-
Notifications
You must be signed in to change notification settings - Fork 4.5k
Insights: run-llama/llama_index
Overview
Could not load contribution data
Please try again later
1 Release published by 1 person
-
v0.10.44
published
Jun 10, 2024
55 Pull requests merged by 38 people
-
Split HuggingFace embeddings in HuggingFace API and TextGenerationInference packages
#14013 merged
Jun 12, 2024 -
Feat: IBM watsonx.ai llm and embeddings integration
#13600 merged
Jun 12, 2024 -
Fix to milvus filter enum parsing
#14111 merged
Jun 12, 2024 -
fix anthropic llm calls
#14108 merged
Jun 12, 2024 -
Wrong mongo name was used instead of Postgres
#14107 merged
Jun 12, 2024 -
Remove unnecessary excluded from fields in Bedrock embedding
#14085 merged
Jun 12, 2024 -
Feature/added trust remote code
#14102 merged
Jun 12, 2024 -
nit: fix for pandas excel reader
#14086 merged
Jun 12, 2024 -
[ZenGuard LLamaPack] Update README and colab links
#14083 merged
Jun 12, 2024 -
Update `anthropic` dependency to `0.26.2` minimum version
#14091 merged
Jun 12, 2024 -
Add support for Llama 3 Instruct prompt format
#14072 merged
Jun 11, 2024 -
Implement Bedrock Converse API for function calling
#14055 merged
Jun 11, 2024 -
fix/postgres-metadata-in-filter-single-elem
#14035 merged
Jun 11, 2024 -
Integration: Remove stacktrace from notebook in AI21
#14064 merged
Jun 11, 2024 -
Add PandasExcelReader class for parsing excel files
#13991 merged
Jun 11, 2024 -
Bumping Mendable version
#14079 merged
Jun 11, 2024 -
feat: add spans to ingestion pipline
#14062 merged
Jun 11, 2024 -
Add api key as field in Gemini Embedding
#14061 merged
Jun 11, 2024 -
Expand milvus vector store filter options
#13961 merged
Jun 11, 2024 -
v0.10.44
#14056 merged
Jun 10, 2024 -
Integration: AI21 Labs Jamba-Instruct Support
#14030 merged
Jun 10, 2024 -
correct __del__ Vllm
#14053 merged
Jun 10, 2024 -
Bump tornado from 6.4 to 6.4.1 in /llama-index-packs/llama-index-packs-diff-private-simple-dataset
#14039 merged
Jun 10, 2024 -
fix(max-document-length): remove limit
#14041 merged
Jun 10, 2024 -
Add inclusion filter to chromadb
#14010 merged
Jun 10, 2024 -
Add WEBP and GIF to supported image types for SimpleDirectoryReader
#14038 merged
Jun 10, 2024 -
[ZenGuard LlamaPack] Add keywords and update colab link
#14037 merged
Jun 9, 2024 -
fix[issue-13876]: GoogleDriveReader save credentials to disk on cloud
#14022 merged
Jun 8, 2024 -
fix: typo in awsdocdb
#14023 merged
Jun 8, 2024 -
Fix Non-English Display Name
#14021 merged
Jun 8, 2024 -
refactor: add spans to `abstractmethods` via mixin
#14003 merged
Jun 8, 2024 -
Improve type annotations
#13973 merged
Jun 7, 2024 -
Adding streaming support for SQLAutoVectorQueryEngine
#13947 merged
Jun 7, 2024 -
Fix error when using azure_ad without setting the API key
#13970 merged
Jun 7, 2024 -
Fix LanceDBVectorStore add logic (#13992)
#13993 merged
Jun 7, 2024 -
Bump tornado from 6.4 to 6.4.1
#13995 merged
Jun 7, 2024 -
Update lpg_index_guide.md (minor typo)
#13997 merged
Jun 7, 2024 -
fix(deepinfrallm): default max_tokens
#13998 merged
Jun 7, 2024 -
Bind MongoDB primary key ID to Document object to ensure refresh_ref_docs only vectorizes changed data.
