Insights: run-llama/llama_index
Overview
Could not load contribution data
Please try again later
2 Releases published by 1 person
-
v0.10.35 2024-05-07 (v0.10.35)
published
May 7, 2024 -
v0.10.36
published
May 9, 2024
65 Pull requests merged by 40 people
-
bump rerank versions
#13465 merged
May 13, 2024 -
gpt-4o support
#13463 merged
May 13, 2024 -
Fix the RAG fusion pipeline
#13413 merged
May 13, 2024 -
fix: update `OpenAIAssistantAgent` to use `attachments` rather than `file_ids`
#13341 merged
May 13, 2024 -
Add New Integration for DeepInfra Embedding Model
#13323 merged
May 13, 2024 -
Created an integration to use llms built for Apple's MLX library
#13231 merged
May 13, 2024 -
edit llama3 notebooks
#13456 merged
May 13, 2024 -
fix: Corrected connection parameters in connections.connect()
#13448 merged
May 13, 2024 -
update: bump version!
#13445 merged
May 12, 2024 -
fix: user_message does not exist bug
#13432 merged
May 11, 2024 -
Fix AzureAiSearchVectorStore metadata f-string
#13435 merged
May 11, 2024 -
llama3 groq cookbook
#13436 merged
May 11, 2024 -
nit: add colab badge
#13433 merged
May 11, 2024 -
add llama3 cookbook
#13427 merged
May 11, 2024 -
Add nb for RBC talk/workshop
#13430 merged
May 11, 2024 -
Adds Unit and Integration tests for MongoDBAtlasVectorSearch
#12854 merged
May 10, 2024 -
Update `llama-index-llms-huggingface` dependency
#13420 merged
May 10, 2024 -
Update ZCP Managed Index & Milvus Index demos
#13170 merged
May 10, 2024 -
Add support for Relyt as a Vector Store
#13075 merged
May 10, 2024 -
Implement async methods in RedisKVStore
#12943 merged
May 10, 2024 -
Update multi_modal_rag_evaluation.ipynb
#13418 merged
May 10, 2024 -
vbump cohere llm
#13417 merged
May 10, 2024 -
[Dynamic Session] Fixed some indexing issue and resolved a runtime error message
#13414 merged
May 10, 2024 -
Fix Cohere Rerank bug
#13410 merged
May 10, 2024 -
Fix retriever integration
#13409 merged
May 10, 2024 -
Add Dynamic Sessions Integration
#13342 merged
May 9, 2024 -
fix: missing authorized_user_info check on GoogleDriveReader
#13394 merged
May 9, 2024 -
This example is about Llama 3, not 2
#13403 merged
May 9, 2024 -
Await Firestores's AsyncDocumentReference before converting to dict
#13386 merged
May 9, 2024 -
import missing response type
#13382 merged
May 9, 2024 -
add dynamic model listing support
#13398 merged
May 9, 2024 -
Add CallbackManager to MultiModalLLM
#13400 merged
May 9, 2024 -
Rename OPENAI_API_TOKEN to OPENAI_API_KEY
#13402 merged
May 9, 2024 -
Update tests for Github readers
#13387 merged
May 9, 2024 -
[version] bump version to 0.10.36
#13396 merged
May 9, 2024 -
Pebblo-Llama PebbloSafeReader
#13128 merged
May 9, 2024 -
Call Cohere RAG inference with `documents` argument
#13196 merged
May 9, 2024 -
Kdb.ai
#13194 merged
May 9, 2024 -
Add VectorStore integration for alibaba cloud opensearch vector service
#13286 merged
May 9, 2024 -
Add `start_char_idx` and `end_char_idx`: `MarkdownElementNodeParser`
#13377 merged
May 9, 2024 -
udpates to multion tool to align with updated api/sdk
#13373 merged
May 8, 2024 -
Update WeaviateVectorStore to use weaviate client version to v4
#13229 merged
May 8, 2024 -
use handlers from global default
#13368 merged
May 8, 2024 -
Fix bug where PDFReader ignores extra_info
#13369 merged
May 8, 2024 -
add sync httpx client support for openai/azure
#13370 merged
May 8, 2024 -
Add ``fail_on_http_error`` arg to github repository reader.
