docs: Update docs_v2 with integrations and installation

Squashed commit of the following: commit cd04736756d9ec9f4b9533c85007d474db8ba558 Author: Douglas Bett <bettdalpha@gmail.com> Date: Wed Sep 18 08:53:39 2024 +0300 update sidebars.js commit d3fed3c17185fc29f1a4d7221f6be86265d60cf3 Author: Douglas Bett <bettdalpha@gmail.com> Date: Wed Sep 18 08:53:20 2024 +0300 Add installation docs commit 36fd583db116c69be132edaa5a4ec092bbbfbd92 Author: Douglas Bett <bettdalpha@gmail.com> Date: Wed Sep 18 08:52:09 2024 +0300 Add concepts documentation commit 48317baef7119d8dd0d1b5892d21a87ec69818c8 Author: Douglas Bett <bettdalpha@gmail.com> Date: Wed Sep 18 07:43:23 2024 +0300 Add integrations commit bedfcda18e10af33cf64a95ccf9925226233e098 Author: Douglas Bett <bettdalpha@gmail.com> Date: Wed Sep 18 07:42:57 2024 +0300 switch to autogenerated sidebar
davidmigloz · Sep 18, 2024 · 65bcef8 · 65bcef8
1 parent 90c5a0f
commit 65bcef8
Show file tree

Hide file tree

Showing 19 changed files with 2,437 additions and 75 deletions.
diff --git a/docs_v2/docs/03-how_to/01-installation.md b/docs_v2/docs/03-how_to/01-installation.md
@@ -1,40 +1,51 @@
 # Installation
+Langchain as a framework consists of a number of packages. They're split into different packages allowing you to choose exactly what pieces of the framework to install and use. 
 
-LangChain as a framework consists of a number of packages. 
-
-### [`langchain_core`](https://pub.dev/packages/langchain_core)
-This package contains base abstractions of different components and ways to compose them together.
-The interfaces for core components like LLMs, vector stores, retrievers and more are defined here.
-No third party integrations are defined here.
-
-> Depend on this package to build frameworks on top of LangChain.dart or to interoperate with it.
+## Installing essential Langchain.dart packages
 
 ### [`langchain`](https://pub.dev/packages/langchain)
-
 Contains higher-level and use-case specific chains, agents, and retrieval algorithms that are at the core of the application's cognitive architecture.
 
-> Depend on this package to build LLM applications with LangChain.dart.  
+> Depend on this package to build LLM applications with Langchain.dart.  
 > 
 > This package exposes `langchain_core` so you don't need to depend on it explicitly.
 
-### [`langchain_community`](https://pub.dev/packages/langchain_community)
+```bash
+dart pub add langchain
+```
 
-Contains third-party integrations and community-contributed components that are not part of the core LangChain.dart API.
+### [`langchain_core`](https://pub.dev/packages/langchain_core)
+This package contains base abstractions of different components and ways to compose them together.
+The interfaces for core components like LLMs, vector stores, retrievers and more are defined here.
+> Depend on this package to build frameworks on top of Langchain.dart or to interoperate with it.
 
-> Depend on this package if you want to use any of the integrations or components it provides.
+To install this package in your Dart or Flutter project
+```bash
+dart pub add langchain_core
+```
 
-To start using LangChain.dart, add `langchain` as a dependency to your `pubspec.yaml` file. 
-```yaml
-dependencies:
-  langchain: {version}
-  langchain_community: {version}
-  langchain_openai: {version}
-  langchain_google: {version}
-  ...
+### [`langchain_community`](https://pub.dev/packages/langchain_community)
+Contains third-party integrations and community-contributed components that are not part of the core Langchain.dart API.
+> Depend on this package if you want to use any of the integrations or components it provides like CSV,JSON,Text or HTML loaders and more.  
+
+```bash
+dart pub add langchain langchain_community
 ```
 
-Let's say you're using [OpenAI](https://platform.openai.com/), you'd choose the `langchain_openai` package.
+## Integration packages
+Certain integrations like OpenAI and Anthropic have their own packages. Any integrations that require their own package will be documented as such in the Integration docs.
+<!-- //TODO(bettdouglas): Add Integration Docs -->
 
+Let's say you're using [OpenAI](https://platform.openai.com/), install the `langchain_openai` package.
+```bash
+dart pub add langchain langchain_community langchain_openai
+```
+
+Let's say you want Google integration to use (GoogleAI, VertexAI, Gemini etc), install the `langchain_google` package. 
+```bash
+dart pub add langchain langchain_community langchain_google
+```
+The following table contains the list of existing Langchain.dart integration packages. 
 
 | Package                                                             | Version                                                                                                                      | Description                                                                                                                                                                                             |
 |---------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
@@ -49,3 +60,18 @@ Let's say you're using [OpenAI](https://platform.openai.com/), you'd choose the
 | [langchain_pinecone](https://pub.dev/packages/langchain_pinecone)   | [![langchain_pinecone](https://img.shields.io/pub/v/langchain_pinecone.svg)](https://pub.dev/packages/langchain_pinecone)    | Pinecone vector database integration                                                                                                                                                                    |
 | [langchain_chroma](https://pub.dev/packages/langchain_chroma)       | [![langchain_chroma](https://img.shields.io/pub/v/langchain_chroma.svg)](https://pub.dev/packages/langchain_chroma)          | Chroma vector database integration                                                                                                                                                                      |
 | [langchain_supabase](https://pub.dev/packages/langchain_supabase)   | [![langchain_supabase](https://img.shields.io/pub/v/langchain_supabase.svg)](https://pub.dev/packages/langchain_supabase)    | Supabase Vector database integration                                                                                                                                                                    |
+## Documentation
+
+Detailed documentation for various integrations can be found in the `/docs/05-integration/` directory:
+
+- [Anthropic](/docs/integrations/anthropic)
+- [Anyscale](/docs/integrations/anyscale)
+- [Firebase VertexAI](/docs/integrations/firebase_vertex_ai)
+- [GCP VertexAI](/docs/integrations/gcp_vertex_ai)
+- [GoogleAI](/docs/integrations/googleai)
+- [MistralAI](/docs/integrations/mistralai)
+- [Ollama](/docs/integrations/ollama)
+- [OpenRouter](/docs/integrations/open_router)
+- [OpenAI](/docs/integrations/openai)
+- [PrEM](/docs/integrations/prem)
+- [TogetherAI](/docs/integrations/together_ai)
diff --git a/docs_v2/docs/03-how_to/02-structured_output.md b/docs_v2/docs/03-how_to/02-structured_output.md
@@ -0,0 +1,14 @@
+---
+sidebar_position: 3
+keywords: [structured output, json, information extraction, with_structured_output]
+---
+# How to return structured data from a model
+
+> This guide assumes familiarity with the following concepts:
+> - [Chat models](/docs/concepts/#chat-models)
+> - [Function/tool calling](/docs/concepts/#functiontool-calling)
+
+
+It is often useful to have a model return output that matches a specific schema. One common use-case is extracting data from text to insert into a database or use with some other downstream system. This guide covers a few strategies for getting structured outputs from a model.
+
+