#14000 merged
Jun 7, 2024 -
Qdrant: Create payload index for doc_id
#14001 merged
Jun 7, 2024 -
[ZenGuard LLamaPack] Add a colab link to README
#14005 merged
Jun 7, 2024 -
add option to specify embed_model to NLSQLTableQueryEngine
#14006 merged
Jun 7, 2024 -
Add more embeddings to configurable transformations
#14008 merged
Jun 7, 2024 -
[llamapack] update link for ZenGuard colab
#13989 merged
Jun 6, 2024 -
[llamapacks] fix the ZenGuard llampack package name
#13988 merged
Jun 6, 2024 -
LlamaPacks: Add ZenGuard llamapack
#13959 merged
Jun 6, 2024 -
Update jina embedding notebook to include multimodal capability
#13974 merged
Jun 6, 2024 -
Broaden SQLAlchemy support in llama-index-vector-stores-postgres to 1.4+
#13936 merged
Jun 6, 2024 -
+ DuckDBRetriever
#13929 merged
Jun 6, 2024 -
📝 Fix streaming example in "standalone usage" docs
#13981 merged
Jun 6, 2024 -
feat: add spans for multimodal LLMs
#13966 merged
Jun 6, 2024 -
Support all filter operators for Milvus vector store
#13745 merged
Jun 6, 2024 -
Update outdated docs
#13951 merged
Jun 6, 2024 -
This key is necessary for sitemaps to be generated by mkdocs
#13963 merged
Jun 5, 2024
20 Pull requests opened by 19 people
-
LlamaPacks: Add memary llamapack
#13968 opened
Jun 6, 2024 -
Add Cleanlab's LLM integration
#13994 opened
Jun 6, 2024 -
Changing BM25Retriever _retrieve to use numpy methods
#14015 opened
Jun 8, 2024 -
feat(gutenberg): implement new reader
#14025 opened
Jun 8, 2024 -
Fixed System Prompts for Structured Generation
#14026 opened
Jun 8, 2024 -
Correcting the behaviour of the constructor of llama_index.core.utils.GlobalsHelper
#14040 opened
Jun 9, 2024 -
Added helper args to generate_qa_pairs
#14054 opened
Jun 10, 2024 -
MilvusVectorStore: always include text_key in output_fields
#14076 opened
Jun 11, 2024 -
LanceDB: code cleanup, minor updates
#14077 opened
Jun 11, 2024 -
Feature/add command r support oci genai
#14080 opened
Jun 11, 2024 -
Enable Function calling and agent runner for Vertex AI
#14088 opened
Jun 11, 2024 -
Docs overhaul: 2024-06
#14089 opened
Jun 11, 2024 -
Add default node property to neo4j upsert relations
#14095 opened
Jun 12, 2024 -
feat: add marker-pdf reader
#14099 opened
Jun 12, 2024 -
[Core][Retrieval] Implement NDCG metric
#14100 opened
Jun 12, 2024 -
Add MistralAI Finetuning API support
#14101 opened
Jun 12, 2024 -
added method visualizing graph_store in jupyter notebooks
#14104 opened
Jun 12, 2024 -
Prem AI Templates Llama Index support
#14105 opened
Jun 12, 2024 -
Fix parsing sql query.py
#14109 opened
Jun 12, 2024 -
Add Mixture Of Agents paper implementation
#14112 opened
Jun 12, 2024
126 Issues closed by 18 people
-
[Question]: llama-index-embeddings-huggingface without torch and cudnn librarires
#13975 closed
Jun 12, 2024 -
[Bug]: OpenAIAgent.astream_chat() does not work
#14087 closed
Jun 12, 2024 -
[Bug]: WandbCallbackHandler causes streaming response to be empty
#11711 closed
Jun 12, 2024 -
[Question]: why it told me message is not stringable
#11684 closed
Jun 12, 2024 -
[Documentation]: Update replicate_multi_modal notebook to avoid cold boot penalty
#11666 closed
Jun 12, 2024 -
[Bug]: doc_ids parameter of VectorIndexRetriever being absolutely ignored
#11602 closed
Jun 12, 2024 -
[Question]: exception when calling RetrieverQueryEngine with a FusionRetriver
#11430 closed
Jun 12, 2024 -
Connection Timeout with Elastic Search
#9492 closed
Jun 12, 2024 -
[Bug]: AttributeError: 'Anthropic' object has no attribute 'beta'
#14103 closed
Jun 12, 2024 -
[Bug]: llama-index-vector-stores-opensearch -> TypeError: object tuple can't be used in 'await' expression
#11826 closed
Jun 12, 2024 -
[Bug]: Postgres MetadataFilter FilterOperator.IN will fail if value is list with one element.
#14034 closed
Jun 11, 2024 -
[Bug]: Cannot use SentenceWindowNodeParser with custom SentenceSplitter
#14029 closed
Jun 11, 2024 -
[Question]: how to chat with custom database data in offline mode
#11655 closed
Jun 11, 2024 -
[Bug]: query_engine.query()返回错误openai.APITimeoutError: Request timed out.
