Knowledge Base on Producthunt daily

outline

Thu, 31 Jul 2025 15:34:29 +0800

outline/outline

A fast, collaborative, knowledge base for your team built using React and Node.js.
Try out Outline using our hosted version at www.getoutline.com.

This is the source code that runs Outline and all the associated services. If you want to use Outline then you don’t need to run this code, we offer a hosted version of the app at getoutline.com. You can also find documentation on using Outline in our guide.

If you’d like to run your own copy of Outline or contribute to development then this is the place for you.

Installation

Please see the documentation for running your own copy of Outline in a production configuration.

If you have questions or improvements for the docs please create a thread in GitHub discussions.

Development

There is a short guide for setting up a development environment if you wish to contribute changes, fixes, and improvements to Outline.

Contributing

Outline is built and maintained by a small team – we’d love your help to fix bugs and add features!

Before submitting a pull request please discuss with the core team by creating or commenting in an issue on GitHub – we’d also love to hear from you in the discussions. This way we can ensure that an approach is agreed on before code is written. This will result in a much higher likelihood of your code being accepted.

If you’re looking for ways to get started, here’s a list of ways to help us improve Outline:

Translation into other languages
Issues with good first issue label
Performance improvements, both on server and frontend
Developer happiness and documentation
Bugs and other issues listed on GitHub

Architecture

If you’re interested in contributing or learning more about the Outline codebase please refer to the architecture document first for a high level overview of how the application is put together.

Debugging

In development Outline outputs simple logging to the console, prefixed by categories. In production it outputs JSON logs, these can be easily parsed by your preferred log ingestion pipeline.

HTTP logging is disabled by default, but can be enabled by setting the DEBUG=http environment variable.

Tests

We aim to have sufficient test coverage for critical parts of the application and aren’t aiming for 100% unit test coverage. All API endpoints and anything authentication related should be thoroughly tested.

To add new tests, write your tests with Jest and add a file with .test.js extension next to the tested code.

# To run all tests
make test

# To run backend tests in watch mode
make watch

Once the test database is created with make test you may individually run frontend and backend tests directly.

# To run backend tests
yarn test:server

# To run a specific backend test
yarn test:server myTestFile

# To run frontend tests
yarn test:app

Migrations

Sequelize is used to create and run migrations, for example:

1
2

yarn sequelize migration:generate --name my-migration
yarn sequelize db:migrate

Or to run migrations on test database:

`1`	`yarn sequelize db:migrate --env test`

Activity

License

Outline is BSL 1.1 licensed.

rag-from-scratch

Fri, 25 Jul 2025 15:33:48 +0800

langchain-ai/rag-from-scratch

RAG From Scratch

LLMs are trained on a large but fixed corpus of data, limiting their ability to reason about private or recent information. Fine-tuning is one way to mitigate this, but is often not well-suited for factual recall and can be costly. Retrieval augmented generation (RAG) has emerged as a popular and powerful mechanism to expand an LLM’s knowledge base, using documents retrieved from an external data source to ground the LLM generation via in-context learning. These notebooks accompany a video playlist that builds up an understanding of RAG from scratch, starting with the basics of indexing, retrieval, and generation.

Video playlist

ragbits

Mon, 09 Jun 2025 15:31:32 +0800

deepsense-ai/ragbits

🐰 Ragbits

Building blocks for rapid development of GenAI applications

Homepage | Documentation | Contact

Features

🔨 Build Reliable & Scalable GenAI Apps

Swap LLMs anytime – Switch between 100+ LLMs via LiteLLM or run local models.
Type-safe LLM calls – Use Python generics to enforce strict type safety in model interactions.
Bring your own vector store – Connect to Qdrant, PgVector, and more with built-in support.
Developer tools included – Manage vector stores, query pipelines, and test prompts from your terminal.
Modular installation – Install only what you need, reducing dependencies and improving performance.

📚 Fast & Flexible RAG Processing

Ingest 20+ formats – Process PDFs, HTML, spreadsheets, presentations, and more. Process data using Docling, Unstructured or create a custom parser.
Handle complex data – Extract tables, images, and structured content with built-in VLMs support.
Connect to any data source – Use prebuilt connectors for S3, GCS, Azure, or implement your own.
Scale ingestion – Process large datasets quickly with Ray-based parallel processing.

🚀 Deploy & Monitor with Confidence

Real-time observability – Track performance with OpenTelemetry and CLI insights.
Built-in testing – Validate prompts with promptfoo before deployment.
Auto-optimization – Continuously evaluate and refine model performance.
Chat UI – Deploy chatbot interface with API, persistance and user feedback.

Installation

To get started quickly, you can install with:

`1`	`pip install ragbits`

This is a starter bundle of packages, containing:

ragbits-core - fundamental tools for working with prompts, LLMs and vector databases.
ragbits-agents - abstractions for building agentic systems.
ragbits-document-search - retrieval and ingestion piplines for knowledge bases.
ragbits-evaluate - unified evaluation framework for Ragbits components.
ragbits-chat - full-stack infrastructure for building conversational AI applications.
ragbits-cli - ragbits shell command for interacting with Ragbits components.

Alternatively, you can use individual components of the stack by installing their respective packages.

