From 660c728124240af9f7492ff624864b87a61c46f6 Mon Sep 17 00:00:00 2001 From: Santiago Olivar Date: Sat, 20 Apr 2024 10:13:22 -0700 Subject: [PATCH] updated a link --- _posts/2024-04-19-Data-Agents-With-LalaIndex.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/_posts/2024-04-19-Data-Agents-With-LalaIndex.md b/_posts/2024-04-19-Data-Agents-With-LalaIndex.md index bbef493..e22ecb5 100644 --- a/_posts/2024-04-19-Data-Agents-With-LalaIndex.md +++ b/_posts/2024-04-19-Data-Agents-With-LalaIndex.md @@ -18,7 +18,7 @@ The main core steps of a Data Agent include: - **Reasoning Loop:** This loop determines how the Agent will interact with different data tools. LlamaIndex supports a [variety of Agents and functionalities](https://docs.llamaindex.ai/en/stable/examples/agent/Chatbot_SEC/), including: - [**ReAct Agent:**](https://docs.llamaindex.ai/en/stable/examples/Agent/react_Agent_with_query_engine/) It involves a 3-step process: Thought (determine which tool to use), Action (use the tool to take an action), and Observation (check the result and iterate until a final result is obtained). - [**Function Calling Agent:**](https://docs.llamaindex.ai/en/stable/examples/Agent/openai_Agent_parallel_function_calling/) A unified abstraction that utilizes function calling capabilities of different LLMs to call given tools. - - [**Chain-of-Abstraction Agent:**][https://docs.llamaindex.ai/en/stable/examples/agent/coa_agent/] Implements a generalized version of the strategy described in the [original paper](https://arxiv.org/pdf/2401.17464.pdf). It enables LLMs to learn more general reasoning strategies that are robust to shifts of domain knowledge relevant to different reasoning questions. + - [**Chain-of-Abstraction Agent:**](https://docs.llamaindex.ai/en/stable/examples/agent/coa_agent/) Implements a generalized version of the strategy described in the [original paper](https://arxiv.org/pdf/2401.17464.pdf). It enables LLMs to learn more general reasoning strategies that are robust to shifts of domain knowledge relevant to different reasoning questions. - [**Retrieval Augmented:**](https://docs.llamaindex.ai/en/stable/examples/Agent/openai_Agent_retrieval/) Utilizes an Agent together with a tool retriever to manage an index on an arbitrary number of data tools, reducing latency and cost by retrieving only relevant tools. - [**Controlling Reasoning Loop:**](https://docs.llamaindex.ai/en/stable/examples/Agent/return_direct_Agent/?h=return_direct) Allows modification of the Agent reasoning loop, where the output is returned directly instead of using an LLM, useful for speeding up response times. - [**Step-wise Controllable:**](https://docs.llamaindex.ai/en/stable/examples/agent/agent_runner/agent_runner/) Provides more granular control of the Agent by separating task creation and execution, enabling sharing feedback to the Agent as it completes tasks.