Jakub Bartczuk

pulled model not found fix - added to FAQ

4

I've added a fix by [sridvijay](https://github.com/sridvijay) from #3876 to the documentation.

Is there a generic way to change model's `max_tokens` dynamically?

9

I have a use case where I want to use the same LM in different steps with different `max_tokens` and context size. I use `dspy.configure` to set this LM. Some...

Ediprolog gives incorrect answer even though scryer is correct

1

I have a following Prolog file ```prolog man(socrates). man(adam). woman(alice). mortal(X):- man(X). mortal(X):- woman(X). /* ?- mortal(alice). */ ``` Ediprolog responds with ``` /* ?- mortal(alice). %@ false. */ ```...

Abstract over LM

7

# TL;DR Currently org-ai uses OpenAI API. In some cases someone might use different API or even local LLM. # Context There are many interesting open-source models that can be...

Tests

1

@rksm please let me know if you want to write a test suite for the plugin. If you have high-level ideas what would be most beneficial approach just write this...

LM memory AKA vector databases

1

# TL;DR Retrieval mechanisms can be used to provide kind of memory for an LLM. This memory can be used for semantic search and QA based on retrieved code/documentation fragments....

How to use `run_query` in streaming mode/limiting number of matches?

3

I've written basic bindings for Python in [my project](https://github.com/lambdaofgod/pyscryer) using `lib_machine::Machine`'s `run_query`. For queries that return small number of matches it works fine, but when I run a query that...

CodexGraph - building is done but nothing was added to Neo4J

4

### Initial Checks - [X] I have searched GitHub for a duplicate issue and I'm sure this is something new - [X] I have read and followed [the docs &...

Predictors with Ollama return input prompt in answer

2

DSPy versions I checked: 2.4.0 and 2.4.12 Ollama version: 0.1.9 I use model served with ollama (I tried it with both "chat" and "text") ``` import dspy model = dspy.OllamaLocal(model='aya',...