mindflowai / mindflow Goto Github PK
View Code? Open in Web Editor NEW๐ง AI-powered CLI git wrapper, boilerplate code generator, chat history manager, and code search engine to streamline your dev workflow ๐
๐ง AI-powered CLI git wrapper, boilerplate code generator, chat history manager, and code search engine to streamline your dev workflow ๐
when calling mf index then mf query on a single file
takes a long time and it just kinda has an empty resonse feed. we should have a progress bar
running on MacOS 12.6.3, conda 4.3.27, Python 3.9.7
mf login {OPENAI_API_KEY}
runs without errors and correctly shows the API key in run_login but after inspecting
.config/mindflow/DB.json turns out to be empty.
more db.json
{}
Hence running mf chat "tell me a joke"
outputs
No service API key configured. Please configure an API key for at least one service.
ConfiguredService
, ConfiguredModel
, and MindFlowModel
values seem to be re-instantiated each time their values are accessed. I only want the models and services to be loaded in once.
the conversation class' _prune
function is responsible for pruning a conversation's earlier messages to keep a form of chat persistence, but for all conversations (and the current token limits for openai) need to be under 4096 total tokens. something is broken with this mechanism and the earlier message pruning doesn't work.
to fix you need to run mf history clear
but that just gets rid of all chat persistence.
Currently, embeddings are generated at inference. This is slow, but it saves space. At some point, I'll want to save these embeddings for faster inference.
Simple Term Menu package is only Mac OS compatible. This makes MindFlow pretty much unusable for non mac users.
In need of tests! Please add tests using pytest.
I want to make sure the mf diff command is properly parsing and feeding the diffs into gpt.
Maybe some of the requirements are only required for development and doesnt have to be a dependency for users.
TEST
Traceback (most recent call last):
File "/Users/koc/opt/anaconda3/lib/python3.9/site-packages/numpy/core/__init__.py", line 23, in <module>
from . import multiarray
File "/Users/koc/opt/anaconda3/lib/python3.9/site-packages/numpy/core/multiarray.py", line 10, in <module>
from . import overrides
File "/Users/koc/opt/anaconda3/lib/python3.9/site-packages/numpy/core/overrides.py", line 6, in <module>
from numpy.core._multiarray_umath import (
ImportError: dlopen(/Users/koc/opt/anaconda3/lib/python3.9/site-packages/numpy/core/_multiarray_umath.cpython-39-darwin.so, 0x0002): Library not loaded: '@rpath/libopenblas.dylib'
Referenced from: '/Users/koc/opt/anaconda3/lib/python3.9/site-packages/numpy/core/_multiarray_umath.cpython-39-darwin.so'
Reason: tried: '/Users/koc/opt/anaconda3/lib/libopenblas.dylib' (no such file), '/Users/koc/opt/anaconda3/lib/libopenblas.dylib' (no such file), '/Users/koc/opt/anaconda3/lib/python3.9/site-packages/numpy/core/../../../../libopenblas.dylib' (no such file), '/Users/koc/opt/anaconda3/lib/libopenblas.dylib' (no such file), '/Users/koc/opt/anaconda3/lib/libopenblas.dylib' (no such file), '/Users/koc/opt/anaconda3/lib/python3.9/site-packages/numpy/core/../../../../libopenblas.dylib' (no such file), '/Users/koc/opt/anaconda3/lib/libopenblas.dylib' (no such file), '/Users/koc/opt/anaconda3/bin/../lib/libopenblas.dylib' (no such file), '/Users/koc/opt/anaconda3/lib/libopenblas.dylib' (no such file), '/Users/koc/opt/anaconda3/bin/../lib/libopenblas.dylib' (no such file), '/usr/local/lib/libopenblas.dylib' (no such file), '/usr/lib/libopenblas.dylib' (no such file)
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/Users/koc/opt/anaconda3/bin/mf", line 5, in <module>
from mindflow.cli.new_click_cli.cli_main import mindflow_cli
File "/Users/koc/opt/anaconda3/lib/python3.9/site-packages/mindflow/cli/new_click_cli/cli_main.py", line 5, in <module>
from mindflow.cli.new_click_cli.commands.git.commit import commit
File "/Users/koc/opt/anaconda3/lib/python3.9/site-packages/mindflow/cli/new_click_cli/commands/git/commit.py", line 6, in <module>
from mindflow.core.git.commit import run_commit
File "/Users/koc/opt/anaconda3/lib/python3.9/site-packages/mindflow/core/git/commit.py", line 4, in <module>
from mindflow.core.git.diff import run_diff
File "/Users/koc/opt/anaconda3/lib/python3.9/site-packages/mindflow/core/git/diff.py", line 10, in <module>
from mindflow.db.objects.model import ConfiguredModel
File "/Users/koc/opt/anaconda3/lib/python3.9/site-packages/mindflow/db/objects/model.py", line 4, in <module>
import numpy as np
File "/Users/koc/opt/anaconda3/lib/python3.9/site-packages/numpy/__init__.py", line 144, in <module>
from . import core
File "/Users/koc/opt/anaconda3/lib/python3.9/site-packages/numpy/core/__init__.py", line 49, in <module>
raise ImportError(msg)
ImportError:
IMPORTANT: PLEASE READ THIS FOR ADVICE ON HOW TO SOLVE THIS ISSUE!
Importing the numpy C-extensions failed. This error can happen for
many reasons, often due to issues with your setup or how NumPy was
installed.
We have compiled some common reasons and troubleshooting tips at:
https://numpy.org/devdocs/user/troubleshooting-importerror.html
Please note and check the following:
* The Python version is: Python3.9 from "/Users/koc/opt/anaconda3/bin/python"
* The NumPy version is: "1.22.3"
and make sure that they are the versions you expect.
Please carefully study the documentation linked above for further help.
Original error was: dlopen(/Users/koc/opt/anaconda3/lib/python3.9/site-packages/numpy/core/_multiarray_umath.cpython-39-darwin.so, 0x0002): Library not loaded: '@rpath/libopenblas.dylib'
Referenced from: '/Users/koc/opt/anaconda3/lib/python3.9/site-packages/numpy/core/_multiarray_umath.cpython-39-darwin.so'
Reason: tried: '/Users/koc/opt/anaconda3/lib/libopenblas.dylib' (no such file), '/Users/koc/opt/anaconda3/lib/libopenblas.dylib' (no such file), '/Users/koc/opt/anaconda3/lib/python3.9/site-packages/numpy/core/../../../../libopenblas.dylib' (no such file), '/Users/koc/opt/anaconda3/lib/libopenblas.dylib' (no such file), '/Users/koc/opt/anaconda3/lib/libopenblas.dylib' (no such file), '/Users/koc/opt/anaconda3/lib/python3.9/site-packages/numpy/core/../../../../libopenblas.dylib' (no such file), '/Users/koc/opt/anaconda3/lib/libopenblas.dylib' (no such file), '/Users/koc/opt/anaconda3/bin/../lib/libopenblas.dylib' (no such file), '/Users/koc/opt/anaconda3/lib/libopenblas.dylib' (no such file), '/Users/koc/opt/anaconda3/bin/../lib/libopenblas.dylib' (no such file), '/usr/local/lib/libopenblas.dylib' (no such file), '/usr/lib/libopenblas.dylib' (no such file)
Outputs into the command line could be cleaned up a little bit. After copying to the clipboard, maybe add a new line before output.
git init
in the folder)A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.