#13366 merged
May 8, 2024 -
feat: add attribution tag for pinecone
#13329 merged
May 8, 2024 -
set default max_tokens to 1024
#13371 merged
May 8, 2024 -
Fix hidden temp directory issue for arxiv reader
#13351 merged
May 8, 2024 -
fix truncate passing for aget_query_embedding and get_text_embedding_batch
#13367 merged
May 8, 2024 -
Add Vespa Vector Store to module guide
#13326 merged
May 8, 2024 -
Fix add llama-3 models to Anyscale class
#13336 merged
May 8, 2024 -
feature: add missing openai model token context
#13337 merged
May 8, 2024 -
Fix docs: replace borken notion links
#13346 merged
May 8, 2024 -
patch async utils
#13349 merged
May 8, 2024 -
v0.10.35
#13345 merged
May 7, 2024 -
add docstrings to some base index methods so that they show up in api…
#13338 merged
May 7, 2024 -
fix from_defaults erasing summary buffer history
#13325 merged
May 7, 2024 -
Fix asyncio.run() in async context.
#13309 merged
May 7, 2024 -
Update MarkdownReader to parse text before first header
#13327 merged
May 7, 2024 -
add nvidia nim llm support
#13176 merged
May 7, 2024 -
fix async streaming in condense question
#13306 merged
May 7, 2024 -
fix: fix encoding type access in JinaEmbeddings
#13315 merged
May 7, 2024 -
Remove Global Logging Config from All Production Files
#13321 merged
May 7, 2024 -
Handle ValueError in extract_table_summaries
#13318 merged
May 7, 2024
21 Pull requests opened by 19 people
-
feat: Azure Table Storage integration
#13335 opened
May 7, 2024 -
[WIP] implement vector memory
#13352 opened
May 8, 2024 -
Add dashscope rerank for postprocessor
#13353 opened
May 8, 2024 -
Add support for Vespa Node's and indexing with additional fields
#13356 opened
May 8, 2024 -
implement any and all metadata filters for weaviate vector store
#13365 opened
May 8, 2024 -
Add Alibaba cloud Bailian index intergration
#13378 opened
May 9, 2024 -
Add support for prompt kwarg
#13405 opened
May 9, 2024 -
Implement BaseFilesystemReader in S3Reader and SharePoint Reader
#13408 opened
May 10, 2024 -
Integrations: Upstage Layout Analysis Reader
#13415 opened
May 10, 2024 -
integrations: LanceDB update
#13416 opened
May 10, 2024 -
Avoid unexpected error when stream chat doesn't yield
#13422 opened
May 10, 2024 -
Cassandra database tool
#13423 opened
May 10, 2024 -
Add BaseFilesystemReader interface + implement in SimpleDirectoryReader
#13424 opened
May 11, 2024 -
VectorStore -> BasePydanticVectorStore, also get/delete_nodes, clear()
#13439 opened
May 11, 2024 -
Remove "Truncate" parameter from Bedrock Cohere invoke model request.
#13442 opened
May 12, 2024 -
Integration: Improve Chunk splitter + Relationships between chunks for python files / repositories
#13446 opened
May 12, 2024 -
Trafilatura kwargs and progress bar for trafilatura web reader
#13454 opened
May 12, 2024 -
ReAct output parser changes
#13459 opened
May 13, 2024 -
Add `image_documents` at call time for `MultiModalLLMCompletionProgram`
#13467 opened
May 13, 2024 -
integrations: Update UpTrain Callback Handler to support the new UpTrain evaluation schema and dashboard
#13479 opened
May 14, 2024
70 Issues closed by 20 people
-
[Question]: Automerging index with MongoDB
#13472 closed
May 14, 2024 -
[Bug]: gpt-4o not supported
#13466 closed
May 13, 2024 -
[Question]: Update metadata of an existing node
#10460 closed
May 13, 2024 -
[Bug]: recursive retriever + docstore + upsert pipeline = lost nodes
#10454 closed
May 13, 2024 -
[Bug]: SQL Engine not responding with fetched results
#10338 closed
May 13, 2024 -
[Bug]: OpenAIAssistantAgent now breaks because of OpenAI api changes
#12968 closed
May 13, 2024 -
[Question]: AttributeError: 'NoneType' object has no attribute 'search'
#13391 closed
May 13, 2024 -
[Question]: Dumb llama3 with llamaindex, but not with ollama
#13419 closed
May 13, 2024 -
[Bug]: LocalTensorRTLLM not loading without any debug.
