fix-typo

.github/workflows/codespell.yml

@@ -20,5 +20,3 @@ jobs:
         uses: actions/checkout@v3
       - name: Codespell
         uses: codespell-project/actions-codespell@v2
-        with:
-          skip: guide_imports.json

README.md

@@ -19,7 +19,7 @@
 Looking for the JS/TS version? Check out [LangChain.js](https://github.com/hwchase17/langchainjs).
 
 **Production Support:** As you move your LangChains into production, we'd love to offer more comprehensive support.
-Please fill out [this form](https://6w1pwbss0py.typeform.com/to/rrbrdTH2) and we'll set up a dedicated support Slack channel.
+Please fill out [this form](https://forms.gle/57d8AmXBYp8PP8tZA) and we'll set up a dedicated support Slack channel.
 
 ## 🚨Breaking Changes for select chains (SQLDatabase) on 7/28
 

docs/api_reference/conf.py

@@ -7,66 +7,20 @@
 
 # -- Path setup --------------------------------------------------------------
 
-import json
-import os
-import sys
-from pathlib import Path
-
-import toml
-from docutils import nodes
-from sphinx.util.docutils import SphinxDirective
-
 # If extensions (or modules to document with autodoc) are in another directory,
 # add these directories to sys.path here. If the directory is relative to the
 # documentation root, use os.path.abspath to make it absolute, like shown here.
+#
+import os
+import sys
+
+import toml
 
-_DIR = Path(__file__).parent.absolute()
 sys.path.insert(0, os.path.abspath("."))
 sys.path.insert(0, os.path.abspath("../../libs/langchain"))
 
-with (_DIR.parents[1] / "libs" / "langchain" / "pyproject.toml").open("r") as f:
+with open("../../libs/langchain/pyproject.toml") as f:
     data = toml.load(f)
-with (_DIR / "guide_imports.json").open("r") as f:
-    imported_classes = json.load(f)
-
-
-class ExampleLinksDirective(SphinxDirective):
-    """Directive to generate a list of links to examples.
-
-    We have a script that extracts links to API reference docs
-    from our notebook examples. This directive uses that information
-    to backlink to the examples from the API reference docs."""
-
-    has_content = False
-    required_arguments = 1
-
-    def run(self):
-        """Run the directive.
-
-        Called any time :example_links:`ClassName` is used
-        in the template *.rst files."""
-        class_or_func_name = self.arguments[0]
-        links = imported_classes.get(class_or_func_name, {})
-        list_node = nodes.bullet_list()
-        for doc_name, link in links.items():
-            item_node = nodes.list_item()
-            para_node = nodes.paragraph()
-            link_node = nodes.reference()
-            link_node["refuri"] = link
-            link_node.append(nodes.Text(doc_name))
-            para_node.append(link_node)
-            item_node.append(para_node)
-            list_node.append(item_node)
-        if list_node.children:
-            title_node = nodes.title()
-            title_node.append(nodes.Text(f"Examples using {class_or_func_name}"))
-            return [title_node, list_node]
-        return [list_node]
-
-
-def setup(app):
-    app.add_directive("example_links", ExampleLinksDirective)
-
 
 # -- Project information -----------------------------------------------------
 

docs/api_reference/create_api_rst.py

@@ -40,7 +40,11 @@ API Reference
         functions = _members["functions"]
         if not (classes or functions):
             continue
-        section = f":mod:`langchain.{module}`"
+
+        module_title = module.replace("_", " ").title()
+        if module_title == "Llms":
+            module_title = "LLMs"
+        section = f":mod:`langchain.{module}`: {module_title}"
         full_doc += f"""\
 {section}
 {'=' * (len(section) + 1)}
@@ -74,7 +78,6 @@ Functions
 
 .. autosummary::
     :toctree: {module}
-    :template: function.rst
 
     {fstring}
 

docs/api_reference/modules/evaluation.rst

@@ -0,0 +1,9 @@
+Evaluation
+=======================
+
+LangChain has a number of convenient evaluation chains you can use off the shelf to grade your models' oupputs.
+
+.. automodule:: langchain.evaluation
+   :members:
+   :undoc-members:
+   :inherited-members:

docs/api_reference/templates/class.rst

@@ -26,5 +26,3 @@
    {%- endfor %}
    {% endif %}
    {% endblock %}
-
-.. example_links:: {{ objname }}

docs/api_reference/templates/function.rst

@@ -1,8 +0,0 @@
-:mod:`{{module}}`.{{objname}}
-{{ underline }}==============
-
-.. currentmodule:: {{ module }}
-
-.. autofunction:: {{ objname }}
-
-.. example_links:: {{ objname }}

docs/api_reference/themes/scikit-learn-modern/static/css/theme.css

@@ -745,11 +745,6 @@ span.descname {
   background-color: transparent;
   padding: 0;
   font-family: monospace;
-  font-size: 1.2rem;
-}
-
-em.property {
-  font-weight: normal;
 }
 
 span.descclassname {

docs/docs_skeleton/docs/get_started/introduction.mdx

@@ -51,7 +51,7 @@ Walkthroughs and best-practices for common end-to-end use cases, like:
 Learn best practices for developing with LangChain.
 
 ### [Ecosystem](/docs/ecosystem/)
-LangChain is part of a rich ecosystem of tools that integrate with our framework and build on top of it. Check out our growing list of [integrations](/docs/integrations/) and [dependent repos](/docs/ecosystem/dependents).
+LangChain is part of a rich ecosystem of tools that integrate with our framework and build on top of it. Check out our growing list of [integrations](/docs/ecosystem/integrations/) and [dependent repos](/docs/ecosystem/dependents.html).
 
 ### [Additional resources](/docs/additional_resources/)
 Our community is full of prolific developers, creative builders, and fantastic teachers. Check out [YouTube tutorials](/docs/additional_resources/youtube.html) for great tutorials from folks in the community, and [Gallery](https://github.com/kyrolabs/awesome-langchain) for a list of awesome LangChain projects, compiled by the folks at [KyroLabs](https://kyrolabs.com).

docs/docs_skeleton/docs/get_started/quickstart.mdx

@@ -22,74 +22,28 @@ import OpenAISetup from "@snippets/get_started/quickstart/openai_setup.mdx"
 
 ## Building an application
 
-Now we can start building our language model application. LangChain provides many modules that can be used to build language model applications.
-Modules can be used as stand-alones in simple applications and they can be combined for more complex use cases.
-
-The core building block of LangChain applications is the LLMChain.
-This combines three things:
-- LLM: The language model is the core reasoning engine here. In order to work with LangChain, you need to understand the different types of language models and how to work with them.
-- Prompt Templates: This provides instructions to the language model. This controls what the language model outputs, so understanding how to construct prompts and different prompting strategies is crucial.
-- Output Parsers: These translate the raw response from the LLM to a more workable format, making it easy to use the output downstream.
-
-In this getting started guide we will cover those three components by themselves, and then cover the LLMChain which combines all of them.
-Understanding these concepts will set you up well for being able to use and customize LangChain applications.
-Most LangChain applications allow you to configure the LLM and/or the prompt used, so knowing how to take advantage of this will be a big enabler.
+Now we can start building our language model application. LangChain provides many modules that can be used to build language model applications. Modules can be used as stand-alones in simple applications and they can be combined for more complex use cases.
 
 ## LLMs
+#### Get predictions from a language model
 
-There are two types of language models, which in LangChain are called:
+The basic building block of LangChain is the LLM, which takes in text and generates more text.
 
-- LLMs: this is a language model which takes a string as input and returns a string
-- ChatModels: this is a language model which takes a list of messages as input and returns a message
+As an example, suppose we're building an application that generates a company name based on a company description. In order to do this, we need to initialize an OpenAI model wrapper. In this case, since we want the outputs to be MORE random, we'll initialize our model with a HIGH temperature.
 
-The input/output for LLMs is simple and easy to understand - a string.
-But what about ChatModels? The input there is a list of `ChatMessage`s, and the output is a single `ChatMessage`.
-A `ChatMessage` has two required components:
+import LLM from "@snippets/get_started/quickstart/llm.mdx"
 
-- `content`: This is the content of the message.
-- `role`: This is the role of the entity from which the `ChatMessage` is coming from.
+<LLM/>
 
-LangChain provides several objects to easily distinguish between different roles:
+## Chat models
 
-- `HumanMessage`: A `ChatMessage` coming from a human/user.
-- `AIMessage`: A `ChatMessage` coming from an AI/assistant.
-- `SystemMessage`: A `ChatMessage` coming from the system.
-- `FunctionMessage`: A `ChatMessage` coming from a function call.
+Chat models are a variation on language models. While chat models use language models under the hood, the interface they expose is a bit different: rather than expose a "text in, text out" API, they expose an interface where "chat messages" are the inputs and outputs.
 
-If none of those roles sound right, there is also a `ChatMessage` class where you can specify the role manually.
-For more information on how to use these different messages most effectively, see our prompting guide.
+You can get chat completions by passing one or more messages to the chat model. The response will be a message. The types of messages currently supported in LangChain are `AIMessage`, `HumanMessage`, `SystemMessage`, and `ChatMessage` -- `ChatMessage` takes in an arbitrary role parameter. Most of the time, you'll just be dealing with `HumanMessage`, `AIMessage`, and `SystemMessage`.
 
-LangChain exposes a standard interface for both, but it's useful to understand this difference in order to construct prompts for a given language model.
-The standard interface that LangChain exposes has two methods:
-- `predict`: Takes in a string, returns a string
-- `predict_messages`: Takes in a list of messages, returns a message.
-
-Let's see how to work with these different types of models and these different types of inputs.
-First, let's import an LLM and a ChatModel.
-
-import ImportLLMs from "@snippets/get_started/quickstart/import_llms.mdx"
-
-<ImportLLMs/>
-
-The `OpenAI` and `ChatOpenAI` objects are basically just configuration objects.
-You can initialize them with parameters like `temperature` and others, and pass them around.
-
-Next, let's use the `predict` method to run over a string input.
-
-import InputString from "@snippets/get_started/quickstart/input_string.mdx"
-
-<InputString/>
-
-Finally, let's use the `predict_messages` method to run over a list of messages.
-
-import InputMessages from "@snippets/get_started/quickstart/input_messages.mdx"
-
-<InputMessages/>
-
-For both these methods, you can also pass in parameters as key word arguments.
-For example, you could pass in `temperature=0` to adjust the temperature that is used from what the object was configured with.
-Whatever values are passed in during run time will always override what the object was configured with.
+import ChatModel from "@snippets/get_started/quickstart/chat_model.mdx"
 
+<ChatModel/>
 
 ## Prompt templates
 
@@ -97,66 +51,108 @@ Most LLM applications do not pass user input directly into an LLM. Usually they
 
 In the previous example, the text we passed to the model contained instructions to generate a company name. For our application, it'd be great if the user only had to provide the description of a company/product, without having to worry about giving the model instructions.
 
