• [Bug]: Indexing a document in Elasticsearch with ELSER fails due to a null argument in the request

  #14821 closed Jul 24, 2024

• VectorStoreIndex + transformations not working as expected

  #14921 closed Jul 24, 2024

• Groq integration broken with latest llama-index version

  #14922 closed Jul 23, 2024

• [Bug]: TaskStepOutput sources may include ToolOutput from other steps

  #14884 closed Jul 23, 2024

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

  #12876 closed Jul 23, 2024

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

  #12873 closed Jul 23, 2024

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

  #12871 closed Jul 23, 2024

• [Question]: RAG implementation using Llama Index

  #12870 closed Jul 23, 2024

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

  #12866 closed Jul 23, 2024

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

  #12859 closed Jul 23, 2024

• [Feature Request]: AgentRunner should support multiple session

  #12858 closed Jul 23, 2024

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

  #12851 closed Jul 23, 2024

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

  #12843 closed Jul 23, 2024

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

  #12840 closed Jul 23, 2024

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

  #12749 closed Jul 23, 2024

• [Question]: ModuleNotFoundError: No module named "llama_index. xxxxx"

  #14892 closed Jul 23, 2024

• [Bug]: OpenAI not working

  #14898 closed Jul 23, 2024

43 Issues opened by 40 people

• [Feature Request]: Add LMStudio Embeddings

  #15021 opened Jul 29, 2024

• [Question]: Can we use `TokenCountingHandler` with different models.

  #15020 opened Jul 29, 2024

• [Question]: how can i limit the VectorStoreIndex's from_documents resource usage?

  #15018 opened Jul 29, 2024

• [Bug]: WeaviateVectorStore never delete old documents after pipeline.run

  #15014 opened Jul 29, 2024

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

  #15013 opened Jul 29, 2024

• [Question]: OpenAPIToolSpec - RecursionError: maximum recursion depth exceeded for big OpenAPISpec yaml file.

  #15011 opened Jul 29, 2024

• [Question]: What information is stored in VectorStoreIndex, where can I view this information, and why does print(index.index_struct) only have index_id

  #15009 opened Jul 29, 2024

• 在创建知识图谱的代码中，执行到retrieve时，发生了下面的错误，表示ValueError: too many values to unpack (expected 2) 通常表示在解包操作中，右侧提供的值数量多于左侧预期接收的变量数量

  #15008 opened Jul 29, 2024

• [Question]: {'message': 'Failed to send 1 objects in a batch of 1. Please inspect client.batch.failed_objects or collection.batch.failed_objects for the failed objects.'}

  #15007 opened Jul 29, 2024

• [Question]: I already have a graph knowledge stored in neo4j. is there a way to directly use it for Property Graph index?

  #15005 opened Jul 29, 2024

• [Question]: Retriever documents, embeddings = None

  #14996 opened Jul 27, 2024

• [Question]: How to implement LLM caching

  #14995 opened Jul 27, 2024

• [Question]: Router Query Engine Examples

  #14994 opened Jul 27, 2024

• [Feature Request]: Upgrade Gemini LLM to be function calling for select Gemini LLMs

  #14993 opened Jul 27, 2024

• [Feature Request]: Request for Upgrade to Support Gradient Accumulation Steps in Latest SentenceTransformers Version

  #14989 opened Jul 26, 2024

• [Bug]: MarvinMetadataExtractor not working proerly, as well as the ai_model decorator

  #14987 opened Jul 26, 2024

• [Bug]: MetadataFilters.legacy_filters() breaks with nesting

  #14986 opened Jul 26, 2024

• [Bug]: ValueError: Got a larger chunk overlap (20) than chunk size (100), should be smaller.

  #14985 opened Jul 26, 2024

• [Feature Request]: Support for Metadata Filtering using native Python functions

  #14982 opened Jul 26, 2024

• [Question]: ImportError Ollama

  #14981 opened Jul 26, 2024

• [Bug]: Hugging Face Inference API Fails to Extract Entities with SchemaLLMPathExtractor

  #14978 opened Jul 26, 2024

• [Question]: Extract_prompt with DynamicLLMPathExtractor

  #14975 opened Jul 26, 2024

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

  #14974 opened Jul 26, 2024

• [Question]:

  #14971 opened Jul 25, 2024

• [Feature Request]: Metadata Filters for BM25 Retrievers

  #14959 opened Jul 25, 2024

• [Question]: observability integration for open source models

  #14955 opened Jul 25, 2024

• not able use colbert embeddings with llamaindex

  #14953 opened Jul 25, 2024

• `response.message` in `query_pipeline_memory` example

  #14952 opened Jul 25, 2024

• [Bug]: Broken docstores -> broken indices

  #14943 opened Jul 24, 2024

• [Bug]: VectorStoreIndex insert async not working

  #14940 opened Jul 24, 2024

• [Question]: APIConnectionError

  #14929 opened Jul 24, 2024

• [Question]: can i save a summary index?