#10444 closed
May 12, 2024 -
[Question]:How to properly setup top agent for Multi Document Agent RAG?
#10442 closed
May 12, 2024 -
[Question]: SimpleDirectoryReader failed to load 1 file (but other 100 files are fine)
#13438 closed
May 12, 2024 -
[Bug]: Chatml messages_to_prompt
#13434 closed
May 11, 2024 -
[Feature Request]: Hybrid retrieval support for ElasticSearch VectorStrore.
#10430 closed
May 11, 2024 -
[Question]: how do I specify the number of threads for llama
#10428 closed
May 11, 2024 -
[Question]: AnswerRelevancyEvaluator() and ContextRelevancyEvaluator() result and document are unclear.
#10410 closed
May 11, 2024 -
[Question]: Is there a way to change response_mode in response_synthesizer dynamically?
#13429 closed
May 11, 2024 -
[Bug]: AttributeError: 'tuple' object has no attribute 'score'
#13364 closed
May 11, 2024 -
[Bug]: huggingface embedding model failed with LLamaIndex version 0.9.41, 0.9.40, and even 0.9.33
#10403 closed
May 10, 2024 -
[Question]: How to do Multi-Document RAG with Document Summary Index?
#10389 closed
May 10, 2024 -
[Question]: How to generate responses even when there is no information?
#10378 closed
May 10, 2024 -
[Question]: How can attempting mathematical calculations be prevented?
#13334 closed
May 10, 2024 -
[Question]: How to create a multiDocagent using function call with bedrock llms
#13381 closed
May 10, 2024 -
[Bug]: FirestoreKVStore's aget_all raises AttributeError when collection is not empty
#13385 closed
May 9, 2024 -
[Bug]: no callback_manager field in OpenAIMultiModal?
#13136 closed
May 9, 2024 -
[Bug]: Some notebooks set OPENAI_API_TOKEN instead of OPENAI_API_KEY
#13401 closed
May 9, 2024 -
[Feature Request]: HuggingFaceEmbedding use_fp16=true
#10392 closed
May 9, 2024 -
[Question]: Suddenly slow indexing
#10379 closed
May 9, 2024 -
[Feature Request]: SyneTuneParameterTuner
#10362 closed
May 9, 2024 -
[Bug]: IngestionPipeline 0.9.36 pipline.arun to Redis Not implemented Error
#10248 closed
May 9, 2024 -
[Documentation]: notebook docs/examples/prompts/prompts_rag.ipynb not working
#13390 closed
May 9, 2024 -
[Bug]: demo for pinecone support broken
#13347 closed
May 9, 2024 -
[Feature Request]: Update llama-index-vector-stores-weaviate to weaviate-client version 4.x
#11745 closed
May 8, 2024 -
[Bug]: Seems like setting `Settings.callback_manager` has no effect in QueryPipelines
#13354 closed
May 8, 2024 -
[Bug]: PDFReader doesn't add `extra_info` into metadatas if `return_full_document` is `True`
#13290 closed
May 8, 2024 -
[Bug]: openai http_client type error
#13357 closed
May 8, 2024 -
[Feature Request]: Add `fail_on_http_error` boolean to Github readers
#12649 closed
May 8, 2024 -
[Feature Request]: Add attribution tag to pinecone vector store
#13328 closed
May 8, 2024 -
[Feature Request]: combine indexes or chat over multiple indexes
#10374 closed
May 8, 2024 -
[Question]: Clarification on Behavior of VectorStoreIndex.from_vector_store with Multiple Indices
#10372 closed
May 8, 2024 -
[Question]: pipline() unable to parse Chinese filename
#10369 closed
May 8, 2024 -
[Question]: why node types influence the behavior of similarity_top_k?