-PromptTemplates help with exactly this!
-They bundle up all the logic for going from user input into a fully formatted prompt.
-This can start off very simple - for example, a prompt to produce the above string would just be:
-
 import PromptTemplateLLM from "@snippets/get_started/quickstart/prompt_templates_llms.mdx"
 import PromptTemplateChatModel from "@snippets/get_started/quickstart/prompt_templates_chat_models.mdx"
 
+<Tabs>
+    <TabItem value="llms" label="LLMs" default>
+
+With PromptTemplates this is easy! In this case our template would be very simple:
+
 <PromptTemplateLLM/>
+</TabItem>
+<TabItem value="chat_models" label="Chat models">
 
-However, the advantages of using these over raw string formatting are several.
-You can "partial" out variables - eg you can format only some of the variables at a time.
-You can compose them together, easily combining different templates into a single prompt.
-For explanations of these functionalities, see the [section on prompts](/docs/modules/model_io/prompts) for more detail.
+Similar to LLMs, you can make use of templating by using a `MessagePromptTemplate`. You can build a `ChatPromptTemplate` from one or more `MessagePromptTemplate`s. You can use `ChatPromptTemplate`'s `format_messages` method to generate the formatted messages.
 
-PromptTemplates can also be used to produce a list of messages.
-In this case, the prompt not only contains information about the content, but also each message (its role, its position in the list, etc)
-Here, what happens most often is a ChatPromptTemplate is a list of ChatMessageTemplates.
-Each ChatMessageTemplate contains instructions for how to format that ChatMessage - its role, and then also its content.
-Let's take a look at this below:
+Because this is generating a list of messages, it is slightly more complex than the normal prompt template which is generating only a string. Please see the detailed guides on prompts to understand more options available to you here.
 
 <PromptTemplateChatModel/>
+    </TabItem>
+</Tabs>
 
-ChatPromptTemplates can also include other things besides ChatMessageTemplates - see the [section on prompts](/docs/modules/model_io/prompts) for more detail.
+## Chains
 
-## Output Parsers
+Now that we've got a model and a prompt template, we'll want to combine the two. Chains give us a way to link (or chain) together multiple primitives, like models, prompts, and other chains.
 
-OutputParsers convert the raw output of an LLM into a format that can be used downstream.
-There are few main type of OutputParsers, including:
+import ChainLLM from "@snippets/get_started/quickstart/chains_llms.mdx"
+import ChainChatModel from "@snippets/get_started/quickstart/chains_chat_models.mdx"
 
-- Convert text from LLM -> structured information (eg JSON)
-- Convert a ChatMessage into just a string
-- Convert the extra information returned from a call besides the message (like OpenAI function invocation) into a string.
+<Tabs>
+<TabItem value="llms" label="LLMs" default>
 
-For full information on this, see the [section on output parsers](/docs/modules/model_io/output_parsers)
+The simplest and most common type of chain is an LLMChain, which passes an input first to a PromptTemplate and then to an LLM. We can construct an LLM chain from our existing model and prompt template.
 
-In this getting started guide, we will write our own output parser - one that converts a comma separated list into a list.
+<ChainLLM/>
 
-import OutputParser from "@snippets/get_started/quickstart/output_parser.mdx"
+There we go, our first chain! Understanding how this simple chain works will set you up well for working with more complex chains.
 
-<OutputParser/>
+</TabItem>
+<TabItem value="chat_models" label="Chat models">
 
-## LLMChain
+The `LLMChain` can be used with chat models as well:
 
-We can now combine all these into one chain.
-This chain will take input variables, pass those to a prompt template to create a prompt, pass the prompt to an LLM, and then pass the output through an (optional) output parser.
-This is a convenient way to bundle up a modular piece of logic.
-Let's see it in action!
+<ChainChatModel/>
+</TabItem>
+</Tabs>
 
-import LLMChain from "@snippets/get_started/quickstart/llm_chain.mdx"
+## Agents
 
-<LLMChain/>
+import AgentLLM from "@snippets/get_started/quickstart/agents_llms.mdx"
+import AgentChatModel from "@snippets/get_started/quickstart/agents_chat_models.mdx"
 
-## Next Steps
+Our first chain ran a pre-determined sequence of steps. To handle complex workflows, we need to be able to dynamically choose actions based on inputs.
 
-This is it!
-We've now gone over how to create the core building block of LangChain applications - the LLMChains.
-There is a lot more nuance in all these components (LLMs, prompts, output parsers) and a lot more different components to learn about as well.
-To continue on your journey:
+Agents do just this: they use a language model to determine which actions to take and in what order. Agents are given access to tools, and they repeatedly choose a tool, run the tool, and observe the output until they come up with a final answer.
 
-- [Dive deeper](/docs/modules/model_io) into LLMs, prompts, and output parsers
-- Learn the other [key components](/docs/modules)
-- Check out our [helpful guides](/docs/guides) for detailed walkthroughs on particular topics
-- Explore [end-to-end use cases](/docs/use_cases)
+To load an agent, you need to choose a(n):
+- LLM/Chat model: The language model powering the agent.
+- Tool(s): A function that performs a specific duty. This can be things like: Google Search, Database lookup, Python REPL, other chains. For a list of predefined tools and their specifications, see the [Tools documentation](/docs/modules/agents/tools/).
+- Agent name: A string that references a supported agent class. An agent class is largely parameterized by the prompt the language model uses to determine which action to take. Because this notebook focuses on the simplest, highest level API, this only covers using the standard supported agents. If you want to implement a custom agent, see [here](/docs/modules/agents/how_to/custom_agent.html). For a list of supported agents and their specifications, see [here](/docs/modules/agents/agent_types/).
+
+For this example, we'll be using SerpAPI to query a search engine.
+
+You'll need to install the SerpAPI Python package:
+
+```bash
+pip install google-search-results
+```
+
+And set the `SERPAPI_API_KEY` environment variable.
+
+<Tabs>
+<TabItem value="llms" label="LLMs" default>
+<AgentLLM/>
+</TabItem>
+<TabItem value="chat_models" label="Chat models">
+
+Agents can also be used with chat models, you can initialize one using `AgentType.CHAT_ZERO_SHOT_REACT_DESCRIPTION` as the agent type.
+
+<AgentChatModel/>
+</TabItem>
+</Tabs>
+
+## Memory
+
+The chains and agents we've looked at so far have been stateless, but for many applications it's necessary to reference past interactions. This is clearly the case with a chatbot for example, where you want it to understand new messages in the context of past messages.
+
+The Memory module gives you a way to maintain application state. The base Memory interface is simple: it lets you update state given the latest run inputs and outputs and it lets you modify (or contextualize) the next input using the stored state.
+
+There are a number of built-in memory systems. The simplest of these is a buffer memory which just prepends the last few inputs/outputs to the current input - we will use this in the example below.
+
+import MemoryLLM from "@snippets/get_started/quickstart/memory_llms.mdx"
+import MemoryChatModel from "@snippets/get_started/quickstart/memory_chat_models.mdx"
+
+<Tabs>
+<TabItem value="llms" label="LLMs" default>
+
+<MemoryLLM/>
+</TabItem>
+<TabItem value="chat_models" label="Chat models">
+
+You can use Memory with chains and agents initialized with chat models. The main difference between this and Memory for LLMs is that rather than trying to condense all previous messages into a string, we can keep them as their own unique memory object.
+
+<MemoryChatModel/>
+
+</TabItem>
+</Tabs>

docs/docs_skeleton/docs/guides/evaluation/comparison/index.mdx

@@ -1,24 +0,0 @@
----
-sidebar_position: 3 
----
-# Comparison Evaluators
-
-Comparison evaluators in LangChain help measure two different chain or LLM outputs. These evaluators are helpful for comparative analyses, such as A/B testing between two language models, or comparing different versions of the same model. They can also be useful for things like generating preference scores for ai-assisted reinforcement learning.
-
-These evaluators inherit from the `PairwiseStringEvaluator` class, providing a comparison interface for two strings - typically, the outputs from two different prompts or models, or two versions of the same model. In essence, a comparison evaluator performs an evaluation on a pair of strings and returns a dictionary containing the evaluation score and other relevant details.
-
-To create a custom comparison evaluator, inherit from the `PairwiseStringEvaluator` class and overwrite the `_evaluate_string_pairs` method. If you require asynchronous evaluation, also overwrite the `_aevaluate_string_pairs` method.
-
-Here's a summary of the key methods and properties of a comparison evaluator:
-
-- `evaluate_string_pairs`: Evaluate the output string pairs. This function should be overwritten when creating custom evaluators.
-- `aevaluate_string_pairs`: Asynchronously evaluate the output string pairs. This function should be overwritten for asynchronous evaluation.
-- `requires_input`: This property indicates whether this evaluator requires an input string.
-- `requires_reference`: This property specifies whether this evaluator requires a reference label.
-
-Detailed information about creating custom evaluators and the available built-in comparison evaluators are provided in the following sections.
-
-import DocCardList from "@theme/DocCardList";
-
-<DocCardList />
-

