LangChain.Providers.Amazon.Bedrock

🦜️🔗 LangChain

⚡ Building applications with LLMs through composability ⚡
C# implementation of LangChain. We try to be as close to the original as possible in terms of abstractions, but are open to new entities.

While the SemanticKernel is good and we will use it wherever possible, we believe that it has many limitations and based on Microsoft technologies. We proceed from the position of the maximum choice of available options and are open to using third-party libraries within individual implementations.

I want to note:

• I’m unlikely to be able to make serious progress alone, so my goal is to unite the efforts of C# developers to create a C# version of LangChain and control the quality of the final project
• I try to accept any Pull Request within 24 hours (of course, it depends, but I will try)
• I'm also looking for developers to join the core team. I will sponsor them whenever possible and also share any money received.
• I also respond quite quickly on Discord for any questions related to the project

Usage

You can use our wiki to get started: https://github.com/tryAGI/LangChain/wiki
Also see examples for example usage or tests.

// Price to run from zero(create embeddings and request to LLM): 0,015$
// Price to re-run if database is exists: 0,0004$
// Dependencies: LangChain, LangChain.Databases.Sqlite, LangChain.Sources.Pdf
var provider = new OpenAiProvider("OPENAI_API_KEY");
var llm = new Gpt35TurboModel(provider);
var embeddings = new TextEmbeddingV3SmallModel(provider);

if (!File.Exists("vectors.db"))
{
    var documents = await PdfPigPdfSource.FromUriAsync(
        new Uri("https://canonburyprimaryschool.co.uk/wp-content/uploads/2016/01/Joanne-K.-Rowling-Harry-Potter-Book-1-Harry-Potter-and-the-Philosophers-Stone-EnglishOnlineClub.com_.pdf"));
    
    await SQLiteVectorStore.CreateIndexFromDocuments(
        embeddings: gpt35,
        documents: documents,
        filename: "vectors.db",
        tableName: "vectors",
        textSplitter: new RecursiveCharacterTextSplitter(
            chunkSize: 200,
            chunkOverlap: 50));
}

var database = new SQLiteVectorStore(
    filename: "vectors.db",
    tableName: "vectors",
    embeddings: embeddings);
const string question = "Who was drinking a unicorn blood?";
var similarDocuments = await database.GetSimilarDocuments(question, amount: 5);

var answer = await llm.GenerateAsync(
    $"""
     Use the following pieces of context to answer the question at the end.
     If the answer is not in context then just say that you don't know, don't try to make up an answer.
     Keep the answer as short as possible.

     {similarDocuments.AsString()}

     Question: {question}
     Helpful Answer:
     """, CancellationToken.None).ConfigureAwait(false);

Console.WriteLine($"LLM answer: {answer}"); // The cloaked figure.
Console.WriteLine($"LLM usage: {llm.Usage}");
Console.WriteLine($"Embeddings usage: {embeddings.Usage}");

Contributors

Konstantin S.
🚇 ⚠️ 💻

TesAnti
🚇 ⚠️ 💻

Khoroshev Evgeniy
🚇 ⚠️ 💻

SiegDuch
🚇

gunpal5
🚇 ⚠️ 💻

Ketan Khare
🚇 ⚠️ 💻

Roderic Bos
🚇 ⚠️ 💻

Peter James
🚇 ⚠️ 💻

Ty Augustine
🚇 ⚠️ 💻

Eric Green
🚇 ⚠️ 💻

Support

Priority place for bugs: https://github.com/tryAGI/LangChain/issues
Priority place for ideas and general questions: https://github.com/tryAGI/LangChain/discussions
Discord: https://discord.gg/Ca2xhfBf3v