#10356 closed
May 8, 2024 -
Getting error when PandasQueryEngine called with BARD "Gemini model".
#10345 closed
May 8, 2024 -
[Bug]: BM25 retriever not working just with indexes
#10344 closed
May 8, 2024 -
[Bug]: Arxiv paper reader failing to find files.
#13165 closed
May 8, 2024 -
[Question]: How to classify the data using llama-index(using LLM)
#13355 closed
May 8, 2024 -
[Question]: How exactly do the title, keyword, summary and question answer metadata extractors work?
#13225 closed
May 8, 2024 -
[Question]: How do you correctly load MultiModalVectorStoreIndex from persist directory?
#13102 closed
May 8, 2024 -
[Bug]: Join queries generate by LLM are not handled with schema appropriately
#13276 closed
May 7, 2024 -
Agent Translating to sql query 100% correct but None.H returned for query result [Bug]:
#13324 closed
May 7, 2024 -
[Bug]: log formatting issue in case where _node_content is empty
#11283 closed
May 7, 2024 -
[Bug]: Not able to store Nodes and Objects together in Weaviate
#11473 closed
May 7, 2024 -
[Documentation]: KnowledgeGraphIndex docs is missing docs about parent class BaseIndex[KG]
#10474 closed
May 7, 2024 -
[Question]: Does `gpt-4-32k` still exist and should be in `llama_index` code?
#13339 closed
May 7, 2024 -
[Question]: Redis Chat Store with ChatSummaryMemoryBuffer guide
#13308 closed
May 7, 2024 -
[Bug]: Using MarkdownReader will lose the content before the first `#`.
#13283 closed
May 7, 2024 -
[Bug]: CondenseQuestionChatEngine astream_chat does not handle AsyncStreamingResponse
#13305 closed
May 7, 2024 -
[Question]: Why model `gpt-4-1106-vision-preview` is not present?
#13333 closed
May 7, 2024 -
[Question]: How to print the final prompt after all processing
#13310 closed
May 7, 2024 -
[Bug]: ValueError is not handled in extract_table_summaries
#13316 closed
May 7, 2024 -
[Feature Request]: [Proposal] Integrate Replit ModelFarm with LlamaIndex Python
#10359 closed
May 7, 2024 -
[Question]: Using query_engine.query() failed as socket cannot be created
#10332 closed
May 7, 2024 -
[Question]: load one document size > 20 M, I got the query result very slow. anyway know the reason?
#10169 closed
May 7, 2024 -
[Bug]: not skipping `test_s3_kvstore` in CI
#8264 closed
May 7, 2024 -
[Bug]: Incorrect response from Binary Evaluation (ResponseEvaluator)
#7883 closed
May 7, 2024 -
[Bug]: System prompts not propogating in a query pipeline.
#13311 closed
May 7, 2024 -
[Question]: RateLimitError: Error code: 429
#13278 closed
May 7, 2024 -
[Question]: VespaVectorStore customization for custom nodes
#13319 closed
May 7, 2024
54 Issues opened by 48 people
-
[Question]: RAG on persistent VectoreStore with local Huggingface LLM
#13478 opened
May 14, 2024 -
[Feature Request]: default to pydantic v2
#13477 opened
May 14, 2024 -
[Question]: Inconsistencies when providing answer using contextchatengine
#13475 opened
May 14, 2024 -
[Question]: MongoDB atlas vector search vs ChromaDB
#13474 opened
May 14, 2024 -
[Question]: How to Achieve Parallel processing in SentenceSplitter
#13473 opened
May 14, 2024 -
[Question]: How can we store ChatEngineInstance and ChatMemoryBuffer in a centrailized storage.