docs/docs_skeleton/docs/guides/evaluation/index.mdx

@@ -1,31 +0,0 @@
----
-sidebar_position: 6
----
-
-import DocCardList from "@theme/DocCardList";
-
-# Evaluation
-
-Building applications with language models involves many moving parts. One of the most critical components is ensuring that the outcomes produced by your models are reliable and useful across a broad array of inputs, and that they work well with your application's other software components. Ensuring reliability usually boils down to some combination of application design, testing & evaluation, and runtime checks. 
-
-The guides in this section review the APIs and functionality LangChain provides to help yous better evaluate your applications. Evaluation and testing are both critical when thinking about deploying LLM applications, since production environments require repeatable and useful outcomes.
-
-LangChain offers various types of evaluators to help you measure performance and integrity on diverse data, and we hope to encourage the the community to create and share other useful evaluators so everyone can improve. These docs will introduce the evaluator types, how to use them, and provide some examples of their use in real-world scenarios.
-
-Each evaluator type in LangChain comes with ready-to-use implementations and an extensible API that allows for customization according to your unique requirements. Here are some of the types of evaluators we offer:
-
-- [String Evaluators](/docs/guides/evaluation/string/): These evaluators assess the predicted string for a given input, usually comparing it against a reference string.
-- [Trajectory Evaluators](/docs/guides/evaluation/trajectory/): These are used to evaluate the entire trajectory of agent actions.
-- [Comparison Evaluators](/docs/guides/evaluation/comparison/): These evaluators are designed to compare predictions from two runs on a common input.
-
-These evaluators can be used across various scenarios and can be applied to different chain and LLM implementations in the LangChain library.
-
-We also are working to share guides and cookbooks that demonstrate how to use these evaluators in real-world scenarios, such as:
-
-- [Chain Comparisons](/docs/guides/evaluation/examples/comparisons): This example uses a comparison evaluator to predict the preferred output. It reviews ways to measure confidence intervals to select statistically significant differences in aggregate preference scores across different models or prompts.
-
-## Reference Docs
-
-For detailed information on the available evaluators, including how to instantiate, configure, and customize them, check out the [reference documentation](https://api.python.langchain.com/en/latest/api_reference.html#module-langchain.evaluation) directly.
-
-<DocCardList />

docs/docs_skeleton/docs/guides/evaluation/string/index.mdx

@@ -1,27 +0,0 @@
----
-sidebar_position: 2 
----
-# String Evaluators
-
-A string evaluator is a component within LangChain designed to assess the performance of a language model by comparing its generated outputs (predictions) to a reference string or an input. This comparison is a crucial step in the evaluation of language models, providing a measure of the accuracy or quality of the generated text.
-
-In practice, string evaluators are typically used to evaluate a predicted string against a given input, such as a question or a prompt. Often, a reference label or context string is provided to define what a correct or ideal response would look like. These evaluators can be customized to tailor the evaluation process to fit your application's specific requirements.
-
-To create a custom string evaluator, inherit from the `StringEvaluator` class and implement the `_evaluate_strings` method. If you require asynchronous support, also implement the `_aevaluate_strings` method.
-
-Here's a summary of the key attributes and methods associated with a string evaluator:
-
-- `evaluation_name`: Specifies the name of the evaluation.
-- `requires_input`: Boolean attribute that indicates whether the evaluator requires an input string. If True, the evaluator will raise an error when the input isn't provided. If False, a warning will be logged if an input _is_ provided, indicating that it will not be considered in the evaluation.
-- `requires_reference`: Boolean attribute specifying whether the evaluator requires a reference label. If True, the evaluator will raise an error when the reference isn't provided. If False, a warning will be logged if a reference _is_ provided, indicating that it will not be considered in the evaluation.
-
-String evaluators also implement the following methods:
-
-- `aevaluate_strings`: Asynchronously evaluates the output of the Chain or Language Model, with support for optional input and label.
-- `evaluate_strings`: Synchronously evaluates the output of the Chain or Language Model, with support for optional input and label.
-
-The following sections provide detailed information on available string evaluator implementations as well as how to create a custom string evaluator.
-
-import DocCardList from "@theme/DocCardList";
-
-<DocCardList />

docs/docs_skeleton/docs/guides/evaluation/trajectory/index.mdx

@@ -1,28 +0,0 @@
----
-sidebar_position: 4
----
-# Trajectory Evaluators
-
-Trajectory Evaluators in LangChain provide a more holistic approach to evaluating an agent. These evaluators assess the full sequence of actions taken by an agent and their corresponding responses, which we refer to as the "trajectory". This allows you to better measure an agent's effectiveness and capabilities.
-
-A Trajectory Evaluator implements the `AgentTrajectoryEvaluator` interface, which requires two main methods:
-
-- `evaluate_agent_trajectory`: This method synchronously evaluates an agent's trajectory.
-- `aevaluate_agent_trajectory`: This asynchronous counterpart allows evaluations to be run in parallel for efficiency.
-
-Both methods accept three main parameters:
-
-- `input`: The initial input given to the agent.
-- `prediction`: The final predicted response from the agent.
-- `agent_trajectory`: The intermediate steps taken by the agent, given as a list of tuples.
-
-These methods return a dictionary. It is recommended that custom implementations return a `score` (a float indicating the effectiveness of the agent) and `reasoning` (a string explaining the reasoning behind the score).
-
-You can capture an agent's trajectory by initializing the agent with the `return_intermediate_steps=True` parameter. This lets you collect all intermediate steps without relying on special callbacks.
-
-For a deeper dive into the implementation and use of Trajectory Evaluators, refer to the sections below.
-
-import DocCardList from "@theme/DocCardList";
-
-<DocCardList />
-

docs/docs_skeleton/docs/modules/agents/index.mdx

@@ -3,80 +3,46 @@ sidebar_position: 4
 ---
 # Agents
 
-The core idea of agents is to use an LLM to choose a sequence of actions to take.
-In chains, a sequence of actions is hardcoded (in code).
-In agents, a language model is used as a reasoning engine to determine which actions to take and in which order.
+Some applications require a flexible chain of calls to LLMs and other tools based on user input. The **Agent** interface provides the flexibility for such applications. An agent has access to a suite of tools, and determines which ones to use depending on the user input. Agents can use multiple tools, and use the output of one tool as the input to the next.
 
-There are several key components here:
+There are two main types of agents:
 
-## Agent
+- **Action agents**: at each timestep, decide on the next action using the outputs of all previous actions
+- **Plan-and-execute agents**: decide on the full sequence of actions up front, then execute them all without updating the plan
 
-This is the class responsible for deciding what step to take next.
-This is powered by a language model and a prompt.
-This prompt can include things like:
+Action agents are suitable for small tasks, while plan-and-execute agents are better for complex or long-running tasks that require maintaining long-term objectives and focus. Often the best approach is to combine the dynamism of an action agent with the planning abilities of a plan-and-execute agent by letting the plan-and-execute agent use action agents to execute plans.
 
-1. The personality of the agent (useful for having it respond in a certain way)
-2. Background context for the agent (useful for giving it more context on the types of tasks it's being asked to do)
-3. Prompting strategies to invoke better reasoning (the most famous/widely used being [ReAct](https://arxiv.org/abs/2210.03629))
+For a full list of agent types see [agent types](/docs/modules/agents/agent_types/). Additional abstractions involved in agents are:
+- [**Tools**](/docs/modules/agents/tools/): the actions an agent can take. What tools you give an agent highly depend on what you want the agent to do
+- [**Toolkits**](/docs/modules/agents/toolkits/): wrappers around collections of tools that can be used together a specific use case. For example, in order for an agent to
+  interact with a SQL database it will likely need one tool to execute queries and another to inspect tables
 
-LangChain provides a few different types of agents to get started.
-Even then, you will likely want to customize those agents with parts (1) and (2).
-For a full list of agent types see [agent types](/docs/modules/agents/agent_types/)
+## Action agents
 
-## Tools
+At a high-level an action agent:
+1. Receives user input
+2. Decides which tool, if any, to use and the tool input
+3. Calls the tool and records the output (also known as an "observation")
+4. Decides the next step using the history of tools, tool inputs, and observations
+5. Repeats 3-4 until it determines it can respond directly to the user
 
-Tools are functions that an agent calls.
-There are two important considerations here:
+Action agents are wrapped in **agent executors**, which are responsible for calling the agent, getting back an action and action input, calling the tool that the action references with the generated input, getting the output of the tool, and then passing all that information back into the agent to get the next action it should take.
 
-1. Giving the agent access to the right tools
-2. Describing the tools in a way that is most helpful to the agent
+Although an agent can be constructed in many ways, it typically involves these components:
 
-Without both, the agent you are trying to build will not work.
-If you don't give the agent access to a correct set of tools, it will never be able to accomplish the objective.
-If you don't describe the tools properly, the agent won't know how to properly use them.
+- **Prompt template**: Responsible for taking the user input and previous steps and constructing a prompt
+  to send to the language model
+- **Language model**: Takes the prompt with use input and action history and decides what to do next
+- **Output parser**: Takes the output of the language model and parses it into the next action or a final answer
 
-LangChain provides a wide set of tools to get started, but also makes it easy to define your own (including custom descriptions).
-For a full list of tools, see [here](/docs/modules/agents/tools/)
+## Plan-and-execute agents
 
-## Toolkits
+At a high-level a plan-and-execute agent:
+1. Receives user input
+2. Plans the full sequence of steps to take
+3. Executes the steps in order, passing the outputs of past steps as inputs to future steps
 
-Often the set of tools an agent has access to is more important than a single tool.
-For this LangChain provides the concept of toolkits - groups of tools needed to accomplish specific objectives.
-There are generally around 3-5 tools in a toolkit.
-
-LangChain provides a wide set of toolkits to get started.
-For a full list of toolkits, see [here](/docs/modules/agents/toolkits/)
-
-## AgentExecutor
-
-The agent executor is the runtime for an agent.
-This is what actually calls the agent and executes the actions it chooses.
-Pseudocode for this runtime is below:
-
-```python
-next_action = agent.get_action(...)
-while next_action != AgentFinish:
-    observation = run(next_action)
-    next_action = agent.get_action(..., next_action, observation)
-return next_action
-```
-
-While this may seem simple, there are several complexities this runtime handles for you, including:
-
-1. Handling cases where the agent selects a non-existent tool
-2. Handling cases where the tool errors
-3. Handling cases where the agent produces output that cannot be parsed into a tool invocation
-4. Logging and observability at all levels (agent decisions, tool calls) either to stdout or [LangSmith](https://smith.langchain.com).
-
-## Other types of agent runtimes
-
-The `AgentExecutor` class is the main agent runtime supported by LangChain.
-However, there are other, more experimental runtimes we also support.
-These include:
-
-- [Plan-and-execute Agent](/docs/modules/agents/agent_types/plan_and_execute.html)
-- [Baby AGI](/docs/use_cases/autonomous_agents/baby_agi.html)
-- [Auto GPT](/docs/use_cases/autonomous_agents/autogpt.html)
+The most typical implementation is to have the planner be a language model, and the executor be an action agent. Read more [here](/docs/modules/agents/agent_types/plan_and_execute.html).
 
