We've also added a new type of memory This type of memory allows for using the results of previous tool invocations in future agent interactions This means if you ask a follow up question, you don't have to do retrieval all over again
AGENTS
-
Conversational Retrieval Agents Replace ConversationalRetrievalChain
By
–
Conversational Retrieval Agents The most popular chain in @langchain is the ConversationalRetrievalChain, which allows you chat with your data Using an agent instead can allow for great flexibility, and its a narrow and well defined enough agent that its fairly reliable
-
Conversational Retrieval Agents: Advanced QA Systems
By
–
I'll dive into details in this thread, but quick links: Blog: https://
blog.langchain.dev/conversational
-retrieval-agents/
… Python Docs: https://
python.langchain.com/docs/use_cases
/question_answering/how_to/conversational_retrieval_agents
… JS Docs: https://
js.langchain.com/docs/use_cases
/question_answering/conversational_retrieval_agents
… -
Personal Assistant AI Agent Launches on Product Hunt
By
–
And we're live! Check out Personal Assistant on Product Hunt… the first AI agent that can operate your browser
-
Seven Key Patterns for Building LLM-Based Systems
By
–
A very good blog post by @eugeneyan on “Patterns for building LLM based systems and products”. He covers the seven key patterns to build LLM based systems in greater detail. Link: https://
eugeneyan.com/writing/llm-pa
tterns/
… Must read for folks looking to build LLM based features / products -
Profitero’s AI Chatbot Streamlines Retail Media Analytics
By
–
A new chatbot from the e-commerce analytics company Profitero aims to help companies connect the dots across the fragmented but burgeoning world of retail media.
-
Training Personal Email Assistant with Conversation Variety
By
–
That’s a good point. Yeah if there is sufficient variety in the conversations, I can see how one can train a personal email assistant that way.
-
Teaching LLMs to Use Tools via Documentation Instead of Demonstrations
By
–
Using tool documentation rather than demonstrations to teach LLMs how to use new tools and APIs Potential ideas: • Simplifies deploying new APIs and tools for AI assistants by just providing documentation. • Enables businesses to leverage cutting edge AI innovations as soon
-
AI Chatbots Fail at Shopping Assistant Tasks
By
–
I Asked #AI #Chatbots to Help Me Shop. They All Failed https://
bit.ly/3P0qYIa via @WIRED