#11638 closed
Jun 11, 2024 -
How to configure for production - llama networks. Example?
#11652 closed
Jun 11, 2024 -
[Question]: nodes filters and selection based on metadata
#11634 closed
Jun 11, 2024 -
[Bug]: ValueError: Could not extract tool use from input text:
#11630 closed
Jun 11, 2024 -
[Question]: How to load the existing Nebula Graph data into KnowledgeGraphIndex?
#11601 closed
Jun 11, 2024 -
[Question]: Not able to install llama-index-storage-chat-store-azure
#14069 closed
Jun 11, 2024 -
Agent enters infinite loop , even max_iteration=3 wont work
#14071 closed
Jun 11, 2024 -
[Question]: local model files location
#14059 closed
Jun 11, 2024 -
[Question]: How to pass ServiceContext as Settings to VectorStoreIndex
#14036 closed
Jun 10, 2024 -
[Feature Request]: Add MistralAI foundations models to Bedrock integrations
#11625 closed
Jun 10, 2024 -
[Question]: Issues when fine tuning embedding model BAAI/bge-m3 with llama index fine-tuning guide
#11620 closed
Jun 10, 2024 -
[Bug]: GoogleDriveReader DesktopApp credentials fails
#11615 closed
Jun 10, 2024 -
[Question]: Is there a way to have the system automatically choose whether to use the LLM or the RAG?
#11609 closed
Jun 10, 2024 -
[Question]: ReActOutputParser not support chinese
#11608 closed
Jun 10, 2024 -
[Question]: Table relationship problem
#11605 closed
Jun 10, 2024 -
HELP!!!!!!!!!! Can anyone help me in understanding how knowledge graph works internally in llama index?
#11600 closed
Jun 10, 2024 -
[Bug]: segmentation fault
#11598 closed
Jun 10, 2024 -
[Question]: How does TreeIndex retrieve nodes
#11597 closed
Jun 10, 2024 -
[Feature Request]: Accept custom filter ODATA expression for Azure AI Search
#11596 closed
Jun 10, 2024 -
[Question]: chat-engi had no respond
#11595 closed
Jun 10, 2024 -
[Bug]: Python interpreter fails when trying to assign Settings.embed_model from huggingface
#11589 closed
Jun 10, 2024 -
[Bug]: ModuleNotFoundError: No module named 'vllm.model_executor.parallel_utils'.
#14048 closed
Jun 10, 2024 -
ImportError: Cannot import name "PropertyGraphIndex" from "llama_index.core"
#14051 closed
Jun 10, 2024 -
[Question]: Are there any ways to load files in a local git repo with available `readers`
#14043 closed
Jun 10, 2024 -
[Bug]: Can't import RedisCache; missing from llama_index.core.ingestion.cache
#10731 closed
Jun 9, 2024 -
[Documentation]: The GIF in the Unify Integration demo isn't displayed
#13910 closed
Jun 9, 2024 -
[Question]: Retrieved nodes using TreeIndex as retriever with scores = None
#11587 closed
Jun 9, 2024 -
[Bug]: Prebuilt example questions bias questioning strategy
#11585 closed
Jun 9, 2024 -
[Question]: node structure for elasticsearch ~ Dosubot
#13996 closed
Jun 9, 2024 -
[Bug]: GoogleDriveReader still save token to disk after is_cloud arg set to True
#13876 closed
Jun 8, 2024 -
[Bug]: Not able to presentation content under shapes or smart art
#11560 closed
Jun 8, 2024 -
[Question]: Issues when fine tuning model (following llama_index guide)
#11582 closed
Jun 8, 2024 -
[Documentation]: openai_agent example is incompatible with latest openai library
#11579 closed
Jun 8, 2024 -
[Feature Request]: Starling-LM-7B-alpha Query Engine Pack?
#11556 closed
Jun 8, 2024 -
[Documentation]: How to import FaissVectorStore
#11550 closed
Jun 8, 2024 -
[Documentation]: Llama_Index Vectara AutoRetriever not working based on documentation
#11515 closed
Jun 8, 2024 -
[Feature Request]: MITRE Attack Framework
#11512 closed
Jun 8, 2024 -
[Question]: Keywords extraction in Knowledge graph
#11505 closed
Jun 8, 2024 -
[Question]: How can I set output_parser locally?
