v0.0.51 Unify return types for intermediate steps – h/t @johnjnay Add sports & knowledge graph results to SerpAPI wrapper – @brunotorious Document improvements: @eltociear @samcwl Making tools editable – h/t @brunotorious Memory support for chains with multi inputs
AGENTS
-
Making Tools Editable: Customize Tool Descriptions for Better Agent Performance
By
–
Making tools editable When loading tools, they come with default descriptions. Sometimes, as @brunotorious pointed out, you may want to edit their descriptions in order to get them to work better with agents Now you can: https://
langchain.readthedocs.io/en/latest/exam
ples/agents/custom_tools.html#Modify-existing-tools
… -
Beyond Copilot: The Next Evolution in AI Developer Experience
By
–
The Big Question in AI-driven developer experience: What's after Copilot? Everyone is convinced this is "just" the beginning but can't articulate what the next killer form factor will be. Increasingly convinced next step change won't be from optimal stuffing context windows
-
Open Source Chatbot Creation Example Released
By
–
There's been lots of chatbots announced recently Check out for an open source example of how to create one! @brunotorious
-
Multi-input Tools with Agents Documentation Improved
By
–
Multi-input tools with agents It wasn't super clear how to use tools that require multiple inputs with agents bryan on discord called this out, and as a result there is improved documentation! https://
langchain.readthedocs.io/en/latest/exam
ples/agents/multi_input_tool.html
… -
Improved Agent Output Parsing for LLM Integration
By
–
Better parsing of agent output For some agents, the parsing of LLM output to agent action was pretty brittle A few people called this out, but s/o in particular to brandon69 on discord This should be improved, and can now handle things like multi line return values!
-
LangChain v0.0.47: Community Updates and Agent Improvements
By
–
v0.0.47 – lots of community initiated changes! Documentation Updates – @GradientAscent8 Easier support for creating vectorstores from many docs – s/o @GradientAscent8 Multi-input tools with agents Better parsing of agent output explanations:
-
LangChain v0.0.46: Memory Bug Fix Enables Agents as Tools
By
–
v0.0.46 ReadMe improvement from @altryne Bug fix for handling of memory, highlighted by @andrewgleave This fix now allows you to use chains & agents *with memory* as tools in other agents!! This means that agents can have much more powerful tools now
-
Reasoning and Pattern Recognition as Transferable Abilities
By
–
Reasoning and pattern recognition are abilities, not problem types. They're what you use to solve problems in different settings, they're not inherent to the problems themselves.
-
LangChain AGI Demo Now Available on Hugging Face Spaces
By
–
And now @JavaFXpert put this in a @huggingface spaces! https://
huggingface.co/spaces/JavaFXp
ert/langchain-agi
…