 ## Get started
 

docs/docs_skeleton/docs/modules/agents/toolkits/index.mdx

@@ -3,8 +3,8 @@ sidebar_position: 3
 ---
 # Toolkits
 
-:::info
-Head to [Integrations](/docs/integrations/toolkits/) for documentation on built-in toolkit integrations.
-:::
-
 Toolkits are collections of tools that are designed to be used together for specific tasks and have convenience loading methods.
+
+import DocCardList from "@theme/DocCardList";
+
+<DocCardList />

docs/docs_skeleton/docs/modules/agents/tools/how_to/_category_.yml

@@ -0,0 +1,2 @@
+label: 'How-to'
+position: 0

docs/docs_skeleton/docs/modules/agents/tools/index.mdx

@@ -3,10 +3,6 @@ sidebar_position: 2
 ---
 # Tools
 
-:::info
-Head to [Integrations](/docs/integrations/tools/) for documentation on built-in tool integrations.
-:::
-
 Tools are interfaces that an agent can use to interact with the world.
 
 ## Get started

docs/docs_skeleton/docs/modules/agents/tools/integrations/_category_.yml

@@ -0,0 +1 @@
+label: 'Integrations'

docs/docs_skeleton/docs/modules/callbacks/how_to/_category_.yml

@@ -0,0 +1,2 @@
+label: 'How-to'
+position: 0

docs/docs_skeleton/docs/modules/callbacks/index.mdx

@@ -3,10 +3,6 @@ sidebar_position: 5
 ---
 # Callbacks
 
-:::info
-Head to [Integrations](/docs/integrations/callbacks/) for documentation on built-in callbacks integrations with 3rd-party tools.
-:::
-
 LangChain provides a callbacks system that allows you to hook into the various stages of your LLM application. This is useful for logging, monitoring, streaming, and other tasks.
 
 import GetStarted from "@snippets/modules/callbacks/get_started.mdx"

docs/docs_skeleton/docs/modules/callbacks/integrations/_category_.yml

@@ -0,0 +1 @@
+label: 'Integrations'

docs/docs_skeleton/docs/modules/data_connection/document_loaders/how_to/_category_.yml

@@ -0,0 +1,2 @@
+label: 'How-to'
+position: 0

docs/docs_skeleton/docs/modules/data_connection/document_loaders/index.mdx

@@ -3,10 +3,6 @@ sidebar_position: 0
 ---
 # Document loaders
 
-:::info
-Head to [Integrations](/docs/integrations/document_loaders/) for documentation on built-in document loader integrations with 3rd-party tools.
-:::
-
 Use document loaders to load data from a source as `Document`'s. A `Document` is a piece of text
 and associated metadata. For example, there are document loaders for loading a simple `.txt` file, for loading the text
 contents of any web page, or even for loading a transcript of a YouTube video.

docs/docs_skeleton/docs/modules/data_connection/document_loaders/integrations/_category_.yml

@@ -0,0 +1 @@
+label: 'Integrations'

docs/docs_skeleton/docs/modules/data_connection/document_transformers/index.mdx

@@ -3,10 +3,6 @@ sidebar_position: 1
 ---
 # Document transformers
 
-:::info
-Head to [Integrations](/docs/integrations/document_transformers/) for documentation on built-in document transformer integrations with 3rd-party tools.
-:::
-
 Once you've loaded documents, you'll often want to transform them to better suit your application. The simplest example
 is you may want to split a long document into smaller chunks that can fit into your model's context window. LangChain
 has a number of built-in document transformers that make it easy to split, combine, filter, and otherwise manipulate documents.

docs/docs_skeleton/docs/modules/data_connection/retrievers/how_to/_category_.yml

@@ -0,0 +1,2 @@
+label: 'How-to'
+position: 0

docs/docs_skeleton/docs/modules/data_connection/retrievers/index.mdx

@@ -3,10 +3,6 @@ sidebar_position: 4
 ---
 # Retrievers
 
-:::info
-Head to [Integrations](/docs/integrations/retrievers/) for documentation on built-in retriever integrations with 3rd-party tools.
-:::
-
 A retriever is an interface that returns documents given an unstructured query. It is more general than a vector store.
 A retriever does not need to be able to store documents, only to return (or retrieve) it. Vector stores can be used
 as the backbone of a retriever, but there are other types of retrievers as well.

docs/docs_skeleton/docs/modules/data_connection/text_embedding/index.mdx

@@ -3,10 +3,6 @@ sidebar_position: 2
 ---
 # Text embedding models
 
-:::info
-Head to [Integrations](/docs/integrations/text_embedding/) for documentation on built-in integrations with text embedding model providers.
-:::
-
 The Embeddings class is a class designed for interfacing with text embedding models. There are lots of embedding model providers (OpenAI, Cohere, Hugging Face, etc) - this class is designed to provide a standard interface for all of them.
 
 Embeddings create a vector representation of a piece of text. This is useful because it means we can think about text in the vector space, and do things like semantic search where we look for pieces of text that are most similar in the vector space.

docs/docs_skeleton/docs/modules/data_connection/text_embedding/integrations/_category_.yml

@@ -0,0 +1 @@
+label: 'Integrations'

docs/docs_skeleton/docs/modules/data_connection/vectorstores/index.mdx

@@ -3,10 +3,6 @@ sidebar_position: 3
 ---
 # Vector stores
 
-:::info
-Head to [Integrations](/docs/integrations/vectorstores/) for documentation on built-in integrations with 3rd-party vector stores.
-:::
-
 One of the most common ways to store and search over unstructured data is to embed it and store the resulting embedding
 vectors, and then at query time to embed the unstructured query and retrieve the embedding vectors that are
 'most similar' to the embedded query. A vector store takes care of storing embedded data and performing vector search

docs/docs_skeleton/docs/modules/data_connection/vectorstores/integrations/_category_.yml

@@ -0,0 +1 @@
+label: 'Integrations'

docs/docs_skeleton/docs/modules/evaluation/comparison/index.mdx

@@ -0,0 +1,8 @@
+---
+sidebar_position: 3 
+---
+# Comparison Evaluators
+
+import DocCardList from "@theme/DocCardList";
+
+<DocCardList />

docs/docs_skeleton/docs/modules/evaluation/index.mdx

@@ -0,0 +1,28 @@
+---
+sidebar_position: 6
+---
+
+import DocCardList from "@theme/DocCardList";
+
+# Evaluation
+
+Language models can be unpredictable. This makes it challenging to ship reliable applications to production, where repeatable, useful outcomes across diverse inputs are a minimum requirement. Tests help demonstrate each component in an LLM application can produce the required or expected functionality. These tests also safeguard against regressions while you improve interconnected pieces of an integrated system. However, measuring the quality of generated text can be challenging. It can be hard to agree on the right set of metrics for your application, and it can be difficult to translate those into better performance. Furthermore, it's common to lack sufficient evaluation data adequately test the range of inputs and expected outputs for each component when you're just getting started. The LangChain community is building open source tools and guides to help address these challenges.
+
+LangChain exposes different types of evaluators for common types of evaluation. Each type has off-the-shelf implementations you can use to get started, as well as an
+ extensible API so you can create your own or contribute improvements for everyone to use. The following sections have example notebooks for you to get started.
+
+- [String Evaluators](/docs/modules/evaluation/string/): Evaluate the predicted string for a given input, usually against a reference string
+- [Trajectory Evaluators](/docs/modules/evaluation/trajectory/): Evaluate the whole trajectory of agent actions
+- [Comparison Evaluators](/docs/modules/evaluation/comparison/): Compare predictions from two runs on a common input
+
+
+This section also provides some additional examples of how you could use these evaluators for different scenarios or apply to different chain implementations in the LangChain library. Some examples include:
+
+- [Preference Scoring Chain Outputs](/docs/modules/evaluation/examples/comparisons): An example using a comparison evaluator on different models or prompts to select statistically significant differences in aggregate preference scores
+
+
+## Reference Docs
+
+For detailed information of the available evaluators, including how to instantiate, configure, and customize them. Check out the [reference documentation](https://api.python.langchain.com/en/latest/api_reference.html#module-langchain.evaluation) directly.
+
+<DocCardList />

docs/docs_skeleton/docs/modules/evaluation/string/index.mdx

@@ -1,9 +1,8 @@
 ---
-sidebar_position: 0
+sidebar_position: 2 
 ---
-
-# Callbacks
+# String Evaluators
 
 import DocCardList from "@theme/DocCardList";
 
-<DocCardList />
+<DocCardList />

docs/docs_skeleton/docs/modules/evaluation/trajectory/index.mdx

@@ -0,0 +1,8 @@
+---
+sidebar_position: 4
+---
+# Trajectory Evaluators
+
+import DocCardList from "@theme/DocCardList";
+
+<DocCardList />

docs/docs_skeleton/docs/modules/memory/how_to/_category_.yml

@@ -0,0 +1,2 @@
+label: 'How-to'
+position: 0

docs/docs_skeleton/docs/modules/memory/index.mdx

@@ -6,10 +6,6 @@ sidebar_position: 3
 
 🚧 _Docs under construction_ 🚧
 
-:::info
-Head to [Integrations](/docs/integrations/memory/) for documentation on built-in memory integrations with 3rd-party tools.
-:::
-
 By default, Chains and Agents are stateless,
 meaning that they treat each incoming query independently (like the underlying LLMs and chat models themselves).
 In some applications, like chatbots, it is essential

docs/docs_skeleton/docs/modules/memory/integrations/_category_.yml

@@ -0,0 +1 @@
+label: 'Integrations'

docs/docs_skeleton/docs/modules/model_io/models/chat/how_to/_category_.yml

@@ -0,0 +1,2 @@
+label: 'How-to'
+position: 0

docs/docs_skeleton/docs/modules/model_io/models/chat/index.mdx

@@ -3,16 +3,18 @@ sidebar_position: 1
 ---
 # Chat models
 
-:::info
-Head to [Integrations](/docs/integrations/chat/) for documentation on built-in integrations with chat model providers.
-:::
-
 Chat models are a variation on language models.
 While chat models use language models under the hood, the interface they expose is a bit different.
 Rather than expose a "text in, text out" API, they expose an interface where "chat messages" are the inputs and outputs.
 
 Chat model APIs are fairly new, so we are still figuring out the correct abstractions.
 
