Skip to content

Error 500 #1

@Captain-Bacon

Description

@Captain-Bacon

Hi there,

You have NO idea how exciting this is for a chronic adhd hyperfocus geek non programmer like myself.

I run on a Mac, and port 500 is used for Airplay stuff. I exported the flask run variable to port 5050

export FLASK_RUN_PORT = 5050

and then amended the knowledgebase line:

    this.serverUrl = 'http://localhost:5050';

However it doesn't sseem to be working. Flask is running on port 5050 OK...

WARNING:chromadb:Using embedded DuckDB with persistence: data will be stored in: ./.chroma_persist
WARNING:chromadb.api.models.Collection:No embedding_function provided, using default embedding function: SentenceTransformerEmbeddingFunction
2023-04-28 15:22:42.571274: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/langchain/chains/retrieval_qa/base.py:183: UserWarning: VectorDBQA is deprecated - please use from langchain.chains import RetrievalQA
warnings.warn(

  • Serving Flask app 'server'
  • Debug mode: off
    INFO:werkzeug:WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead.
  • Running on http://127.0.0.1:5050

But it's 'typing' forever.

When I run an inspect pop-up on it I see the below:

Screenshot 2023-04-28 at 15 51 07

Obviously I'm missing something somewhere as it's not working, and still talking about port 5000. I'm a complete green-horn, so was hoping you could help me figure this out, and then every mac user would be able to do the same.

FWIW I made a little script to run which bypasses some of the command lines

import os
import subprocess

set the environment variables

os.environ['TOKENIZERS_PARALLELISM'] = 'false'
os.environ['OPENAI_API_KEY'] = 'sk....'
os.environ['FLASK_RUN_PORT'] = '5050'

change the working directory

os.chdir('path/to/dir/memex/server')

run the flask app

subprocess.call('FLASK_APP=server flask run', shell=True)

Then saved a plist file so that the startup launcher daemons on the Mac launch the server every time the mac turns on. Saves me having to remember.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions