[Rag application Bug] Warning TT undefined function 32

[danielstankw]

I am trying to create super simple RAG application locally. I am local LLM model which I verified to work. The embeddings are Azure OpenAI and I write a python script to test it, and it also work. Whenever I run the pipeline I get the following error.

Saving works, but I get error (below) every time I upsert vector database.

2024-04-08 20:28:52 [INFO]: ⬆️ POST /api/v1/vector/internal-upsert/2c177181-8271-435e-98ff-57504e26af17
Warning: TT: undefined function: 32
2024-04-08 20:30:19 [ERROR]: Error: Connection error.
Error: Error: Connection error.
    at InMemoryVectorStore_VectorStores.upsert (/usr/local/lib/node_modules/flowise/node_modules/flowise-components/dist/nodes/vectorstores/InMemory/InMemoryVectorStore.js:25:27)
    at process.processTicksAndRejections (node:internal/process/task_queues:95:5)
    at async buildFlow (/usr/local/lib/node_modules/flowise/dist/utils/index.js:265:17)
    at async App.upsertVector (/usr/local/lib/node_modules/flowise/dist/index.js:1698:13)
    at async /usr/local/lib/node_modules/flowise/dist/index.js:1193:13
2024-04-08 20:30:19 [ERROR]: [server]: Error: Error: Error: Connection error.
Error: Error: Error: Connection error.
    at buildFlow (/usr/local/lib/node_modules/flowise/dist/utils/index.js:326:19)
    at process.processTicksAndRejections (node:internal/process/task_queues:95:5)
    at async App.upsertVector (/usr/local/lib/node_modules/flowise/dist/index.js:1698:13)
    at async /usr/local/lib/node_modules/flowise/dist/index.js:1193:13

[HenryHengZJ]

The error says that is not able to reach LocalAI connection. If you are running both FW and LocalAI on Docker, you might have to change the LocalAI base path - https://docs.flowiseai.com/integrations/langchain/chat-models/chatlocalai#flowise-setup

[danielstankw]

@HenryHengZJ I am hosting my LLM using VLLM and connect to the endpoint using FastApi. I have tested before and I am able to use local LLM with no issues, so I do not see why here it would be the source of the problem. Do you have other suggestions on what could be the problem>?