#11497 closed
Jun 8, 2024 -
使用HuggingFaceInferenceAPIEmbedding无法连接到api接口
#11495 closed
Jun 8, 2024 -
[Feature Request]: incremental updating in es store
#11472 closed
Jun 8, 2024 -
[Question]: Composability Of Nodes Using MultiModalVectorStoreIndex Class
#11460 closed
Jun 8, 2024 -
[Question]: index.as_retrieve returns None, causing an error
#11455 closed
Jun 8, 2024 -
[Question]: Some questions about the algorithmic aspects of similarity_top_k.
#11429 closed
Jun 8, 2024 -
[Question]:Using semantic router with llamaindex
#11415 closed
Jun 8, 2024 -
[Bug]: AttributeError: 'Vertex' object has no attribute '_chat_client'
#11407 closed
Jun 8, 2024 -
[Bug]: similarity_cutoff, is it working?
#11405 closed
Jun 8, 2024 -
[Question]: Retriever unable to retrieve json data from json file and quesition ?
#11403 closed
Jun 8, 2024 -
[Question]: Can MultiStepQueryEngine use SubQuestionQueryEngine?
#11371 closed
Jun 8, 2024 -
[Question]: Alternatives to MultiModalVectorStoreIndex?
#11357 closed
Jun 8, 2024 -
[Bug]: index.as_chat_engine is throwing error openai.NotFoundError: Error code: 404
#11356 closed
Jun 8, 2024 -
[Question]: Using an LLM hosted using LocalAI to query documents
#11350 closed
Jun 8, 2024 -
[Bug]:
#11348 closed
Jun 8, 2024 -
[Question]: Ingestion Pipeline and KG not utilizing GPU
#11344 closed
Jun 8, 2024 -
[Documentation]: The steps to update ReActAgent prompt have changed from what is documented.
#11331 closed
Jun 8, 2024 -
[Bug]: Validation Error in Bm25 Retreiver
#11319 closed
Jun 8, 2024 -
[Question]: How llama-index can handle a large table?
#11312 closed
Jun 8, 2024 -
[Bug]: End of response stream is of type 'NoneType' using OpenAILike model, resulting in an TypeError
#11289 closed
Jun 8, 2024 -
[Bug]: ContextChatEngine.from_defaults still relies on ServiceContext
#11286 closed
Jun 8, 2024 -
[Bug]: ModuleNotFoundError: No module named 'tree_sitter'
#11273 closed
Jun 8, 2024 -
[Bug]: Possible bug in query pipeline agent notebook?
#11096 closed
Jun 8, 2024 -
[Question]: Is relation between nodes being thrown away when constructing KG using KnowledgeGraphIndex?
#11000 closed
Jun 8, 2024 -
[Bug]: MultiModal tutorial typo
#10757 closed
Jun 8, 2024 -
[Feature Request]: Be able to split text and get the ranges that originated each chunk
#10686 closed
Jun 8, 2024 -
[Feature Request]: Add proper async support
#10590 closed
Jun 8, 2024 -
[Question]: SQLAutoVectorQueryEngine ValueError: Invalid result.ind: -2
#9510 closed
Jun 8, 2024 -
[Question]: Which model do you use to "detect" important tables in a pdf document?
#10239 closed
Jun 8, 2024 -
[Bug]: RedisVectorStore delete_ref_doc doesn't delete all nodes
#9509 closed
Jun 8, 2024 -
Denodo connector for Llama-index
#8150 closed
Jun 8, 2024 -
[Bug]:
#14018 closed
Jun 8, 2024 -
[Feature Request]:
#14011 closed
Jun 8, 2024 -
[Question]: Is it possible to use LlamaIndex ReAct Agent with Citation Query Engine
#11525 closed
Jun 7, 2024 -
[Feature Request]: Incorporate AWS Bedrock agents
#11462 closed
Jun 7, 2024 -
[Bug]: original query_str vs custome_embedding_str is passed to Hybrid search for sparse embedding
#11453 closed
Jun 7, 2024 -
Problems with setting a local emebdding model using HuggingFaceEmbedding
#11446 closed
Jun 7, 2024 -
[Question]: How to adjust the depth and breadth of TreeIndex
#11441 closed
Jun 7, 2024 -
[Bug]: error with guidance library
#11440 closed
Jun 7, 2024 -
[Question]: Agents get stuck
#11433 closed
Jun 7, 2024 -
[Question]: Setting up Index based on tree index builds a hierarchical tree
#11423 closed
Jun 7, 2024 -
[Bug]: Conflicting pydantic versions in llama_index and docarray
#11401 closed
Jun 7, 2024 -
[Question]: What is the advantage of using Retriever Router Query Engine over Router Query Engine?
