Hi all , iam used pagedcsvreader along with chromadb and when iam querying with similarity_top_k as 10 but none of the documents are relevant to query. Although iam directly specifying important keywords in query. What can I do to improve rag with CSV data

iam implementing a rag chatbot, but it's always answering from first retrieved documents only. If I can any other questions retrieved documents are same . It's not able to retrieve different set of documents

how to use a chatengine with codellama to create coding assistant

iam getting segmentation fault core dumped in my chat engine

iam using document summary index for my context chat engine, now my chat chat engine only answers about summary or it can answer based on orginal document if some information is not captured in summary

how can I use streaming response from chat engine in fastapi

hey how can I use my local url , which is llamacpp python server hosted locally in 8000 port in llamaindex for llm inference

how can I use llmlingua with chatengine

Iam hosting a llamacpp server locally, how can I use this server for Rag implementation to make llm calls ?

How to make llamacpp model inference faster. ? Iam using llamaindex rag with local gguf model and it's taking more than 2 min for single query

It's there any memory tool to keep track of history , similar to langchain memory buffer ?

how can I make chat_engine execution faster by using all cpu cores if needed

I have multiple CSV files and data dictionary describing about each column . I want to use only open source llm and Rag to create conversational chatbot with memory. It should be able to perform aggregations also on my CSV data files

https://docs.llamaindex.ai/en/stable/examples/pipeline/query_pipeline_pandas.html

Pandas query engine is not working properly with open source llms like Zephyr 7b. Any guide to work with CSV files , building rag chatbot

Is continuous batching available in llamacpp cpu server?

@kapa.ai hey how can I create seperate context engine in fastapi for different users in llamaindex.

Hi how to use hosted llamacpp server in llamaindex for chat engine. Iam trying by importing OpenAiLike and passing model name and base_api still getting error

@kapa.ai how to use llama CPP server in llamaindex . I launched openapi compatible llamacpp server. How can I use this url

Hi All , do we have any llm server framework like vllm, open llm which can be run only on cpu and make use of multiple cpus in cluster like master and worker to serve multiple inferences parallel

@kapa.ai llamaindex support for xinference cpu

@kapa.ai I am doing a rag chatbot with chat engine, how can I limit my output to strictly context and provide as less output as possible. Right now iam getting answer and also full follow up information about my question

@kapa.ai how to set prompt template for Microsoft phi-2 model and how to pass to llamacpp

Hi , I seen llmlingua and tried with llamaindex , also using llamacpp for loading llm. For each question the time taken to get prefix match hit is too high . Llm inference time although reduced, time taken to hit llm is so high that without llmlingua my chat engine is giving faster response. Any idea on this. Iam using only cpu

Hi , is there a way to make pandas query engine more contextual like taking previous input/output into context for follow up questions