Question Answering with citations Ahead of our webinar on Wednesday, more `functions` goodness from @jxnlco
: Answer a question (with citations) from a piece of context. Uses `functions` to specify the return schema of the answer + supporting facts https://
python.langchain.com/docs/modules/c
hains/additional/qa_citations
…
AI
-
Question Answering with Citations Using LangChain Functions
By
–
-
Deploy Computer Vision Apps with Hugging Face Spaces and Gradio
By
–
🎥 New Video Alert!https://t.co/PkU9Felksh
— Satya Mallick (@LearnOpenCV) 19 juin 2023
Unlock the secrets of deploying a Computer Vision App in our latest video!
🚀We simplify the process with Hugging Face Spaces and Gradio. Tune in to elevate your #techgame! #ComputerVision #AppDeployment #HuggingFace #Gradio #ai… pic.twitter.com/aKydWO9VGiNew Alert! https://
youtube.com/watch?v=6b3S2D
2TiAo
… Unlock the secrets of deploying a Computer Vision App in our latest video! We simplify the process with Hugging Face Spaces and Gradio. Tune in to elevate your #techgame! #ComputerVision #AppDeployment #HuggingFace #Gradio #ai -
AMAT and ASML: Semiconductor Capital Equipment Valuations Under Pressure
By
–
Time to drop AMAT and ASML as New Street pushes semi-cap recovery to 2025 The P/Es are way above historical norms. https://
thetechnologyletter.com/the-posts/time
-to-drop-amat-and-asml-as-new-street-pushes-semi-cap-recovery-to-2025
… $ASML $AMAT #investing #semiconductor -
Zscaler CEO: Bold Statements on Cybersecurity Market Opportunities
By
–
Please enjoy my interview with Zscaler CEO Jay Chaudhry. Zscaler CEO: Our stock is a great buy at any price “Check Point is the living dead,” and other bold statements. https://
thetechnologyletter.com/the-posts/zsca
ler-ceo-chaudhry-disrupting-the-old-guard-is-a-mega-opportunity
… $ZS $CHKP $PANW $IBM $HPE #investing #stocks #cybersecurity #AIart -
Memory Types and Reflection for Improved Chatbot Performance
By
–
The most interesting thing here IMO is the exploration of multiple different types of "memory" for creating chatbots
— Harrison Chase (@hwchase17) 19 juin 2023
Baseline would just be retrieval over the raw corpus, but by doing some reflection-like things as a preprocessing step, you can get better results https://t.co/XKeHg3Rgp0The most interesting thing here IMO is the exploration of multiple different types of "memory" for creating chatbots Baseline would just be retrieval over the raw corpus, but by doing some reflection-like things as a preprocessing step, you can get better results
-
Webinar on Functions: Use Cases and Q&A Session
By
–
To hear more about `functions`, join us (me, Atty, @fpingham
, and @jxnlco
) for an exciting webinar this Wednesday! We'll cover how to use it, what some common use cases are, and then answer any and all questions! -
LLM Functions and Pydantic Schema Parsing Integration
By
–
llm_kwargs: this is where we specify `functions` and `function_call` output_parser: this is where we parse the `function_call` response into either a string, json object, or pydantic object @pydantic is really nice for letting users specify schema in a Pythonic way!
-
Adding Function Chains: Extraction, Tagging, Question-Answering
By
–
So that's the general formula for how we're adding `functions` chains So far we've added: – Extraction
– Tagging
– Question-Answering with citations We're EXTREMELY open to contributions here – with this formula should be a pretty easy addition -
LLM Configuration and Prompt Templates Setup Guide
By
–
Breaking that down: llm: this is the language model, at the moment needs to be an @OpenAI Chat model prompt: this is the prompt template to use. Generally should be a list of message templates this is pretty standard, nothing new so far
-
Function Call OutputParser for API Response Handling
By
–
When doing this, the `content` field on the response message will be blank The real response is in the `function_call` section To make it easier to use that information, we've added an OutputParser than picks out that information