#11383 closed
Jun 7, 2024 -
[Feature Request]: Enhance .as_retriever() Method for Hybrid Query Mode to Include Nodes with Score = 0
#11372 closed
Jun 7, 2024 -
[Question]: How to use LM_FORMAT_ENFORCER with TreeSummarize
#11369 closed
Jun 7, 2024 -
RagEvaluatorPack : Unable to download LabelledRagDataset from llama-hub on a windows 10 machine
#11349 closed
Jun 7, 2024 -
[Question]: How to guarantee Pydantic Output with open source LLMs such as Zephyr and Mixtral-8x7b
#11345 closed
Jun 7, 2024 -
[Bug]: SentenceSplitter_split crashes on a sequence of 10 MB lower letters
#11341 closed
Jun 7, 2024 -
[Bug]: openai assistant "from_existing" ignores Organization ID
#11299 closed
Jun 7, 2024 -
[Question]: OpenAIAgent changes user query
#13216 closed
Jun 7, 2024 -
[Question]: How to force the LLM to use a tool through the query engine?
#13957 closed
Jun 7, 2024 -
[Question]: Generate Only SQL Query
#13986 closed
Jun 7, 2024 -
[Bug]: KnowledgeGraphIndex not returning triplets in networkx when using documentation example
#13806 closed
Jun 7, 2024 -
[Question]: The retriever failed to fetch the relevant info from chromadb
#13856 closed
Jun 7, 2024 -
[Question]: Why do I keep getting this WARNING?
#13898 closed
Jun 7, 2024 -
[Question]: how does llamaindex support large datasets?
#13987 closed
Jun 6, 2024 -
API key for content summarization
#13984 closed
Jun 6, 2024 -
[Question]: sent-len of sentence-spliter
#13982 closed
Jun 6, 2024
45 Issues opened by 39 people
-
[Bug]: ReplicateError: Unauthenticated
#14106 opened
Jun 12, 2024 -
[Bug]: function_call does not generate langfuse subspans for a custom AsyncBaseTool class
#14097 opened
Jun 12, 2024 -
[Question]: Retriever search depth in a custom node relationship environment
#14096 opened
Jun 12, 2024 -
[Question]: Why does Bedrock prints out prompt and other unnecessary symbols?
#14094 opened
Jun 12, 2024 -
[Bug]: Getting deprecation message for Neo4jPropertyGraphStore
#14093 opened
Jun 12, 2024 -
[Bug]: Nebulagraph - upsert_triplet() function has empty string obj
#14092 opened
Jun 12, 2024 -
[Question]: Further explanation of total embedding token usage
#14090 opened
Jun 12, 2024 -
[Question]: nested agents
#14082 opened
Jun 11, 2024 -
[Question]: Llama Index with local Embedding Model Dont Finish
#14078 opened
Jun 11, 2024 -
[Question]: Metadata filtering in chat engine.
#14075 opened
Jun 11, 2024 -
[Question]: How to use MilvusVectorStore with text_key and additional metadata?
#14074 opened
Jun 11, 2024 -
[Question]: I want to store the chat_history in a postgresql that is installed locally on my machine.
#14073 opened
Jun 11, 2024 -
[Bug]: Query id error while running elasticsearch with same index name
#14070 opened
Jun 11, 2024 -
[Bug]: TreeSummarize Llamacpp llm Requested tokens exceed context window
#14066 opened
Jun 11, 2024 -
[Feature Request]: Azure Serverless Endpoint Support
#14058 opened
Jun 10, 2024 -
[Bug]: refresh_ref_docs() not updating documents
#14057 opened
Jun 10, 2024 -
[Documentation]: Document the pipeline used by NLSQLTableQueryEngine (and potentially other query engines)
#14050 opened
Jun 10, 2024 -
Is there a way for me to enable my LLM agent to write and execute python code in a sandboxed environment?
#14049 opened
Jun 10, 2024 -
[Bug]: VectorIndexAutoRetriever run fail with gpt-4o
#14047 opened
Jun 10, 2024 -
[Question]: Embeddings In ElasticSearch
#14046 opened
Jun 10, 2024 -
[Question]: I want to highlight the souce of extracted data for a pdf, what are the metadata required ?
