I built an AI Agent that use vector store as a tool for RAG. But i cannot make the RAG to work. I use Gemini Flash model for language, and Gemini Embedding model04 for embedding.
What is the error message (if any)?
I am getting an “Empty Array” message within the node “In-Memory Vector Store”, eventhough the “embedding model” step is showing a response with embeddings.
Ensure to copy your n8n workflow and paste it in the code block, that is in between the pairs of triple backticks, which also could be achieved by clicking </> (preformatted text) in the editor and pasting in your workflow.
```
<your workflow>
```
That implies to any JSON output you would like to share with us.
Make sure that you have removed any sensitive information from your workflow and include dummy or pinned data with it!
Have you added any data (embeddings) to that store before started using it as a tool? Your workflow does not appear to show that you did. If so, no suprise it retuns no data.
Note it is in-memory store. Hence its persistence is also short-lived. You woudn’t use it for a production workflow.
Same here, when running in Editor, it answers 100% right. But on production (Workflow calling) it gave only empty results. I think is an issue with the Memory Key when you are calling a subworkflow (maybe its using the father workflow id to append to the key to avoid colisions)
Same here, I am using the qdrant vector database store, and I have the same results. Gemini returns the embeddings, but the vector database has an empty response.
I have the same issue. The qdrant vector store returns chunks but no text it. I tried connecting to the same vector store using langchain and it works fine. I wonder if anyone has solved this issue
