probably something different. these are triggered deterministically, you probably want something like you described to be triggered as needed by the agent
AI
-
PipelinePrompts formatting order and application guide
By
–
When `.format` is called, the PipelinePrompts are first formatted in order, and are then used in future formatting steps with their respective `name` arguments Finally, the FinalPrompt.format is called using any previously formatted values as neccesary
-
LangChain Prompt Composition Features for Reusability
By
–
Python Documentation: https://
python.langchain.com/en/latest/modu
les/prompts/prompt_templates/examples/prompt_composition.html
… JS/TS Documentation: https://
js.langchain.com/docs/modules/p
rompts/prompt_templates/prompt_composition
… We want to make prompts as composable and reusable as possible – would love feedback on this implementation! -
PipelinePrompt: Sequencing Prompt Templates for AI Workflows
By
–
The way this works is you define a `PipelinePrompt` with two components: – FinalPrompt: the final prompt template to be formatted
– PipelinePrompts: a sequence of tuples of (name, PromptTemplate) The `name` argument is how the formatted prompt will be passed to future prompts -
Pipeline Prompt: Composing Reusable Prompt Pieces Together
By
–
Composable Prompts Wouldn't it be nice if there was a way to compose prompts together, reusing pieces across prompts? In the newest Python and JS release there now is with `Pipeline Prompt`! Links
-
Eliminate Non-Value Activities to Boost Career Growth
By
–
Eliminating or minimizing non-value-added habits and activities will dramatically improve your life and career.
-
Foundation Models with Business Proprietary Data Integration
By
–
Incorporating businesses’ proprietary data into foundation models is the way forward. Commentary from @RodrigoLiang on the Azure ML Integration with Snowflake, via @insideBIGDATA1's "Heard on the Street" roundup. Read the full commentary roundup at https://
insidebigdata.com/2023/06/05/hea
rd-on-the-street-6-5-2023/
… -
GPTeam Deep Dive: Open Source Generative Agents Simulation
By
–
GPTeam Deep Dive GPTeam by @itstimconnors and team is a fully OSS project building off of @joon_s_pk
's "Generative Agents" paper Vey excited to share a guest blog post be him, going into great detail as to how they build the complex simulation -
Human Validation for Safe LLM Tool Integration
By
–
Human-in-the-loop Tool Validation LLMs can become dangerous when hooked up to tools To help safeguard against this you can require human validation before the tool is run (or run in certain ways) https://
python.langchain.com/en/latest/modu
les/agents/tools/human_approval.html
… h/t @PieterHumphrey for the idea -
Core Stability vs Experimental Features in Software Development
By
–
the core stuff is and will be even. some of the integrations wont be, and some of the experimental stuff wont be