#14045 opened
Jun 10, 2024 -
[Bug]: `QueryPipeline` only using the `query_str` of the query transform output `QueryBundle`
#14044 opened
Jun 10, 2024 -
[Question]: Graph Data Processing
#14033 opened
Jun 9, 2024 -
[Feature Request] Document Loader for single files: Support for file path along with IO bytes object
#14032 opened
Jun 9, 2024 -
[Question]: Building a chatbot with custom data
#14031 opened
Jun 9, 2024 -
[Question]: Is data shared when creating embeddings or querying?
#14027 opened
Jun 8, 2024 -
Enable Gpu when Generating Sparse vectors with Qdrant hybrid Mode.
#14020 opened
Jun 8, 2024 -
[Bug]: VertexAIVectorStore fails w/ IndexError
#14017 opened
Jun 8, 2024 -
[Bug]: When using HyDE, Langfuse doesn't log trace event
#14016 opened
Jun 8, 2024 -
[Bug]: ChatSummaryMemoryBuffer failed with chat_engine
#14014 opened
Jun 8, 2024 -
[Bug]: async functions do not work..
#14004 opened
Jun 7, 2024 -
[Question]: I want to get the coordinates using Unstructured as the metadata of nodes
#14002 opened
Jun 7, 2024 -
[Question]: SQL query response has 'sql\n' from SQLAutoVectorQueryEngine
#13999 opened
Jun 7, 2024 -
[Bug]: LanceDBVectorStore database size blows up on creation
#13992 opened
Jun 6, 2024 -
[Bug]: MongoDBAtlasVectorSearch & VectorStoreIndex.from_vector_store are not working as expected
#13990 opened
Jun 6, 2024 -
[Question]: How to write production grade code
#13985 opened
Jun 6, 2024 -
[Bug]: System prompt has no effect using Ollama
#13983 opened
Jun 6, 2024 -
Elasticsearch persistence
#13979 opened
Jun 6, 2024 -
response generation issue using elasticsearch
#13977 opened
Jun 6, 2024 -
cv-assistant
#13976 opened
Jun 6, 2024 -
[Question]: Does LLamaIndex retriever implicitly filters/slices data based on metadata?
#13972 opened
Jun 6, 2024 -
Elasticsearch embedding retireval issue
#13971 opened
Jun 6, 2024 -
[Question]: Excessive content returned by the Chat engine, How can I get it to not match so much?
#13965 opened
Jun 6, 2024
81 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.
-
add news retriever
#13934 commented on
Jun 10, 2024 • 6 new comments -
[Bug]: IngestionPipeline Parallel Processing for HuggingFaceEmbedding
#13956 commented on
Jun 7, 2024 • 6 new comments -
[Question]: I want to buid a local multimodal RAG chatbot, but I get error below
#13943 commented on
Jun 7, 2024 • 4 new comments -
[Bug]: Unable to use Seaborn when asking the LLM to graph
#13592 commented on
Jun 12, 2024 • 4 new comments -
[Bug]: KVDocumentStore generates many duplicate Node_IDs in ref_doc_info collection for both Redis and Mongo docstore
#13945 commented on
Jun 7, 2024 • 3 new comments -
[Bug]: ReAct Agent `stream_chat()` does not trigger tool calling, though `chat()` does
#11013 commented on
Jun 11, 2024 • 3 new comments -
Integrations: Upstage Layout Analysis Reader
#13415 commented on
Jun 12, 2024 • 3 new comments -
Add AgentOps integration
#13935 commented on
Jun 7, 2024 • 2 new comments -
LLMTextCompletionProgram: when output long json, it will be error ,
#12395 commented on
Jun 7, 2024 • 2 new comments -
[Core] Omni-Modal Embedding, Vector Index and Retriever
#13551 commented on
Jun 12, 2024 • 2 new comments -
[Bug]: BM25Retriever cannot work on chinese
#13866 commented on
Jun 10, 2024 • 2 new comments -
feat: Add Managed Index for LlamaIndex on Vertex AI for RAG
#13626 commented on
Jun 6, 2024 • 1 new comment -
EntityExtractor
#13774 commented on
Jun 9, 2024 • 1 new comment -
[Question]: Combine/merge multiple VectorStoreIndex directories into a single index for querying
#13264 commented on
Jun 10, 2024 • 1 new comment -
[Bug]: Getting incomplete responses in async mode with anthropic
#9678 commented on
Jun 10, 2024 • 1 new comment -
[Bug]: RAPTOR failed due to duplicated Document ID
#11594 commented on
Jun 10, 2024 • 1 new comment -
[Bug]: MarkdownElementNodeParser:pandas.errors.ParserError: Error tokenizing data. C error: EOF inside string starting at row 0
#13942 commented on
Jun 10, 2024 • 1 new comment -
[Feature Request]: Multiple vector stores shared accross the same document store namespace, while using refresh_ref_docs
#12086 commented on
Jun 11, 2024 • 1 new comment -
[Bug]: LlamaIndex taking too long i.e like about 20-30 minutes to bring back a response.
