Add human prefix for memory Previously, in memory the user input was hardcoded to "Human" Now, thanks to Andrew Huang, it is exposed as a parameter that can be controlled https://
langchain.readthedocs.io/en/latest/modu
les/memory/examples/conversational_customization.html#human-prefix
…
@langchain
-
LangChain Memory Human Prefix Parameter Now Customizable
By
–
-
LangChain Improves Agent Max Iterations Handling with Final LLM Pass
By
–
More graceful handling of agent max iterations Previously, when an agent reached max iterations, it just stopped with a fixed message Now it makes one final forward pass through the LLM to generate a best guess final answer h/t @johnjnay for idea https://
langchain.readthedocs.io/en/latest/modu
les/agents/examples/max_iterations.html
… -
LangChain v0.0.55 Release: Agent and Chain Improvements
By
–
v0.0.55 HuggingFace docs update (
@_lewtun
)
Unify argument names for intermediate steps in map-reduce & refine chains (h/t @johnjnay
)
More graceful handling of agent max iterations (h/t @johnjnay
)
Add human prefix for memory (Andrew Huang) -
LangChain Gallery Showcases Community AI Projects
By
–
Gallery Our favorite section to write, this includes awesome examples of things created with LangChain (many open sources!), from people like @johnjnay @brunotorious @BlackHC @JavaFXpert @chillzaza_ @matthiassamwald https://
langchain.readthedocs.io/en/latest/gall
ery.html
… -
LangChain Use Cases: Agents, Chatbots, QA, Summarization
By
–
Use Cases A new section, this highlights common use cases of LangChain, including: – Agents
– Chatbots
– Question Answering over your documents
– Summarization
– Evaluation https://
langchain.readthedocs.io/en/latest/inde
x.html#use-cases
… -
LangChain Ecosystem Integration with Major AI Players
By
–
Ecosystem A new section as well, this highlights how LangChain integrates with other players in this space, including: @OpenAI @CohereAI @huggingface @weaviate_io @pinecone @AI21Labs @HazyResearch https://
langchain.readthedocs.io/en/latest/ecos
ystem.html
… -
Getting Started with LangChain for LLM Application Development
By
–
Getting Started Covers all aspects of how to get started using LangChain to build an LLM application – including installation, environment setup, and a walkthrough of the main modules https://
langchain.readthedocs.io/en/latest/gett
ing_started/getting_started.html
… -
LangChain Core Modules: Prompts, LLMs, Chains, Agents
By
–
Modules The main modules of functionality that make up LangChain, consisting of: – Prompt Templates
– LLMs
– Utilities (search, vector DBs, etc)
– Chains
– Agents
– Memory -
LangChain Revamps Documentation with New Sections
By
–
New Year, New Docs In an effort to make LangChain easier-to-use than ever before, we've revamped our docs. Sections include: Getting Started
Modules
[NEW] Use Cases
[NEW] Ecosystem
Gallery -
LangChain Quickstart: Google Search Integration with Agents
By
–
See these docs for a quickstart for this utility: https://
langchain.readthedocs.io/en/latest/exam
ples/chains/google_search.html
… But, probably more importantly, see these docs for a guide on how to load it as a tool that you can use with an agent: https://
langchain.readthedocs.io/en/latest/exam
ples/agents/search_tools.html
…