Jamie Coombes

ConversationChain's conversation.predict() multiple times gives confusing logging. Inspired by: https://python.langchain.com/en/latest/modules/memory/examples/conversational_customization.html Minimal Confusing Example: ```python from langchain.llms import OpenAI from langchain.chains import ConversationChain from langchain.memory import ConversationBufferMemory llm = OpenAI(temperature=0) conversation...

[Feature Request] ConversationalChain prints system, user and human message prompts using separate colors.

1

Currently the logging output from the ConversationChain is quite hard to read. I believe implementing separate colors from System Messages, Human Messages and AI messages by role would involve modifying...

[Request]: Implement '__matmul__' method on 'PythonObject'

2

### Bug description I'm writing some 'hello-gpu' code which works with pytorch. /home/user/code/obvs/obvs/gputest.🔥:29:15: error: 'PythonObject' does not implement the '__matmul__' method z = x @ y ### Steps to reproduce...

### Is this a new bug in dbt-expectations? - [X] I believe this is a new bug in dbt-expectations - [X] I have searched the existing issues, and I could...

Update extensions.json

1

on cookiecutter, vscode will now recommend the user installs the `ruff` extension. This harmonises the extensions.json with the settings.json

https://github.com/microsoft/vscode-python/wiki/Migration-to-Python-Tools-Extensions

Change the getting_started and quickstart docs to fix these issues in pre-commit. ``` poetry-export...................................................................Failed - hook id: poetry-export - files were modified by this hook Configuration file exists at /Users/jamie/Library/Preferences/pypoetry,...

``` Warning: poetry-plugin-export will not be installed by default in a future version of Poetry. In order to avoid a breaking change and make your automation forward-compatible, please install poetry-plugin-export...

Ollama Integration doesn't allow setting num_ctx in ollama ^ The default value of num_ctx in the API is 2k, and I would like to run llama3:70b with num_ctx 8192. https://docs.crewai.com/how-to/LLM-Connections/