#10984 commented on
Jun 11, 2024 • 1 new comment -
[Bug]: "POST /generate HTTP/1.1" 404 Not Found
#13041 commented on
Jun 12, 2024 • 1 new comment -
llamaindex vllm error
#12955 commented on
Jun 12, 2024 • 1 new comment -
How I measure the tokens for Chain of table code snippet?
#12588 commented on
Jun 12, 2024 • 1 new comment -
[Feature Request]: Track OpenAI LLM Usage Cost
#13443 commented on
Jun 12, 2024 • 1 new comment -
[Bug]: AttributeError: 'AzureOpenAIMultiModal' object has no attribute 'predict'
#13958 commented on
Jun 6, 2024 • 1 new comment -
[Question]: How to get nodes from ES ?
#13656 commented on
Jun 6, 2024 • 1 new comment -
[Bug]: custom_llm_provider not honored in litellm.py
#13814 commented on
Jun 6, 2024 • 1 new comment -
[Feature Request]: default to pydantic v2
#13477 commented on
Jun 6, 2024 • 1 new comment -
[Question]: Run multimodal LLM locally
#13606 commented on
Jun 7, 2024 • 1 new comment -
[Question]: Multi modal rag
#12039 commented on
Jun 7, 2024 • 1 new comment -
[Bug]: LanceDBVectorStore doesn't sanitize data well enough for lance's liking
#11788 commented on
Jun 8, 2024 • 0 new comments -
[Bug]: Query Engine fails to query with similarity_top_k greater than 15
#11839 commented on
Jun 11, 2024 • 0 new comments -
[Bug]: condense question missing from traces
#11860 commented on
Jun 11, 2024 • 0 new comments -
[Feature Request]: In Postgres Keyword Search, give user flexibility to select between match all words or any words
#10580 commented on
Jun 11, 2024 • 0 new comments -
Display source node
#11690 commented on
Jun 11, 2024 • 0 new comments -
[Feature Request]: Support for structured text generation via outlines lib.
#11824 commented on
Jun 11, 2024 • 0 new comments -
[Question]: Build SummaryIndex from existing vector store's documents?
#11757 commented on
Jun 6, 2024 • 0 new comments -
[Question]: What is the difference between PDFReader and PyMuPDFReader
#11729 commented on
Jun 6, 2024 • 0 new comments -
[Question]: Why DocxReader doesn't split the file to pages?
#11730 commented on
Jun 6, 2024 • 0 new comments -
[Question]: Agent using multiple indices of the same documents to answer different types of questions
#11758 commented on
Jun 6, 2024 • 0 new comments -
[Feature Request]: Streaming Support for Async Query Engine Queries
#11755 commented on
Jun 6, 2024 • 0 new comments -
[Question]: When using TreeIndex, will all the leaf nodes be recursively traversed to select the most relevant one?
#11878 commented on
Jun 12, 2024 • 0 new comments -
[Feature Request]: Progress bar for treeSummarize / compact_and_refine summarizer
#11908 commented on
Jun 12, 2024 • 0 new comments -
[Bug]: WikipediaReader cannot handle with pages that contain url encoding.
#11905 commented on
Jun 12, 2024 • 0 new comments -
[Bug]: Konko integration does not correctly pass the api key when making requests.
#11917 commented on
Jun 12, 2024 • 0 new comments -
[Question]: Azure AI search index size is 0 ?
#11897 commented on
Jun 12, 2024 • 0 new comments -
[Bug]: Token counter not working for RaptorPack
#11828 commented on
Jun 12, 2024 • 0 new comments -
[Question]: Using react agent with sql query tool and vector query index but it is not giving proper response for vector query index
#11906 commented on
Jun 12, 2024 • 0 new comments -
[Question]: Agents and chat engine
#11882 commented on
Jun 12, 2024 • 0 new comments -
[Bug]: loading docx file with SimpleDirectoryReader : File is not a zip file. Skipping...