+The following sections of documentation are provided:
+
+- **How-to guides**: Walkthroughs of core functionality, like streaming, creating chat prompts, etc.
+
+- **Integrations**: How to use different chat model providers (OpenAI, Anthropic, etc).
+
 ## Get started
 
 import GetStarted from "@snippets/modules/model_io/models/chat/get_started.mdx"

docs/docs_skeleton/docs/modules/model_io/models/chat/integrations/_category_.yml

@@ -0,0 +1 @@
+label: 'Integrations'

docs/docs_skeleton/docs/modules/model_io/models/llms/how_to/_category_.yml

@@ -0,0 +1,2 @@
+label: 'How-to'
+position: 0

docs/docs_skeleton/docs/modules/model_io/models/llms/index.mdx

@@ -3,12 +3,14 @@ sidebar_position: 0
 ---
 # LLMs
 
-:::info
-Head to [Integrations](/docs/integrations/llms/) for documentation on built-in integrations with LLM providers.
-:::
-
 Large Language Models (LLMs) are a core component of LangChain.
-LangChain does not serve its own LLMs, but rather provides a standard interface for interacting with many different LLMs.
+LangChain does not serve it's own LLMs, but rather provides a standard interface for interacting with many different LLMs.
+
+For more detailed documentation check out our:
+
+- **How-to guides**: Walkthroughs of core functionality, like streaming, async, etc.
+
+- **Integrations**: How to use different LLM providers (OpenAI, Anthropic, etc.)
 
 ## Get started
 

docs/docs_skeleton/docs/modules/model_io/models/llms/integrations/_category_.yml

@@ -0,0 +1 @@
+label: 'Integrations'

docs/docs_skeleton/generate_api_reference_links.py

@@ -1,150 +0,0 @@
-import importlib
-import inspect
-import json
-import logging
-import os
-import re
-from pathlib import Path
-
-logging.basicConfig(level=logging.INFO)
-logger = logging.getLogger(__name__)
-# Base URL for all class documentation
-_BASE_URL = "https://api.python.langchain.com/en/latest/"
-
-# Regular expression to match Python code blocks
-code_block_re = re.compile(r"^(```python\n)(.*?)(```\n)", re.DOTALL | re.MULTILINE)
-# Regular expression to match langchain import lines
-_IMPORT_RE = re.compile(r"(from\s+(langchain\.\w+(\.\w+)*?)\s+import\s+)(\w+)")
-
-_CURRENT_PATH = Path(__file__).parent.absolute()
-# Directory where generated markdown files are stored
-_DOCS_DIR = _CURRENT_PATH / "docs"
-_JSON_PATH = _CURRENT_PATH.parent / "api_reference" / "guide_imports.json"
-
-
-def find_files(path):
-    """Find all MDX files in the given path"""
-    for root, _, files in os.walk(path):
-        for file in files:
-            if file.endswith(".mdx") or file.endswith(".md"):
-                yield os.path.join(root, file)
-
-
-def get_full_module_name(module_path, class_name):
-    """Get full module name using inspect"""
-    module = importlib.import_module(module_path)
-    class_ = getattr(module, class_name)
-    return inspect.getmodule(class_).__name__
-
-
-def main():
-    """Main function"""
-    global_imports = {}
-
-    for file in find_files(_DOCS_DIR):
-        print(f"Adding links for imports in {file}")
-
-        # replace_imports now returns the import information rather than writing it to a file
-        file_imports = replace_imports(file)
-
-        if file_imports:
-            # Use relative file path as key
-            relative_path = os.path.relpath(file, _DOCS_DIR)
-            doc_url = f"https://python.langchain.com/docs/{relative_path.replace('.mdx', '').replace('.md', '')}"
-            for import_info in file_imports:
-                doc_title = import_info["title"]
-                class_name = import_info["imported"]
-                if class_name not in global_imports:
-                    global_imports[class_name] = {}
-                global_imports[class_name][doc_title] = doc_url
-
-    # Write the global imports information to a JSON file
-    with _JSON_PATH.open("w") as f:
-        json.dump(global_imports, f)
-
-
-def _get_doc_title(data: str, file_name: str) -> str:
-    try:
-        return re.findall(r"^#\s+(.*)", data, re.MULTILINE)[0]
-    except IndexError:
-        pass
-    # Parse the rst-style titles
-    try:
-        return re.findall(r"^(.*)\n=+\n", data, re.MULTILINE)[0]
-    except IndexError:
-        return file_name
-
-
-def replace_imports(file):
-    """Replace imports in each Python code block with links to their documentation and append the import info in a comment"""
-    all_imports = []
-    with open(file, "r") as f:
-        data = f.read()
-
-    file_name = os.path.basename(file)
-    _DOC_TITLE = _get_doc_title(data, file_name)
-
-    def replacer(match):
-        # Extract the code block content
-        code = match.group(2)
-        # Replace if any import comment exists
-        # TODO: Use our own custom <code> component rather than this
-        # injection method
-        existing_comment_re = re.compile(r"^<!--IMPORTS:.*?-->\n", re.MULTILINE)
-        code = existing_comment_re.sub("", code)
-
-        # Process imports in the code block
-        imports = []
-        for import_match in _IMPORT_RE.finditer(code):
-            class_name = import_match.group(4)
-            try:
-                module_path = get_full_module_name(import_match.group(2), class_name)
-            except AttributeError as e:
-                logger.warning(f"Could not find module for {class_name}, {e}")
-                continue
-            except ImportError as e:
-                # Some CentOS OpenSSL issues can cause this to fail
-                logger.warning(f"Failed to load for class {class_name}, {e}")
-                continue
-
-            url = (
-                _BASE_URL
-                + "/"
-                + module_path.split(".")[1]
-                + "/"
-                + module_path
-                + "."
-                + class_name
-                + ".html"
-            )
-
-            # Add the import information to our list
-            imports.append(
-                {
-                    "imported": class_name,
-                    "source": import_match.group(2),
-                    "docs": url,
-                    "title": _DOC_TITLE,
-                }
-            )
-
-        if imports:
-            all_imports.extend(imports)
-            # Create a unique comment containing the import information
-            import_comment = f"<!--IMPORTS:{json.dumps(imports)}-->"
-            # Inject the import comment at the start of the code block
-            return match.group(1) + import_comment + "\n" + code + match.group(3)
-        else:
-            # If there are no imports, return the original match
-            return match.group(0)
-
-    # Use re.sub to replace each Python code block
-    data = code_block_re.sub(replacer, data)
-
-    with open(file, "w") as f:
-        f.write(data)
-    return all_imports
-
-
-if __name__ == "__main__":
-    main()

docs/docs_skeleton/src/theme/CodeBlock/index.js

@@ -21,7 +21,7 @@ function Imports({ imports }) {
       </h4>
       <ul style={{ paddingBottom: "1rem" }}>
         {imports.map(({ imported, source, docs }) => (
-          <li key={imported}>
+          <li>
             <a href={docs}>
               <span>{imported}</span>
             </a>{" "}
@@ -34,25 +34,14 @@ function Imports({ imports }) {
 }
 
 export default function CodeBlockWrapper({ children, ...props }) {
-  // Initialize imports as an empty array
-  let imports = [];
-
-  // Check if children is a string
   if (typeof children === "string") {
-    // Search for an IMPORTS comment in the code
-    const match = /<!--IMPORTS:(.*?)-->\n/.exec(children);
-    if (match) {
-      imports = JSON.parse(match[1]);
-      children = children.replace(match[0], "");
-    }
-  } else if (children.imports) {
-    imports = children.imports;
+    return <CodeBlock {...props}>{children}</CodeBlock>;
   }
 
   return (
     <>
-      <CodeBlock {...props}>{children}</CodeBlock>
-      {imports.length > 0 && <Imports imports={imports} />}
+      <CodeBlock {...props}>{children.content}</CodeBlock>
+      <Imports imports={children.imports} />
     </>
   );
-}
+}

docs/docs_skeleton/vercel_build.sh

@@ -1,32 +1,10 @@
 #!/bin/bash
 
-### See: https://github.com/urllib3/urllib3/issues/2168
-# Requests lib breaks for old SSL versions,
-# which are defaults on Amazon Linux 2 (which Vercel uses for builds)
-yum -y update
-yum remove openssl-devel -y
-yum install gcc bzip2-devel libffi-devel zlib-devel wget tar -y
-yum install openssl11 -y
-yum install openssl11-devel -y
-# Install python 3.11 to connect with openSSL 1.1.1
-wget https://www.python.org/ftp/python/3.11.4/Python-3.11.4.tgz 
-tar xzf Python-3.11.4.tgz 
-cd Python-3.11.4 
-./configure 
-make altinstall
-# Check python version
-echo "Python Version"
-python3.11 --version
 cd ..
-###
-
-# Install nbdev and generate docs
-cd ..
-python3.11 -m venv .venv
+python3 --version
+python3 -m venv .venv
 source .venv/bin/activate
-python3.11 -m pip install --upgrade pip
-python3.11 -m pip install -r vercel_requirements.txt
+python3 -m pip install -r vercel_requirements.txt
 cp -r extras/* docs_skeleton/docs
 cd docs_skeleton
 nbdoc_build
-python3.11 generate_api_reference_links.py

docs/extras/_templates/integration.mdx

@@ -31,7 +31,7 @@ There isn't any special setup for it.
 
 ## LLM
 
-See a [usage example](/docs/integrations/llms/INCLUDE_REAL_NAME).
+See a [usage example](/docs/modules/model_io/models/llms/integrations/INCLUDE_REAL_NAME.html).
 
 ```python
 from langchain.llms import integration_class_REPLACE_ME
@@ -40,7 +40,7 @@ from langchain.llms import integration_class_REPLACE_ME
 
 ## Text Embedding Models
 
-See a [usage example](/docs/integrations/text_embedding/INCLUDE_REAL_NAME)
+See a [usage example](/docs/modules/data_connection/text_embedding/integrations/INCLUDE_REAL_NAME.html)
 
 ```python
 from langchain.embeddings import integration_class_REPLACE_ME
@@ -49,7 +49,7 @@ from langchain.embeddings import integration_class_REPLACE_ME
 
 ## Chat Models
 
-See a [usage example](/docs/integrations/chat/INCLUDE_REAL_NAME)
+See a [usage example](/docs/modules/model_io/models/chat/integrations/INCLUDE_REAL_NAME.html)
 
 ```python
 from langchain.chat_models import integration_class_REPLACE_ME
@@ -57,7 +57,7 @@ from langchain.chat_models import integration_class_REPLACE_ME
 
 ## Document Loader
 
-See a [usage example](/docs/integrations/document_loaders/INCLUDE_REAL_NAME).
+See a [usage example](/docs/modules/data_connection/document_loaders/integrations/INCLUDE_REAL_NAME.html).
 
