Dylan Hogg

Hi @narasimhankrishna, I some rough code to do basic CPU training in a fork that might be of use to you: https://github.com/dylanhogg/address-net/blob/master/train.py You'll need to change the paths etc but...

@narasimhankrishna Yes I think you need to include all the columns from the GNAF dataset in your training data - I added Postgres create tables, loading and export to training...

Hey @Aj-232425, Do you have a branch with the training code you're running? Log output would be useful too, if possible. It's been quite a while since I looked at...

Hey @Aj-232425, I've put together a (very rough) upgrade to TF2 here: https://github.com/dylanhogg/address-net/tree/tf2 I pulled fresh Aug22 GNAF data and regenerated the `address_view` csv and tfrecord datasets. Then locally I...

@taratuncho, I am curious to know what text address input you used to get that output result? Without the input it is hard to diagnose the output. I ran the...

There is a PR for this fix, in addition to enabling resume on partially downloaded files here: https://github.com/pytube/pytube/pull/1873 You can also use this fix via `pip install git+https://github.com/dylanhogg/pytube.git@resume_partial_download` if you...

Fair observation, thanks for the feedback. Currently repo similarity calculation is quite naive, and is in need of improvement. Right now it uses sentence_transformers with the `all-MiniLM-L6-v2` model to calculate...

Thanks for your suggestions, now added. Some will not display by default due to lower star count, this link shows all regardless of stars: https://www.awesomepython.org/?full=1

You can specify a different LLM provider, including running with a local https://github.com/jmorganca/ollama model. You should be able to specify (via the `--llm-model` argument, see [docs here](https://github.com/dylanhogg/llmgraph/#optional-arguments)) anything supported by...

Thanks for looking into this @yaricom - doing a bit more digging and I note that for my Agent I am setting a state key in `custom_before_agent_callback()` with a "user:"...