  #14928 opened Jul 24, 2024

• [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 opened Jul 24, 2024

• [Bug]: PandasQueryEngine cannot execute simple pandasframe code, giving error "NameError: name 'pd' is not defined"

  #14926 opened Jul 24, 2024

• [Question]: ReAct Agent's stream_chat method only returns the first step while using FastAPI and Streamlit

  #14924 opened Jul 24, 2024

• [Question]: Different similarity_top_k values return data with significant differences and varying scores

  #14923 opened Jul 24, 2024

• [Question]: Do I have the correct version; what is the correct import statement for GPT Index?

  #14912 opened Jul 23, 2024

• [Bug]: Inefficient Neo4j Driver Initialization and Missing Connection Closure in Neo4jPropertyGraphStore

  #14907 opened Jul 23, 2024

• [Question]: SentenceWindowNodeParser obtaining different results for retrieval depending on the window size.

  #14906 opened Jul 23, 2024

• [Documentation]: Correct the formatting of reference

  #14903 opened Jul 23, 2024

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

  #14902 opened Jul 23, 2024

• [Bug]: LlamaIndex: Parallelizing Ingestion Pipeline: httpx.ReadTimeout: Error running coroutine

  #14901 opened Jul 23, 2024

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

  #14897 opened Jul 23, 2024

67 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]: llama_index.llms.ollama httpx.HTTPStatusError: Server error '500 Internal Privoxy Error' for url 'http:https://localhost:11434/api/chat'

  #14880 commented on Jul 23, 2024 • 0 new comments

• [Bug]: Azure Open AI returns 500 model error when used in OpenAIAgent

  #14882 commented on Jul 23, 2024 • 0 new comments

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

  #13526 commented on Jul 23, 2024 • 0 new comments

• [Bug]: When using llamaIndex to access a Ollama local LLM (llama3:8b)service in mac, there will be error 503

  #13640 commented on Jul 23, 2024 • 0 new comments

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

  #14870 commented on Jul 23, 2024 • 0 new comments

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

  #14804 commented on Jul 23, 2024 • 0 new comments

• [Question]: similarity_top_k not clear

  #14808 commented on Jul 23, 2024 • 0 new comments

• [Bug]: Code in Guidance Pydantic Program doc not working

  #13379 commented on Jul 23, 2024 • 0 new comments

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

  #13962 commented on Jul 23, 2024 • 0 new comments

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

  #14809 commented on Jul 23, 2024 • 0 new comments

• [Feature Request]: AI application buliding

  #14719 commented on Jul 23, 2024 • 0 new comments

• [Question]: Evaluating correctness of my RAG solution

  #13063 commented on Jul 23, 2024 • 0 new comments

• Unable to query the Weaviate Index using RaptorRetriever and RetrieverQueryEngine Modules[Bug]:

  #13045 commented on Jul 23, 2024 • 0 new comments

• [Question]: llm completion giving bad results

  #13048 commented on Jul 23, 2024 • 0 new comments

• [Bug]: ConfluenceReader doesn't support table-cells with multiple lines

  #13050 commented on Jul 23, 2024 • 0 new comments

• [Question]: OpenAIAgent.from_tools not working with streamlit, works fine outside it.

  #13040 commented on Jul 23, 2024 • 0 new comments

• [Question]: Storing query responses as cache for faster retrieval

  #12411 commented on Jul 23, 2024 • 0 new comments

• replicate with llama-index and streamlit - unable to find documents[Question]:

  #10155 commented on Jul 23, 2024 • 0 new comments

• [Bug]: sql_retriever.py parse_response_to_sql returning query with 'sql' keyword in the query.

  #14824 commented on Jul 23, 2024 • 0 new comments

• [Bug]:

  #14825 commented on Jul 23, 2024 • 0 new comments

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

  #13800 commented on Jul 24, 2024 • 0 new comments

• [Feature Request]: Support Claude 3.5 Sonnet Multimodal

  #14568 commented on Jul 24, 2024 • 0 new comments

• [Bug]: ReAct Agent `stream_chat()` does not trigger tool calling, though `chat()` does

  #11013 commented on Jul 24, 2024 • 0 new comments

• [Feature Request]: MongoDB doc_store add Index

  #13078 commented on Jul 24, 2024 • 0 new comments

• [Feature Request]: Allow google readers to take token and credential path

  #13092 commented on Jul 24, 2024 • 0 new comments

• [Feature Request]: show_progress=True to return an iterator with progress?

  #13058 commented on Jul 24, 2024 • 0 new comments

• [Question]: Getting JSONDecodeerror while using "LLMTextCompletionProgram" along with "mistral ai 7b" LLM

  #13080 commented on Jul 24, 2024 • 0 new comments

• [Question]: Can I skip using indexing if the documents are very less?

  #13073 commented on Jul 24, 2024 • 0 new comments

• [Documentation]: There is no "view code" [Azure]

  #13084 commented on Jul 24, 2024 • 0 new comments

• [Question]: need document

  #13079 commented on Jul 24, 2024 • 0 new comments

• [Bug]: Can not download PaulGrahamEssayDataset

  #12915 commented on Jul 24, 2024 • 0 new comments

• [Question]: Summarize a long document?