 ```python
 from langchain.document_loaders import integration_class_REPLACE_ME

docs/extras/guides/evaluation/comparison/pairwise_string.ipynb

@@ -1,381 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "2da95378",
-   "metadata": {},
-   "source": [
-    "# Pairwise String Comparison\n",
-    "\n",
-    "Often you will want to compare predictions of an LLM, Chain, or Agent for a given input. The `StringComparison` evaluators facilitate this so you can answer questions like:\n",
-    "\n",
-    "- Which LLM or prompt produces a preferred output for a given question?\n",
-    "- Which examples should I include for few-shot example selection?\n",
-    "- Which output is better to include for fintetuning?\n",
-    "\n",
-    "The simplest and often most reliable automated way to choose a preferred prediction for a given input is to use the `pairwise_string` evaluator.\n",
-    "\n",
-    "Check out the reference docs for the [PairwiseStringEvalChain](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.comparison.eval_chain.PairwiseStringEvalChain.html#langchain.evaluation.comparison.eval_chain.PairwiseStringEvalChain) for more info."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "f6790c46",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from langchain.evaluation import load_evaluator\n",
-    "\n",
-    "evaluator = load_evaluator(\"labeled_pairwise_string\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "49ad9139",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'reasoning': 'Both responses are relevant to the question asked, as they both provide a numerical answer to the question about the number of dogs in the park. However, Response A is incorrect according to the reference answer, which states that there are four dogs. Response B, on the other hand, is correct as it matches the reference answer. Neither response demonstrates depth of thought, as they both simply provide a numerical answer without any additional information or context. \\n\\nBased on these criteria, Response B is the better response.\\n',\n",
-       " 'value': 'B',\n",
-       " 'score': 0}"
-      ]
-     },
-     "execution_count": 2,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "evaluator.evaluate_string_pairs(\n",
-    "    prediction=\"there are three dogs\",\n",
-    "    prediction_b=\"4\",\n",
-    "    input=\"how many dogs are in the park?\",\n",
-    "    reference=\"four\",\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "7491d2e6-4e77-4b17-be6b-7da966785c1d",
-   "metadata": {},
-   "source": [
-    "## Methods\n",
-    "\n",
-    "\n",
-    "The pairwise string evaluator can be called using [evaluate_string_pairs](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.comparison.eval_chain.PairwiseStringEvalChain.html#langchain.evaluation.comparison.eval_chain.PairwiseStringEvalChain.evaluate_string_pairs) (or async [aevaluate_string_pairs](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.comparison.eval_chain.PairwiseStringEvalChain.html#langchain.evaluation.comparison.eval_chain.PairwiseStringEvalChain.aevaluate_string_pairs)) methods, which accept:\n",
-    "\n",
-    "- prediction (str) – The predicted response of the first model, chain, or prompt.\n",
-    "- prediction_b (str) – The predicted response of the second model, chain, or prompt.\n",
-    "- input (str) – The input question, prompt, or other text.\n",
-    "- reference (str) – (Only for the labeled_pairwise_string variant) The reference response.\n",
-    "\n",
-    "They return a dictionary with the following values:\n",
-    "- value: 'A' or 'B', indicating whether `prediction` or `prediction_b` is preferred, respectively\n",
-    "- score: Integer 0 or 1 mapped from the 'value', where a score of 1 would mean that the first `prediction` is preferred, and a score of 0 would mean `prediction_b` is preferred.\n",
-    "- reasoning: String \"chain of thought reasoning\" from the LLM generated prior to creating the score"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "ed353b93-be71-4479-b9c0-8c97814c2e58",
-   "metadata": {},
-   "source": [
-    "## Without References\n",
-    "\n",
-    "When references aren't available, you can still predict the preferred response.\n",
-    "The results will reflect the evaluation model's preference, which is less reliable and may result\n",
-    "in preferences that are factually incorrect."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "586320da",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from langchain.evaluation import load_evaluator\n",
-    "\n",
-    "evaluator = load_evaluator(\"pairwise_string\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "7f56c76e-a39b-4509-8b8a-8a2afe6c3da1",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'reasoning': 'Both responses are correct and relevant to the question. However, Response B is more helpful and insightful as it provides a more detailed explanation of what addition is. Response A is correct but lacks depth as it does not explain what the operation of addition entails. \\n\\nFinal Decision: [[B]]',\n",
-       " 'value': 'B',\n",
-       " 'score': 0}"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "evaluator.evaluate_string_pairs(\n",
-    "    prediction=\"Addition is a mathematical operation.\",\n",
-    "    prediction_b=\"Addition is a mathematical operation that adds two numbers to create a third number, the 'sum'.\",\n",
-    "    input=\"What is addition?\",\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "4a09b21d-9851-47e8-93d3-90044b2945b0",
-   "metadata": {
-    "tags": []
-   },
-   "source": [
-    "## Defining the Criteria\n",
-    "\n",
-    "By default, the LLM is instructed to select the 'preferred' response based on helpfulness, relevance, correctness, and depth of thought. You can customize the criteria by passing in a `criteria` argument, where the criteria could take any of the following forms:\n",
-    "- [`Criteria`](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.criteria.eval_chain.Criteria.html#langchain.evaluation.criteria.eval_chain.Criteria) enum or its string value - to use one of the default criteria and their descriptions\n",
-    "- [Constitutional principal](https://api.python.langchain.com/en/latest/chains/langchain.chains.constitutional_ai.models.ConstitutionalPrinciple.html#langchain.chains.constitutional_ai.models.ConstitutionalPrinciple) - use one any of the constitutional principles defined in langchain\n",
-    "- Dictionary: a list of custom criteria, where the key is the name of the criteria, and the value is the description.\n",
-    "- A list of criteria or constitutional principles - to combine multiple criteria in one.\n",
-    "\n",
-    "Below is an example for determining preferred writing responses based on a custom style."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "8539e7d9-f7b0-4d32-9c45-593a7915c093",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "custom_criteria = {\n",
-    "    \"simplicity\": \"Is the language straightforward and unpretentious?\",\n",
-    "    \"clarity\": \"Are the sentences clear and easy to understand?\",\n",
-    "    \"precision\": \"Is the writing precise, with no unnecessary words or details?\",\n",
-    "    \"truthfulness\": \"Does the writing feel honest and sincere?\",\n",
-    "    \"subtext\": \"Does the writing suggest deeper meanings or themes?\",\n",
-    "}\n",
-    "evaluator = load_evaluator(\"pairwise_string\", criteria=custom_criteria)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "fec7bde8-fbdc-4730-8366-9d90d033c181",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'reasoning': 'Response A is simple, clear, and precise. It uses straightforward language to convey a deep and sincere message about families. The metaphor of joy and sorrow as music is effective and easy to understand.\\n\\nResponse B, on the other hand, is more complex and less clear. The language is more pretentious, with words like \"domicile,\" \"resounds,\" \"abode,\" \"dissonant,\" and \"elegy.\" While it conveys a similar message to Response A, it does so in a more convoluted way. The precision is also lacking due to the use of unnecessary words and details.\\n\\nBoth responses suggest deeper meanings or themes about the shared joy and unique sorrow in families. However, Response A does so in a more effective and accessible way.\\n\\nTherefore, the better response is [[A]].',\n",
-       " 'value': 'A',\n",
-       " 'score': 1}"
-      ]
-     },
-     "execution_count": 6,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "evaluator.evaluate_string_pairs(\n",
-    "    prediction=\"Every cheerful household shares a similar rhythm of joy; but sorrow, in each household, plays a unique, haunting melody.\",\n",
-    "    prediction_b=\"Where one finds a symphony of joy, every domicile of happiness resounds in harmonious,\"\n",
-    "    \" identical notes; yet, every abode of despair conducts a dissonant orchestra, each\"\n",
-    "    \" playing an elegy of grief that is peculiar and profound to its own existence.\",\n",
-    "    input=\"Write some prose about families.\",\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "a25b60b2-627c-408a-be4b-a2e5cbc10726",
-   "metadata": {},
-   "source": [
-    "## Customize the LLM\n",
-    "\n",
-    "By default, the loader uses `gpt-4` in the evaluation chain. You can customize this when loading."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "de84a958-1330-482b-b950-68bcf23f9e35",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.chat_models import ChatAnthropic\n",
-    "\n",
-    "llm = ChatAnthropic(temperature=0)\n",
-    "\n",
-    "evaluator = load_evaluator(\"labeled_pairwise_string\", llm=llm)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "e162153f-d50a-4a7c-a033-019dabbc954c",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'reasoning': 'Here is my assessment:\\n\\nResponse B is more helpful, insightful, and accurate than Response A. Response B simply states \"4\", which directly answers the question by providing the exact number of dogs mentioned in the reference answer. In contrast, Response A states \"there are three dogs\", which is incorrect according to the reference answer. \\n\\nIn terms of helpfulness, Response B gives the precise number while Response A provides an inaccurate guess. For relevance, both refer to dogs in the park from the question. However, Response B is more correct and factual based on the reference answer. Response A shows some attempt at reasoning but is ultimately incorrect. Response B requires less depth of thought to simply state the factual number.\\n\\nIn summary, Response B is superior in terms of helpfulness, relevance, correctness, and depth. My final decision is: [[B]]\\n',\n",
-       " 'value': 'B',\n",
-       " 'score': 0}"
-      ]
-     },
-     "execution_count": 8,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "evaluator.evaluate_string_pairs(\n",
-    "    prediction=\"there are three dogs\",\n",
-    "    prediction_b=\"4\",\n",
-    "    input=\"how many dogs are in the park?\",\n",
-    "    reference=\"four\",\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "e0e89c13-d0ad-4f87-8fcb-814399bafa2a",
-   "metadata": {},
-   "source": [
-    "## Customize the Evaluation Prompt\n",
-    "\n",
-    "You can use your own custom evaluation prompt to add more task-specific instructions or to instruct the evaluator to score the output.\n",
-    "\n",
-    "*Note: If you use a prompt that expects generates a result in a unique format, you may also have to pass in a custom output parser (`output_parser=your_parser()`) instead of the default `PairwiseStringResultOutputParser`"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "fb817efa-3a4d-439d-af8c-773b89d97ec9",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from langchain.prompts import PromptTemplate\n",
-    "\n",
-    "prompt_template = PromptTemplate.from_template(\n",
-    "    \"\"\"Given the input context, which do you prefer: A or B?\n",
-    "Evaluate based on the following criteria:\n",
-    "{criteria}\n",
-    "Reason step by step and finally, respond with either [[A]] or [[B]] on its own line.\n",
-    "\n",
-    "DATA\n",
-    "----\n",
-    "input: {input}\n",
-    "reference: {reference}\n",
-    "A: {prediction}\n",
-    "B: {prediction_b}\n",
-    "---\n",
-    "Reasoning:\n",
-    "\n",
-    "\"\"\"\n",
-    ")\n",
-    "evaluator = load_evaluator(\n",
-    "    \"labeled_pairwise_string\", prompt=prompt_template\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "d40aa4f0-cfd5-4cb4-83c8-8d2300a04c2f",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "input_variables=['prediction', 'reference', 'prediction_b', 'input'] output_parser=None partial_variables={'criteria': 'helpfulness: Is the submission helpful, insightful, and appropriate?\\nrelevance: Is the submission referring to a real quote from the text?\\ncorrectness: Is the submission correct, accurate, and factual?\\ndepth: Does the submission demonstrate depth of thought?'} template='Given the input context, which do you prefer: A or B?\\nEvaluate based on the following criteria:\\n{criteria}\\nReason step by step and finally, respond with either [[A]] or [[B]] on its own line.\\n\\nDATA\\n----\\ninput: {input}\\nreference: {reference}\\nA: {prediction}\\nB: {prediction_b}\\n---\\nReasoning:\\n\\n' template_format='f-string' validate_template=True\n"
-     ]
-    }
-   ],
-   "source": [
-    "# The prompt was assigned to the evaluator\n",
-    "print(evaluator.prompt)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "9467bb42-7a31-4071-8f66-9ed2c6f06dcd",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'reasoning': 'Helpfulness: Both A and B are helpful as they provide a direct answer to the question.\\nRelevance: A is relevant as it refers to the correct name of the dog from the text. B is not relevant as it provides a different name.\\nCorrectness: A is correct as it accurately states the name of the dog. B is incorrect as it provides a different name.\\nDepth: Both A and B demonstrate a similar level of depth as they both provide a straightforward answer to the question.\\n\\nGiven these evaluations, the preferred response is:\\n',\n",
-       " 'value': 'A',\n",
-       " 'score': 1}"
-      ]
-     },
-     "execution_count": 11,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "evaluator.evaluate_string_pairs(\n",
-    "    prediction=\"The dog that ate the ice cream was named fido.\",\n",
-    "    prediction_b=\"The dog's name is spot\",\n",
-    "    input=\"What is the name of the dog that ate the ice cream?\",\n",
-    "    reference=\"The dog's name is fido\",\n",
-    ")"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.2"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/extras/guides/evaluation/string/Untitled.ipynb

