issues upload of documents to localGPT

[Robertp75]

Hello, I installed and configured a localGPT-LLM with an .env file as follows:
PERSIST_DIRECTORY=C:\Users\testuser\AppData\Local\r-miniconda\db
MODEL_TYPE=GPT4All
MODEL_PATH=C:\Users\testuser\AppData\Local\r-miniconda\bin\ggml-gpt4all-j-v1.3-groovy.bin
EMBEDDINGS_MODEL_NAME=all-MiniLM-L6-v2
MODEL_N_CTX=1000
TARGET_SOURCE_CHUNKS=4
The localGPT chat works brilliant but I have issues to receive the content of uploaded documents.
The documents were uploaded (ingest.py) correctly as I printed the content of the "chroma-embeddings.parquet"-file via python and the content of the uploaded document will be displayed. Its seems as the model is not searching in the "chroma-embeddings.parquet"-file while prompting. Does anybody has an idea what the issue could be. Maybe I have wrong configuration settings somewhere? Many thanks in advance.