github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-06-26 00:23:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update Documentation: Corrected Typos and Improved Clarity (#11725)

Browse Source 
Docs updates

---------

Co-authored-by: Advaya <126754021+bluevayes@users.noreply.github.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
This commit is contained in:
VAS 2023-11-11 03:44:44 +05:30 committed by GitHub
parent e165daa0ae
commit 8fa960641a
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
6 changed files with 17 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
docs/docs/modules/agents/agent_types/index.mdx
View File

@ -38,7 +38,7 @@ It uses the ReAct framework to decide which tool to use, and uses memory to reme
## [Self-ask with search](/docs/modules/agents/agent_types/self_ask_with_search) ## [Self-ask with search](/docs/modules/agents/agent_types/self_ask_with_search)
This agent utilizes a single tool that should be named `Intermediate Answer`. This agent utilizes a single tool that should be named `Intermediate Answer`.
This tool should be able to lookup factual answers to questions. This agent This tool should be able to look up factual answers to questions. This agent
is equivalent to the original [self-ask with search paper](https://ofir.io/self-ask.pdf), is equivalent to the original [self-ask with search paper](https://ofir.io/self-ask.pdf),
where a Google search API was provided as the tool. where a Google search API was provided as the tool.
@ -46,7 +46,7 @@ where a Google search API was provided as the tool.
This agent uses the ReAct framework to interact with a docstore. Two tools must This agent uses the ReAct framework to interact with a docstore. Two tools must
be provided: a `Search` tool and a `Lookup` tool (they must be named exactly as so). be provided: a `Search` tool and a `Lookup` tool (they must be named exactly as so).
The `Search` tool should search for a document, while the `Lookup` tool should lookup The `Search` tool should search for a document, while the `Lookup` tool should look up
a term in the most recently found document. a term in the most recently found document.
This agent is equivalent to the This agent is equivalent to the
original [ReAct paper](https://arxiv.org/pdf/2210.03629.pdf), specifically the Wikipedia example. original [ReAct paper](https://arxiv.org/pdf/2210.03629.pdf), specifically the Wikipedia example.

2
docs/docs/modules/agents/how_to/custom_llm_agent.mdx
View File

@ -1,4 +1,4 @@
# Custom LLM agent # Custom LLM Agent
This notebook goes through how to create your own custom LLM agent. This notebook goes through how to create your own custom LLM agent.

14
docs/docs/modules/agents/how_to/custom_llm_chat_agent.mdx
View File

@ -1,13 +1,13 @@
# Custom LLM Agent (with a ChatModel) # Custom LLM Chat Agent
This notebook goes through how to create your own custom agent based on a chat model. This notebook explains how to create your own custom agent based on a chat model.
An LLM chat agent consists of three parts: An LLM chat agent consists of four key components:
- `PromptTemplate`: This is the prompt template that can be used to instruct the language model on what to do - `PromptTemplate`: This is the prompt template that instructs the language model on what to do.
- `ChatModel`: This is the language model that powers the agent - `ChatModel`: This is the language model that powers the agent.
- `stop` sequence: Instructs the LLM to stop generating as soon as this string is found - `stop` sequence: Instructs the LLM to stop generating as soon as this string is found.
- `OutputParser`: This determines how to parse the LLM output into an `AgentAction` or `AgentFinish` object - `OutputParser`: This determines how to parse the LLM output into an `AgentAction` or `AgentFinish` object.
The LLM Agent is used in an `AgentExecutor`. This `AgentExecutor` can largely be thought of as a loop that: The LLM Agent is used in an `AgentExecutor`. This `AgentExecutor` can largely be thought of as a loop that:
1. Passes user input and any previous steps to the Agent (in this case, the LLM Agent) 1. Passes user input and any previous steps to the Agent (in this case, the LLM Agent)

4
docs/docs/modules/agents/how_to/mrkl.mdx
View File

@ -3,7 +3,7 @@
This walkthrough demonstrates how to replicate the [MRKL](https://arxiv.org/pdf/2205.00445.pdf) system using agents. This walkthrough demonstrates how to replicate the [MRKL](https://arxiv.org/pdf/2205.00445.pdf) system using agents.
This uses the example Chinook database. This uses the example Chinook database.
To set it up follow the instructions on https://database.guide/2-sample-databases-sqlite/, placing the `.db` file in a notebooks folder at the root of this repository. To set it up, follow the instructions on https://database.guide/2-sample-databases-sqlite/ and place the `.db` file in a "notebooks" folder at the root of this repository.
```python ```python
from langchain.chains import LLMMathChain from langchain.chains import LLMMathChain
@ -127,7 +127,7 @@ mrkl.run("What is the full name of the artist who recently released an album cal
</CodeOutputBlock> </CodeOutputBlock>
## With a chat model ## Using a Chat Model
```python ```python
from langchain.chat_models import ChatOpenAI from langchain.chat_models import ChatOpenAI

6
docs/docs/modules/agents/tools/index.mdx
View File

@ -4,17 +4,17 @@ sidebar_position: 2
# Tools # Tools
:::info :::info
Head to [Integrations](/docs/integrations/tools/) for documentation on built-in tool integrations. For documentation on built-in tool integrations, visit [Integrations](/docs/integrations/tools/).
::: :::
Tools are interfaces that an agent can use to interact with the world. Tools are interfaces that an agent can use to interact with the world.
## Get started ## Getting Started
Tools are functions that agents can use to interact with the world. Tools are functions that agents can use to interact with the world.
These tools can be generic utilities (e.g. search), other chains, or even other agents. These tools can be generic utilities (e.g. search), other chains, or even other agents.
Currently, tools can be loaded with the following snippet: Currently, tools can be loaded using the following snippet:
```python ```python
from langchain.agents import load_tools from langchain.agents import load_tools

4
docs/docs/modules/agents/tools/toolkits.mdx
View File

@ -4,7 +4,7 @@ sidebar_position: 3
# Toolkits # Toolkits
:::info :::info
Head to [Integrations](/docs/integrations/toolkits/) for documentation on built-in toolkit integrations. For documentation on built-in toolkit integrations, visit [Integrations](/docs/integrations/toolkits/).
::: :::
Toolkits are collections of tools that are designed to be used together for specific tasks and have convenience loading methods. Toolkits are collections of tools that are designed to be used together for specific tasks and have convenient loading methods.