Hi, I was trying to follow this tutorial to build a RAG system with my excel file. https://github.com/run-llama/llama_parse/blob/main/examples/excel/o1_excel_rag.ipynb However, when running to nodes = node_parser.get_nodes_from_documents(documents[:2]), it returns an error: ModuleNotFoundError: No module named 'pandas.core.methods.to_dict'. Does anyone have an idea about this issue?

Hi, does anyone happen to know if the AWS OpenSearch can be used as a vector store? If so, does LlamaIndex support it?

Hi guys, I am building a chatbot using OpenAIAssistantAgent but it takes 10+ seconds to generate an answer. Is there any way to improve the speed of response?

Hi guys, I am building a chatbot with RetrieverQueryEngine, which can talk with my documents. Is it possible to add the chat history as 'context' so that the chat bot can answer the question based on conversation memory ?

Hi guys, i am using ReActAgent with retriever engine to build a chat bot. However i got the "ValueError: Reached max iterations." error when running the reactAgent. Does anybody happen to know how can i fix it? Thanks!

Hi all, I am using bge-small embedding model to do the embeddings for my documents, and want to use PGVectorStore to store the vectors (embed_dim=384). The challenge i am having now is that: DataError: (psycopg2.errors.DataException) expected 1536 dimensions, not 384 .

Hi all, when using HuggingFaceLLM to call Llama3, is there a way to dowload the model to the local, or somewhere in AWS?

Hi all, I used to use the VectorStoreIndex.from_documents to create index and save them into the PGVectorStore. When creating the index, I used the serviceContext to configure the chunk size and chunk overlap. However, the ServiceContext is deprecated. Does anyone have any idea how i can configure the chunk zise now?

Hi guys, I am using SemanticSimilarityEvaluator to do the evaluation. Does anyone know if this is to calculate cosine similarity score, or other scores?

Hi, guys! I recently upgraded the llama-index from v0.9 to v0.10. When I run "from llama_index.vector_stores.postgres import PGVectorStore", it returns the error " ImportError: cannot import name 'DEFAULT_PERSIST_FNAME' from partially initialized module 'llama_index.core.vector_stores.simple' (most likely due to a circular import)"

Hi, I used to use the Prompt.from_langchain_prompt in my code, but it failed recently after I installed the latest version of LlamaIndex. Does anyone have any idea about this? Thanks