#11859 commented on
Jun 12, 2024 • 0 new comments -
[Question]: submit form with details from user
#11849 commented on
Jun 12, 2024 • 0 new comments -
IndexError in _extract_rel_text_keywords method of KGTableRetriever class
#11651 commented on
Jun 12, 2024 • 0 new comments -
[Question]: Way to remove some metadata values from vector db (PineconeVectorStore)
#11750 commented on
Jun 6, 2024 • 0 new comments -
LlamaCPP
#11692 commented on
Jun 7, 2024 • 0 new comments -
[Question]: How about supporting to generate sparse vector using TextEmbeddingsInference?😢
#11760 commented on
Jun 7, 2024 • 0 new comments -
[Documentation]: emphasise the mechanism behind the json query engine to let user easily know the possible failure reason
#11773 commented on
Jun 7, 2024 • 0 new comments -
[Question]: Multi modal rag implementation for pdf text and images
#11743 commented on
Jun 8, 2024 • 0 new comments -
Azure OpenAI Questions
#11451 commented on
Jun 8, 2024 • 0 new comments -
[Question]: RAG - how to deal with numerical data
#11648 commented on
Jun 7, 2024 • 0 new comments -
[Question]: Cohere Rerank Vs LLMRerank
#11801 commented on
Jun 9, 2024 • 0 new comments -
[Feature Request]: Prefilled LLM output for controlled generation
#11786 commented on
Jun 9, 2024 • 0 new comments -
Google reader and Notion reader are not working
#3777 commented on
Jun 9, 2024 • 0 new comments -
[Question]: Using agents for multiple documents
#11735 commented on
Jun 6, 2024 • 0 new comments -
[Bug]: Not able to install LLaMa Index on SageMaker Notebook in AWS
#11448 commented on
Jun 6, 2024 • 0 new comments -
[Feature Request]: OneNote Integration
#11811 commented on
Jun 10, 2024 • 0 new comments -
[Question]: AzureAISearchVectorStore and Advanced Retrieval Techniques
#11808 commented on
Jun 10, 2024 • 0 new comments -
[Question]: Connection error
#11802 commented on
Jun 10, 2024 • 0 new comments -
[Question]: Can we let the LLM automatically identify whether RAG should be used in different senarios?
#11573 commented on
Jun 10, 2024 • 0 new comments -
[Feature Request]: Add parallel LLM call to _run_critic function of self_rag pack
#11815 commented on
Jun 10, 2024 • 0 new comments -
[Bug]: Query Engine seems to be using wrong syntax.
#10324 commented on
Jun 10, 2024 • 0 new comments -
[Bug]: TemplateError: Conversation roles must alternate user/assistant/user/assistant/...
#11731 commented on
Jun 6, 2024 • 0 new comments -
[Bug]: raise JsonPathLexerError('Unexpected EOF in string literal or identifier')
#11747 commented on
Jun 6, 2024 • 0 new comments -
[Question]: Reciprocal Rerank Fusion Retriever not compatible to OpenSearch
#11714 commented on
Jun 6, 2024 • 0 new comments -
[Bug]: KnowledgeGraphQueryEngine fails with AttributeError
#11034 commented on
Jun 11, 2024 • 0 new comments -
[Bug]: ValueError: Input keys {'query_str', 'table_schema_objs'} contain keys not in required or optional keys {'table_schema_objs'}
#10790 commented on
Jun 6, 2024 • 0 new comments -
[Bug]: Error when storing to mongo DB index and document store for Knowledge Graph
#9546 commented on
Jun 6, 2024 • 0 new comments -
[Bug]: RAPTOR query engine not working with Opensearch
#11718 commented on
Jun 6, 2024 • 0 new comments -
[Question]: Questions about generation of finetuning dataset and a def of llm
#11853 commented on
Jun 11, 2024 • 0 new comments -
[Feature Request]: LlamaParse + SimpleDirectoryReader output 1 document,if can output markdown by pages
#11850 commented on
Jun 11, 2024 • 0 new comments -
[Question]: Best way to read markdown docs with readers, parsers and splitters and standardization between them
#11865 commented on
Jun 11, 2024 • 0 new comments -
[Bug]: module 'google.generativeai' has no attribute 'aget_embedding'
#11864 commented on
Jun 11, 2024 • 0 new comments -
[Question]: What is the best open source model for VectorIndexAutoRetriever
#11833 commented on
Jun 11, 2024 • 0 new comments