@@ -1,318 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "bce7335e-f3b2-44f3-90cc-8c0a23a89a21",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "from langchain.agents import load_tools\n",
-    "from langchain.agents import initialize_agent\n",
-    "from langchain.chat_models import ChatOpenAI\n",
-    "from langchain.utilities import GoogleSearchAPIWrapper\n",
-    "from langchain.schema import (\n",
-    "    SystemMessage,\n",
-    "    HumanMessage,\n",
-    "    AIMessage\n",
-    ")\n",
-    "\n",
-    "# os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "# os.environ[\"LANGCHAIN_ENDPOINT\"] = \"https://api.smith.langchain.com\"\n",
-    "# os.environ[\"LANGCHAIN_API_KEY\"] = \"******\"\n",
-    "# os.environ[\"LANGCHAIN_PROJECT\"] = \"Jarvis\"\n",
-    "\n",
-    "\n",
-    "prefix_messages = [{\"role\": \"system\", \"content\": \"You are a helpful discord Chatbot.\"}]\n",
-    "\n",
-    "llm = ChatOpenAI(model_name='gpt-3.5-turbo', \n",
-    "             temperature=0.5, \n",
-    "             max_tokens = 2000)\n",
-    "tools = load_tools([\"serpapi\", \"llm-math\"], llm=llm)\n",
-    "agent = initialize_agent(tools,\n",
-    "                         llm,\n",
-    "                         agent=\"zero-shot-react-description\",\n",
-    "                         verbose=True,\n",
-    "                         handle_parsing_errors=True\n",
-    "                         )\n",
-    "\n",
-    "\n",
-    "async def on_ready():\n",
-    "    print(f'{bot.user} has connected to Discord!')\n",
-    "\n",
-    "async def on_message(message):\n",
-    "\n",
-    "    print(\"Detected bot name in message:\", message.content)\n",
-    "\n",
-    "    # Capture the output of agent.run() in the response variable\n",
-    "    response = agent.run(message.content)\n",
-    "\n",
-    "    while response:\n",
-    "        print(response)\n",
-    "        chunk, response = response[:2000], response[2000:]\n",
-    "        print(f\"Chunk: {chunk}\")\n",
-    "    print(\"Response sent.\")\n",
-    "\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 22,
-   "id": "1551ce9f-b6de-4035-b6d6-825722823b48",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from dataclasses import dataclass\n",
-    "@dataclass\n",
-    "class Message:\n",
-    "    content: str"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 23,
-   "id": "6e6859ec-8544-4407-9663-6b53c0092903",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Detected bot name in message: Hi AI, how are you today?\n",
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3mThis question is not something that can be answered using the available tools.\n",
-      "Action: N/A\u001b[0m\n",
-      "Observation: Invalid Format: Missing 'Action Input:' after 'Action:'\n",
-      "Thought:\u001b[32;1m\u001b[1;3mI need to follow the correct format for answering questions.\n",
-      "Action: N/A\u001b[0m\n",
-      "Observation: Invalid Format: Missing 'Action Input:' after 'Action:'\n",
-      "Thought:\u001b[32;1m\u001b[1;3mI need to follow the correct format for answering questions.\n",
-      "Action: N/A\u001b[0m\n",
-      "Observation: Invalid Format: Missing 'Action Input:' after 'Action:'\n",
-      "Thought:\u001b[32;1m\u001b[1;3mI need to follow the correct format for answering questions.\n",
-      "Action: N/A\u001b[0m\n",
-      "Observation: Invalid Format: Missing 'Action Input:' after 'Action:'\n",
-      "Thought:\u001b[32;1m\u001b[1;3mI need to follow the correct format for answering questions.\n",
-      "Action: N/A\u001b[0m\n",
-      "Observation: Invalid Format: Missing 'Action Input:' after 'Action:'\n",
-      "Thought:\u001b[32;1m\u001b[1;3mI need to follow the correct format for answering questions.\n",
-      "Action: N/A\u001b[0m\n",
-      "Observation: Invalid Format: Missing 'Action Input:' after 'Action:'\n",
-      "Thought:\u001b[32;1m\u001b[1;3mI need to follow the correct format for answering questions.\n",
-      "Action: N/A\u001b[0m\n",
-      "Observation: Invalid Format: Missing 'Action Input:' after 'Action:'\n",
-      "Thought:\u001b[32;1m\u001b[1;3mI need to follow the correct format for answering questions.\n",
-      "Action: N/A\u001b[0m\n",
-      "Observation: Invalid Format: Missing 'Action Input:' after 'Action:'\n",
-      "Thought:\u001b[32;1m\u001b[1;3mI need to follow the correct format for answering questions.\n",
-      "Action: N/A\u001b[0m\n",
-      "Observation: Invalid Format: Missing 'Action Input:' after 'Action:'\n",
-      "Thought:\u001b[32;1m\u001b[1;3mI need to follow the correct format for answering questions.\n",
-      "Action: N/A\u001b[0m\n",
-      "Observation: Invalid Format: Missing 'Action Input:' after 'Action:'\n",
-      "Thought:\u001b[32;1m\u001b[1;3mI need to follow the correct format for answering questions.\n",
-      "Action: N/A\u001b[0m\n",
-      "Observation: Invalid Format: Missing 'Action Input:' after 'Action:'\n",
-      "Thought:\u001b[32;1m\u001b[1;3mI need to follow the correct format for answering questions.\n",
-      "Action: N/A\u001b[0m\n",
-      "Observation: Invalid Format: Missing 'Action Input:' after 'Action:'\n",
-      "Thought:\u001b[32;1m\u001b[1;3mI need to follow the correct format for answering questions.\n",
-      "Action: N/A\u001b[0m\n",
-      "Observation: Invalid Format: Missing 'Action Input:' after 'Action:'\n",
-      "Thought:\u001b[32;1m\u001b[1;3mI need to follow the correct format for answering questions.\n",
-      "Action: N/A\u001b[0m\n",
-      "Observation: Invalid Format: Missing 'Action Input:' after 'Action:'\n",
-      "Thought:\u001b[32;1m\u001b[1;3mI need to follow the correct format for answering questions.\n",
-      "Action: N/A\u001b[0m\n",
-      "Observation: Invalid Format: Missing 'Action Input:' after 'Action:'\n",
-      "Thought:\u001b[32;1m\u001b[1;3m\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n",
-      "Agent stopped due to iteration limit or time limit.\n",
-      "Chunk: Agent stopped due to iteration limit or time limit.\n",
-      "Response sent.\n"
-     ]
-    }
-   ],
-   "source": [
-    "await on_message(Message(content=\"Hi AI, how are you today?\"))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 24,
-   "id": "b850294c-7f8f-4e79-adcf-47e4e3a898df",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from langsmith import Client\n",
-    "\n",
-    "client = Client()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 25,
-   "id": "6d089ddc-69bc-45a8-b8db-9962e4f1f5ee",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from itertools import islice\n",
-    "\n",
-    "runs = list(islice(client.list_runs(), 10))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 38,
-   "id": "f0349fac-5a98-400f-ba03-61ed4e1332be",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "runs = sorted(runs, key=lambda x: x.start_time, reverse=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 26,
-   "id": "02f133f0-39ee-4b46-b443-12c1f9b76fff",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "ids = [run.id for run in runs]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 39,
-   "id": "3366dce4-0c38-4a7d-8111-046a58b24917",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "runs2 = list(client.list_runs(id=ids))\n",
-    "runs2 = sorted(runs2, key=lambda x: x.start_time, reverse=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 42,
-   "id": "82915b90-39a0-47d6-9121-56a13f210f52",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "['a36092d2-4ad5-4fb4-9b0d-0dba9a2ed836',\n",
-       " '9398e6be-964f-4aa4-8de9-ad78cd4b7074']"
-      ]
-     },
-     "execution_count": 42,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "[str(x) for x in ids[:2]]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 48,
-   "id": "f610ec91-dc48-4a17-91c5-5c4675c77abc",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from langsmith.run_helpers import traceable\n",
-    "\n",
-    "@traceable(run_type=\"llm\", name=\"\"\"<iframe width=\"560\" height=\"315\" src=\"https://www.youtube.com/embed/dQw4w9WgXcQ?start=5\" title=\"YouTube video player\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share\" allowfullscreen></iframe>\"\"\")\n",
-    "def foo():\n",
-    "    return \"bar\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 49,
-   "id": "bd317bd7-8b2a-433a-8ec3-098a84ba8e64",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'bar'"
-      ]
-     },
-     "execution_count": 49,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "foo()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 52,
-   "id": "b142519b-6885-415c-83b9-4a346fb90589",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from langchain.llms import AzureOpenAI"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "5c50bb2b-72b8-4322-9b16-d857ecd9f347",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.2"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/extras/integrations/airbyte.mdx

