It has different results than our SerpAPI wrapper, so it may not be a drop in replacement. In particular, I've noticed that its more verbose. But maybe that can be improved in parsing of the results? Big to @nickscamara_ for adding this!
CODE
-
Google Custom Search API Free Tier Advantages Over SerpAPI
By
–
The default search API that people seem to use (and the only one previously in LangChain) is SerpAPI One big limitation is that the free plan only supports *100 queries per month* But there is a Google Custom Search alternative that supports *100 queries per day* for free
-
Google Custom Search cheaper alternative SerpAPI LangChain integration guide
By
–
After the free plan, it's also a better deal. SerpAPI is $50 for 5k queries Google Custom Search is $5 for 1k queries, meaning for the same $50 you could get double the queries. So how do you use this cheaper search engine in LangChain?
-
LangChain v0.0.53 Release: Google Search Integration
By
–
LangChain v0.0.53 Doc fixes from @george_zhou Bug fix (highlighted by @yvesbalbas
) Also includes maybe the most requested feature to date… A google search alternative to SerpAPI (by @nickscamara_
) More on this in below -
Free Machine Learning Courses from Top Universities
By
–
100% FREE machine learning courses from top Colleges: – MIT 6.S191 Introduction to Deep Learning
– DS-GA 1008 Deep Learning
– UC Berkeley Full Stack Deep Learning
– UC Berkeley CS 182 Deep Learning
– Cornell Tech CS 5787 Applied Machine Learning -
Using nlp.pipe() for faster batched predictions in spaCy
By
–
Nice example! Here's a tip for next time as well: the nlp.pipe() function operates over a sequence of inputs, and lets the model make batched predictions, making it much faster:
-
Copilot’s Code Synthesis Capabilities Praised as Best
By
–
Copilot is for code completion so you have to write comments to use it like ChatGPT, but it’s the best I’ve seen for code synthesis.
-
Comparing AI Model Trustworthiness: Copilot vs. ChatGPT
By
–
Copilot isn’t ChatGPT. I don’t trust ChatGPT’s output on this stuff at all — way too many errors. I think it specifically aims for equivocation in a way that makes it confabulate wrong technical details.
-
LLMs like Copilot replace Google for code installation commands
By
–
Imports and installation commands are the purest instance of LLMs replacing Google for me. Only the comments in this screenshot were written by hand, and the rest is Copilot completion:
-
AI Code Generation Security Risks and Prudent Practices
By
–
I think writing `pip install …` commands from memory is bad security. If it's `python-foobar` instead of `foobar` you might be installing malware. A more prudent approach is to type `# install foobar with pip:` into Copilot and blindly execute whatever it says.