openai api - llama-index: How to Extract `context_str` Used in ...
Aug 31, 2023 · I'm working with LlamaIndex, and I need to extract the context_str that was used in a query before it was sent to the LLM (Language Model). Here's the relevant code: index = …
LLamaindex: How to add new documents to an existing index
Oct 18, 2024 · LLamaindex: How to add new documents to an existing index Asked 1 year, 8 months ago Modified 1 year, 7 months ago Viewed 1k times
Differences between Langchain & LlamaIndex - Stack Overflow
Aug 28, 2023 · LlamaIndex is also more efficient than Langchain, making it a better choice for applications that need to process large amounts of data. If you are building a general-purpose …
Newest 'llama-index' Questions - Stack Overflow
Dec 5, 2025 · I am trying to create a ReAct agent in LlamaIndex using a local gpt-oss-20b model. I have successfully loaded my local model using HuggingFaceLLM from llama_index.llms.huggingface and …
Use LlamaIndex with different embeddings model - Stack Overflow
May 31, 2023 · OpenAI's GPT embedding models are used across all LlamaIndex examples, even though they seem to be the most expensive and worst performing embedding models compared to …
Failing to install llama-index package - Stack Overflow
May 16, 2023 · if using poetry you can also try relaxing all the version constraints and let the resolver try to figure it out. like this but for llamaindex (the same deps mess happens on langchain too)
large language model - Persist VectorStoreIndex (LlamaIndex) locally ...
Dec 22, 2023 · Persist VectorStoreIndex (LlamaIndex) locally Asked 2 years, 6 months ago Modified 1 year, 11 months ago Viewed 2k times
llama index - LlamaIndex Python: Metadata filter with `None` value …
Aug 26, 2025 · So even though the metadata is stored as {'start_date': None}, filtering with EQ value=None does not return the node. My questions: Is this the expected behavior in LlamaIndex …
python - How to Send a Streaming Response via LlamaIndex to a …
Apr 19, 2024 · Reference FastAPI - StreamingResponse Solution In order to use the StreamingResponse class provided, you'll need to create an async generator or a normal …
ImportError: cannot import name 'VectorStoreIndex' from 'llama_index ...
Llamaindex constantly changes the modules directories. The module you are searching for is: from llama_index.core import VectorStoreIndex And for an especific vectorstore using chromadb as …