#13471 opened
May 14, 2024 -
[Bug]: segmentation fault
#13470 opened
May 14, 2024 -
SummaryModule.__init__() got an unexpected keyword argument 'num_workers'[Question]:
#13469 opened
May 13, 2024 -
[Documentation]: Redis Docstore+Index Store Demo code is incomplete/broken
#13464 opened
May 13, 2024 -
[Question]: Ingestion pipeline duplicates with Postgres
#13461 opened
May 13, 2024 -
[Feature Request]: Allow RagEvaluatorPack to use HuggingFace/Open Source Embeddings
#13460 opened
May 13, 2024 -
[Question]: Similarity_Top_K returns fewer nodes than requested
#13457 opened
May 13, 2024 -
[Question]: How can I improve the accuracy of RAG.
#13455 opened
May 13, 2024 -
[Bug]: Issues with llama_index.core
#13453 opened
May 12, 2024 -
should I add the example notebook to the docs?[Question]:
#13452 opened
May 12, 2024 -
[Bug]: Unable to delete pinecone stored vectors with new pinecone serverless index architecture
#13451 opened
May 12, 2024 -
[Bug]: callback managers not set in post processors correctly.
#13450 opened
May 12, 2024 -
[Question]: Debugging ReActAgent which superficially calls QueryEngineTool?
#13449 opened
May 12, 2024 -
[Bug]: MilvusVectorStore failed to connect non-localhost uri when enable_sparse is True
#13447 opened
May 12, 2024 -
[Feature Request]: Allow trafilatura kwargs for additional options
#13444 opened
May 12, 2024 -
[Feature Request]: Track OpenAI LLM Usage Cost
#13443 opened
May 12, 2024 -
[Bug]: LLAMA INDEX is becoming a Dependency Hell itself
#13441 opened
May 11, 2024 -
GPU OOM during the embedding process
#13428 opened
May 11, 2024 -
[Bug]: Using flask restful server and got [Session and connector has to use same event loop] error
#13426 opened
May 11, 2024 -
[Bug]: DEFAULT_RESPONSE_SYNTHESIS_PROMPT missing
#13425 opened
May 11, 2024 -
[Documentation]: DOI not found
#13406 opened
May 9, 2024 -
[Bug]: llm_completion_callback ignores prompt keyword argument
#13404 opened
May 9, 2024 -
[Bug]: JSONalyzeQueryEngine predict() missing 1 required positional argument: 'text'
#13399 opened
May 9, 2024 -
[Question]: Got empty response when using KnowledgeGraphRAGRetriever with Neo4jGraphStore
#13397 opened
May 9, 2024 -
[Bug]: GoogleDriveReader Must specify `client_config` or `service_account_key`
#13393 opened
May 9, 2024 -
[Question]: why PostgresKVStore table class does not match my postgres vector table schema?
#13392 opened
May 9, 2024 -
[Question]: BM25 Retriever takes long time to load with docstore are its parameter
#13389 opened
May 9, 2024 -
[Feature Request]: Please support stream_chat for vllm
#13388 opened
May 9, 2024 -
[Question]: Chat engine takes long time to generate output for the first query
#13384 opened
May 9, 2024 -
[Bug]: Code in Guidance Pydantic Program doc not working
#13379 opened
May 9, 2024 -
[Bug]: Bedrock Cohere embeddings are not working as expected.
#13376 opened
May 8, 2024 -
[Question]: Is `llama_index` thead-safe?
#13375 opened
May 8, 2024 -
[Question]: How can i get all nodes from the PGVectorDB?
#13363 opened
May 8, 2024 -
[Bug]: Marvin Metadata Extractor Demo code not working
#13360 opened
May 8, 2024 -
use route query engine : http pool time out error
#13359 opened
May 8, 2024 -
[Bug]: OpenSearch ConnectionError(Timeout context manager should be used inside a task)
#13358 opened
May 8, 2024 -
[Feature Request]: Add support for IN filter in weaviate
#13344 opened
May 7, 2024 -
[Question]: My Model won't follow my instructions at all
#13343 opened
May 7, 2024 -
[Question]: Missing async methods for RedisDocumentStore
#13331 opened
May 7, 2024 -
Multiple Metadata filters are not working after version upgradation
#13322 opened
May 7, 2024 -
[Question]: Llama-3-8b-instruct with llama.cpp
#13320 opened
May 7, 2024
61 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.