  #13071 commented on Jul 24, 2024 • 0 new comments

• [Bug]: ModuleNotFoundError: No module named 'llama_index.core.vector_stores.google'

  #12358 commented on Jul 24, 2024 • 0 new comments

• [Feature Request]: AutoMergingRetriever using two Supabase VectorStoreIndex

  #10696 commented on Jul 24, 2024 • 0 new comments

• [Feature Request]: Integrate graph databases as LlamaIndex Graph Stores

  #12517 commented on Jul 24, 2024 • 0 new comments

• [Question]: CondenseQuestionChatEngine try to change the question?

  #13051 commented on Jul 24, 2024 • 0 new comments

• [Bug]: Unable to delete pinecone stored vectors with new pinecone serverless index architecture

  #13451 commented on Jul 25, 2024 • 0 new comments

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

  #13722 commented on Jul 25, 2024 • 0 new comments

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

  #14476 commented on Jul 25, 2024 • 0 new comments

• [Bug]: JSONDecodeError: Extra data: line 1 column 4 (char 3) on download_llama_dataset for PaulGrahamEssay

  #13114 commented on Jul 25, 2024 • 0 new comments

• [Question]: Why is this llama-index query to Ollama (llama3) always timing out?

  #13106 commented on Jul 25, 2024 • 0 new comments

• [Bug]: PostgresSyntaxError when using the "in" operator and MetadataFilters

  #13111 commented on Jul 25, 2024 • 0 new comments

• [Question]: Memory / sizing issues with KnowledgeGraphIndex and embedding

  #13104 commented on Jul 25, 2024 • 0 new comments

• [Question]: vector_store.add(nodes) gives me error = opensearchpy.exceptions.ConnectionTimeout: ConnectionTimeout caused by - TimeoutError()

  #13110 commented on Jul 25, 2024 • 0 new comments

• [Feature Request]: Change OpenAI default embedding model from "text-embedding-ada-002" to "text-embedding-3-small"

  #12994 commented on Jul 25, 2024 • 0 new comments

• [Feature Request]: Text Embeddings Inference Reranker

  #9572 commented on Jul 25, 2024 • 0 new comments

• [Bug]: Cannot use TextToCypherRetriever in Property Graph

  #14536 commented on Jul 26, 2024 • 0 new comments

• [Documentation]: Llama3-Instruct HuggingFaceLLM docs should specify it is a chat model.

  #14516 commented on Jul 26, 2024 • 0 new comments

• Unable to Retrieve Chat Responses from Multiple Indexes.

  #13125 commented on Jul 26, 2024 • 0 new comments

• [Question]: Which Open Source LLM is best for Knowledge Graphs ?

  #13120 commented on Jul 26, 2024 • 0 new comments

• [Question]: I am using Question Generator feature from llama-index , i want to know which LLM is best for this ?

  #13121 commented on Jul 26, 2024 • 0 new comments

• [Bug]: Cannot construct neo4j knowledge graph with embeddings

  #10767 commented on Jul 26, 2024 • 0 new comments

• [Bug]: Error on building and retrieving data using query with AI Search + llama-index

  #10276 commented on Jul 26, 2024 • 0 new comments

• [Bug]: Can a formatted model be added to document reading, including tables, to ensure that important information is not lost when parsing tables and icons

  #13142 commented on Jul 28, 2024 • 0 new comments

• [Feature Request]: Neo4jGraphstore and Neo4jVectorstore should expose the python driver as a parameter to enable users to pass in their own neo4j driver instances

  #13145 commented on Jul 28, 2024 • 0 new comments

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

  #14711 commented on Jul 29, 2024 • 0 new comments

• [Bug]: BM25Retriever cannot work on chinese

  #13866 commented on Jul 29, 2024 • 0 new comments

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

  #14746 commented on Jul 29, 2024 • 0 new comments

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

  #14629 commented on Jul 29, 2024 • 0 new comments

• [Bug]: Wrong display of special characters such as á,ó when streaming response

  #13157 commented on Jul 29, 2024 • 0 new comments

• [Bug]: Token Counter is not working when transformations are applied with an embedding model.

  #13146 commented on Jul 29, 2024 • 0 new comments

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

  #13925 commented on Jul 29, 2024 • 0 new comments

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

  #14652 commented on Jul 24, 2024 • 0 new comments

• bug in reading files from sharepoint (windows)

  #14738 commented on Jul 27, 2024 • 0 new comments

• NVIDIA LlamaIndex Base URL Validation

  #14845 commented on Jul 26, 2024 • 0 new comments

• [WIP] Add mypy to core

  #14883 commented on Jul 29, 2024 • 0 new comments

• Added feature to stream_chat allowing previous chunks to be inserted into the current context window

  #14889 commented on Jul 29, 2024 • 0 new comments