@@ -22,7 +22,7 @@ Have `docker desktop` installed.
 
 ## Document Loader
 
-See a [usage example](/docs/integrations/document_loaders/airbyte_json).
+See a [usage example](/docs/modules/data_connection/document_loaders/integrations/airbyte_json.html).
 
 ```python
 from langchain.document_loaders import AirbyteJSONLoader

docs/extras/integrations/airtable.md

@@ -25,4 +25,4 @@ pip install pyairtable
 from langchain.document_loaders import AirtableLoader
 ```
 
-See an [example](/docs/integrations/document_loaders/airtable.html).
+See an [example](/docs/modules/data_connection/document_loaders/integrations/airtable.html).

docs/extras/integrations/aleph_alpha.mdx

@@ -21,7 +21,7 @@ ALEPH_ALPHA_API_KEY = getpass()
 
 ## LLM
 
-See a [usage example](/docs/integrations/llms/aleph_alpha).
+See a [usage example](/docs/modules/model_io/models/llms/integrations/aleph_alpha.html).
 
 ```python
 from langchain.llms import AlephAlpha
@@ -29,7 +29,7 @@ from langchain.llms import AlephAlpha
 
 ## Text Embedding Models
 
-See a [usage example](/docs/integrations/text_embedding/aleph_alpha).
+See a [usage example](/docs/modules/data_connection/text_embedding/integrations/aleph_alpha.html).
 
 ```python
 from langchain.embeddings import AlephAlphaSymmetricSemanticEmbedding, AlephAlphaAsymmetricSemanticEmbedding

docs/extras/integrations/amazon_api_gateway.mdx

@@ -6,7 +6,7 @@ API Gateway handles all the tasks involved in accepting and processing up to hun
 
 ## LLM
 
-See a [usage example](/docs/integrations/llms/amazon_api_gateway_example).
+See a [usage example](/docs/modules/model_io/models/llms/integrations/amazon_api_gateway_example.html).
 
 ```python
 from langchain.llms import AmazonAPIGateway

docs/extras/integrations/analyticdb.mdx

@@ -12,4 +12,4 @@ To import this vectorstore:
 from langchain.vectorstores import AnalyticDB
 ```
 
-For a more detailed walkthrough of the AnalyticDB wrapper, see [this notebook](/docs/integrations/vectorstores/analyticdb.html)
+For a more detailed walkthrough of the AnalyticDB wrapper, see [this notebook](/docs/modules/data_connection/vectorstores/integrations/analyticdb.html)

docs/extras/integrations/annoy.mdx

@@ -11,7 +11,7 @@ pip install annoy
 
 ## Vectorstore
 
-See a [usage example](/docs/integrations/vectorstores/annoy).
+See a [usage example](/docs/modules/data_connection/vectorstores/integrations/annoy.html).
 
 ```python
 from langchain.vectorstores import Annoy

docs/extras/integrations/apify.mdx

@@ -32,7 +32,7 @@ You can use the `ApifyWrapper` to run Actors on the Apify platform.
 from langchain.utilities import ApifyWrapper
 ```
 
-For a more detailed walkthrough of this wrapper, see [this notebook](/docs/integrations/tools/apify.html).
+For a more detailed walkthrough of this wrapper, see [this notebook](/docs/modules/agents/tools/integrations/apify.html).
 
 
 ### Loader
@@ -43,4 +43,4 @@ You can also use our `ApifyDatasetLoader` to get data from Apify dataset.
 from langchain.document_loaders import ApifyDatasetLoader
 ```
 
-For a more detailed walkthrough of this loader, see [this notebook](/docs/integrations/document_loaders/apify_dataset.html).
+For a more detailed walkthrough of this loader, see [this notebook](/docs/modules/data_connection/document_loaders/integrations/apify_dataset.html).

docs/extras/integrations/arxiv.mdx

@@ -21,7 +21,7 @@ pip install pymupdf
 
 ## Document Loader
 
-See a [usage example](/docs/integrations/document_loaders/arxiv).
+See a [usage example](/docs/modules/data_connection/document_loaders/integrations/arxiv.html).
 
 ```python
 from langchain.document_loaders import ArxivLoader
@@ -29,7 +29,7 @@ from langchain.document_loaders import ArxivLoader
 
 ## Retriever
 
-See a [usage example](/docs/integrations/retrievers/arxiv).
+See a [usage example](/docs/modules/data_connection/retrievers/integrations/arxiv.html).
 
 ```python
 from langchain.retrievers import ArxivRetriever

docs/extras/integrations/atlas.mdx

@@ -24,4 +24,4 @@ To import this vectorstore:
 from langchain.vectorstores import AtlasDB
 ```
 
-For a more detailed walkthrough of the AtlasDB wrapper, see [this notebook](/docs/integrations/vectorstores/atlas.html)
+For a more detailed walkthrough of the AtlasDB wrapper, see [this notebook](/docs/modules/data_connection/vectorstores/integrations/atlas.html)

docs/extras/integrations/awadb.md

@@ -18,4 +18,4 @@ whether for semantic search or example selection.
 from langchain.vectorstores import AwaDB
 ```
 
-For a more detailed walkthrough of the AwaDB wrapper, see [here](/docs/integrations/vectorstores/awadb.html).
+For a more detailed walkthrough of the AwaDB wrapper, see [here](/docs/modules/data_connection/vectorstores/integrations/awadb.html).

docs/extras/integrations/aws_s3.mdx

@@ -16,9 +16,9 @@ pip install boto3
 
 ## Document Loader
 
-See a [usage example for S3DirectoryLoader](/docs/integrations/document_loaders/aws_s3_directory.html).
+See a [usage example for S3DirectoryLoader](/docs/modules/data_connection/document_loaders/integrations/aws_s3_directory.html).
 
-See a [usage example for S3FileLoader](/docs/integrations/document_loaders/aws_s3_file.html).
+See a [usage example for S3FileLoader](/docs/modules/data_connection/document_loaders/integrations/aws_s3_file.html).
 
 ```python
 from langchain.document_loaders import S3DirectoryLoader, S3FileLoader

docs/extras/integrations/azlyrics.mdx

@@ -9,7 +9,7 @@ There isn't any special setup for it.
 
 ## Document Loader
 
-See a [usage example](/docs/integrations/document_loaders/azlyrics).
+See a [usage example](/docs/modules/data_connection/document_loaders/integrations/azlyrics.html).
 
 ```python
 from langchain.document_loaders import AZLyricsLoader

docs/extras/integrations/azure_blob_storage.mdx

@@ -23,13 +23,13 @@ pip install azure-storage-blob
 
 ## Document Loader
 
-See a [usage example for the Azure Blob Storage](/docs/integrations/document_loaders/azure_blob_storage_container.html).
+See a [usage example for the Azure Blob Storage](/docs/modules/data_connection/document_loaders/integrations/azure_blob_storage_container.html).
 
 ```python
 from langchain.document_loaders import AzureBlobStorageContainerLoader
 ```
 
-See a [usage example for the Azure Files](/docs/integrations/document_loaders/azure_blob_storage_file.html).
+See a [usage example for the Azure Files](/docs/modules/data_connection/document_loaders/integrations/azure_blob_storage_file.html).
 
 ```python
 from langchain.document_loaders import AzureBlobStorageFileLoader

docs/extras/integrations/azure_cognitive_search_.mdx

@@ -17,7 +17,7 @@ See [set up instructions](https://learn.microsoft.com/en-us/azure/search/search-
 
 ## Retriever
 
-See a [usage example](/docs/integrations/retrievers/azure_cognitive_search).
+See a [usage example](/docs/modules/data_connection/retrievers/integrations/azure_cognitive_search.html).
 
 ```python
 from langchain.retrievers import AzureCognitiveSearchRetriever

docs/extras/integrations/azure_openai.mdx

@@ -27,7 +27,7 @@ os.environ["OPENAI_API_VERSION"] = "2023-05-15"
 
 ## LLM
 
-See a [usage example](/docs/integrations/llms/azure_openai_example).
+See a [usage example](/docs/modules/model_io/models/llms/integrations/azure_openai_example.html).
 
 ```python
 from langchain.llms import AzureOpenAI
@@ -35,7 +35,7 @@ from langchain.llms import AzureOpenAI
 
 ## Text Embedding Models
 
-See a [usage example](/docs/integrations/text_embedding/azureopenai)
+See a [usage example](/docs/modules/data_connection/text_embedding/integrations/azureopenai.html)
 
 ```python
 from langchain.embeddings import OpenAIEmbeddings
@@ -43,7 +43,7 @@ from langchain.embeddings import OpenAIEmbeddings
 
 ## Chat Models
 
-See a [usage example](/docs/integrations/chat/azure_chat_openai)
+See a [usage example](/docs/modules/model_io/models/chat/integrations/azure_chat_openai.html)
 
 ```python
 from langchain.chat_models import AzureChatOpenAI