-
SecGPT - LlamaIndex Integration
#13127 commented on
May 12, 2024 • 17 new comments -
Contribute the WordLift Vector Store
#13028 commented on
May 13, 2024 • 5 new comments -
[Question]: Why indexing so slow?
#13313 commented on
May 7, 2024 • 4 new comments -
[Question]: How can I use SimpleChatStore to keep a conversation record Germanently?
#13314 commented on
May 7, 2024 • 4 new comments -
Add batch mode to QueryPipeline
#13203 commented on
May 11, 2024 • 4 new comments -
segmentation fault when using HuggingFaceEmbedding
#9949 commented on
May 13, 2024 • 4 new comments -
[Bug]: Not providing a model for the AzureOpenAI llm causes unexpected context size
#13259 commented on
May 10, 2024 • 3 new comments -
[Question]: How to use LabelledRagDataset with RetrieverEvaluator or BatchEvalRunner
#10445 commented on
May 9, 2024 • 2 new comments -
Trying to Create ReACT Agent using Mistral LLM using HuggingFace Inference API but getting error: NotImplementedError: Messages passed in must be of odd length.
#13288 commented on
May 9, 2024 • 2 new comments -
[Bug]: Multiple MetaDataFilters not working even with a condition set.
#10557 commented on
May 8, 2024 • 2 new comments -
[Question]: trust_remote_code=True
#10373 commented on
May 9, 2024 • 2 new comments -
[Bug]: Cohere astream_chat() doesn't work with await
#12841 commented on
May 12, 2024 • 2 new comments -
[Bug]: KnowledgeGraphQueryEngine fails with AttributeError
#11034 commented on
May 13, 2024 • 2 new comments -
[Bug]: Unable to view token counts from Bedrock LLM instance and phoenix Observability
#13046 commented on
May 8, 2024 • 2 new comments -
[Question]: Does agent creation reset memory?
#13312 commented on
May 7, 2024 • 2 new comments -
Llama Tonic : Transcribe
#13137 commented on
May 9, 2024 • 2 new comments -
Integrations: upstage LLM and Embeddings
#13193 commented on
May 11, 2024 • 2 new comments -
[Bug]: UnboundLocalError: cannot access local variable 'x' where it is not associated with a value
#13133 commented on
May 13, 2024 • 2 new comments -
[Bug]: 【Urgent】【Azure OpenAI Embeddings】TypeError: 'NoneType' object is not iterable
#9611 commented on
May 12, 2024 • 1 new comment -
[Feature Request]: Support Multiple Embeddings per Node
#10486 commented on
May 12, 2024 • 1 new comment -
[Question]: Hybrid search?
#12381 commented on
May 12, 2024 • 1 new comment -
[Bug]: Bedrock Integration with Claude3 fails
#11739 commented on
May 11, 2024 • 1 new comment -
Multimodal Retriever is not retrieving right documents with OPENclip embedding models.
#10546 commented on
May 11, 2024 • 1 new comment -
[Bug]: Error when set ''use_async=True'' when using SubQuestionQueryEngine
#10440 commented on
May 8, 2024 • 1 new comment -
Query a vector database against one question to return nodes, then query llm with another question against those nodes.
#13268 commented on
May 13, 2024 • 1 new comment -
[Feature Request]: Add additional metrics to METRIC_REGISTRY for Retrieval and support for different K-s
#11030 commented on
May 13, 2024 • 1 new comment -
[Bug]: LlamaIndex taking too long i.e like about 20-30 minutes to bring back a response.
#10984 commented on
May 13, 2024 • 1 new comment -
[Bug]: Getting incomplete responses in async mode with anthropic
#9678 commented on
May 13, 2024 • 1 new comment -
[Bug]: Extension to 10548
#10550 commented on
May 13, 2024 • 1 new comment -
[Question]: Chat Engines don't support kwargs for chat methods?
#8886 commented on
May 13, 2024 • 1 new comment -
[Question]: Analyze a image with GPT4 Vision?
#12978 commented on
May 13, 2024 • 1 new comment -
[Bug]: cannot use Azure OpenAI with FnRetrieverOpenAIAgent throws LocalProtocolError
#10915 commented on
May 13, 2024 • 1 new comment -
Fix errors because of mix indentation
#13274 commented on
May 8, 2024 • 1 new comment -
Integrate VectorStore from Elasticsearch client
#13291 commented on
May 13, 2024 • 1 new comment -
[Bug]: PandaQueryEngine response
#10498 commented on
May 8, 2024 • 1 new comment -
[Question]: Returning more source nodes
#10160 commented on
May 8, 2024 • 1 new comment -
[Question]: How to change the query engines used in a query_pipeline
#10175 commented on
May 8, 2024 • 1 new comment -
[Question]: I have gpu layers set to 0 but it still tries to use my gpu and runs out of memory. how do I limit it to cpu inference
#10429 commented on
May 8, 2024 • 1 new comment -
[Bug]: Interrupted OpenAiAgent Streaming using K8s and NGINX
#10478 commented on
May 7, 2024 • 1 new comment -
[Bug]: AttributeError: 'LangChainLLM' object has no attribute '_llm'.
#10469 commented on
May 7, 2024 • 1 new comment -
[Feature Request]: Customize OpenAIAssistantAgent
#10538 commented on
May 9, 2024 • 1 new comment -
[Question]: How to speed up index loading time
#9019 commented on
May 9, 2024 • 1 new comment -
[Feature Request]: Add field for document name in LabelledRagDataset
#10518 commented on
May 9, 2024 • 1 new comment -
[Question]: Getting ORA-00933: SQL command not properly ended
#10394 commented on
May 7, 2024 • 1 new comment -
[Bug]: "AttributeError: 'LangchainEmbedding' object has no attribute '_langchain_embedding'
#10475 commented on
May 9, 2024 • 1 new comment -
[Bug]: How to chain multiple QueryEngines
#10480 commented on
May 7, 2024 • 1 new comment -
[Bug]: map_httpcore_exceptions while invoking query_engine.query in colab
#12670 commented on
May 10, 2024 • 1 new comment -
[Bug]: Elasticsearch index creation
#10109 commented on
May 10, 2024 • 1 new comment -
[Feature Request]: Allow for docstore batch insertions
#10437 commented on
May 10, 2024 • 1 new comment -
[Question]: How do I dynamically choose how many nodes to retrieve during query time?
#10521 commented on
May 10, 2024 • 1 new comment -
[Question]: Bedrock LLMs async
#10714 commented on
May 11, 2024 • 1 new comment -
[Question]: Can you help me design the agent RAG system?
#10483 commented on
May 7, 2024 • 0 new comments -
[Question]: Testing of Text to SqL
#13317 commented on
May 7, 2024 • 0 new comments -
[Feature Request]: Support `acomplete` method at `Vllm` class.
#10496 commented on
May 8, 2024 • 0 new comments -
[Feature Request]: Don't force aggregation of embedding strings
#10497 commented on
May 8, 2024 • 0 new comments -
[Feature Request]: multiple value filter on same key in mongoDB vector store.
#13272 commented on
May 9, 2024 • 0 new comments -
[Feature Request]: Support metadata on queryEngine, invocations - make them available to the callback system
#10532 commented on
May 9, 2024 • 0 new comments -
[Bug]: OutputParserException: Failed to parse pydantic object from guidance program
#9414 commented on
May 9, 2024 • 0 new comments -
[Question]: Re-implement `print_text` is a more Pythonic `logging` interface?
#10567 commented on
May 12, 2024 • 0 new comments -
[Code smell]: `_extract_reasoning_step` should have returned `current_reasoning` as an `Optional[...]` instead of a `List[...]`
#10568 commented on
May 12, 2024 • 0 new comments -
[Question]: Is it possible to get the same output whenever I pass the same input?
#10560 commented on
May 11, 2024 • 0 new comments