Quickstart

Basics

To define a prompt and run LLM:

import asyncio
from pydantic import BaseModel
from ragbits.core.llms import LiteLLM
from ragbits.core.prompt import Prompt

class QuestionAnswerPromptInput(BaseModel):
    question: str

class QuestionAnswerPromptOutput(BaseModel):
    answer: str

class QuestionAnswerPrompt(Prompt[QuestionAnswerPromptInput, QuestionAnswerPromptOutput]):
    system_prompt = """
    You are a question answering agent. Answer the question to the best of your ability.
    """
    user_prompt = """
    Question: {{ question }}
    """

llm = LiteLLM(model_name="gpt-4.1-nano", use_structured_output=True)

async def main() -> None:
    prompt = QuestionAnswerPrompt(QuestionAnswerPromptInput(question="What are high memory and low memory on linux?"))
    response = await llm.generate(prompt)
    print(response.answer)

if __name__ == "__main__":
    asyncio.run(main())

Document Search

To build and query a simple vector store index:

import asyncio
from ragbits.core.embeddings import LiteLLMEmbedder
from ragbits.core.vector_stores import InMemoryVectorStore
from ragbits.document_search import DocumentSearch

embedder = LiteLLMEmbedder(model_name="text-embedding-3-small")
vector_store = InMemoryVectorStore(embedder=embedder)
document_search = DocumentSearch(vector_store=vector_store)

async def run() -> None:
    await document_search.ingest("web://https://arxiv.org/pdf/1706.03762")
    result = await document_search.search("What are the key findings presented in this paper?")
    print(result)

if __name__ == "__main__":
    asyncio.run(run())

Retrieval-Augmented Generation

To build a simple RAG pipeline:

import asyncio
from pydantic import BaseModel
from ragbits.core.embeddings import LiteLLMEmbedder
from ragbits.core.llms import LiteLLM
from ragbits.core.prompt import Prompt
from ragbits.core.vector_stores import InMemoryVectorStore
from ragbits.document_search import DocumentSearch

class QuestionAnswerPromptInput(BaseModel):
    question: str
    context: list[str]

class QuestionAnswerPromptOutput(BaseModel):
    answer: str

class QuestionAnswerPrompt(Prompt[QuestionAnswerPromptInput, QuestionAnswerPromptOutput]):
    system_prompt = """
    You are a question answering agent. Answer the question that will be provided using context.
    If in the given context there is not enough information refuse to answer.
    """
    user_prompt = """
    Question: {{ question }}
    Context: {% for item in context %}
        {{ item }}
    {%- endfor %}
    """

embedder = LiteLLMEmbedder(model_name="text-embedding-3-small")
vector_store = InMemoryVectorStore(embedder=embedder)
document_search = DocumentSearch(vector_store=vector_store)
llm = LiteLLM(model_name="gpt-4.1-nano", use_structured_output=True)

async def run() -> None:
    question = "What are the key findings presented in this paper?"

    await document_search.ingest("web://https://arxiv.org/pdf/1706.03762")
    result = await document_search.search(question)

    prompt = QuestionAnswerPrompt(QuestionAnswerPromptInput(
        question=question,
        context=[element.text_representation for element in result],
    ))
    response = await llm.generate(prompt)
    print(response.answer)

if __name__ == "__main__":
    asyncio.run(run())

Chatbot interface with UI

To expose your RAG application through Ragbits UI:

from collections.abc import AsyncGenerator

from pydantic import BaseModel

from ragbits.chat.api import RagbitsAPI
from ragbits.chat.interface import ChatInterface
from ragbits.chat.interface.types import ChatContext, ChatResponse
from ragbits.core.embeddings import LiteLLMEmbedder
from ragbits.core.llms import LiteLLM
from ragbits.core.prompt import Prompt
from ragbits.core.prompt.base import ChatFormat
from ragbits.core.vector_stores import InMemoryVectorStore
from ragbits.document_search import DocumentSearch


class QuestionAnswerPromptInput(BaseModel):
    question: str
    context: list[str]


class QuestionAnswerPrompt(Prompt[QuestionAnswerPromptInput, str]):
    system_prompt = """
    You are a question answering agent. Answer the question that will be provided using context.
    If in the given context there is not enough information refuse to answer.
    """
    user_prompt = """
    Question: {{ question }}
    Context: {% for item in context %}{{ item }}{%- endfor %}
    """


class MyChat(ChatInterface):
    """Chat interface for fullapp application."""

    async def setup(self) -> None:
        self.embedder = LiteLLMEmbedder(model_name="text-embedding-3-small")
        self.vector_store = InMemoryVectorStore(embedder=self.embedder)
        self.document_search = DocumentSearch(vector_store=self.vector_store)
        self.llm = LiteLLM(model_name="gpt-4.1-nano", use_structured_output=True)

        await self.document_search.ingest("web://https://arxiv.org/pdf/1706.03762")

    async def chat(
        self,
        message: str,
        history: ChatFormat | None = None,
        context: ChatContext | None = None,
    ) -> AsyncGenerator[ChatResponse, None]:
        # Search for relevant documents
        result = await self.document_search.search(message)

        prompt = QuestionAnswerPrompt(
            QuestionAnswerPromptInput(
                question=message,
                context=[element.text_representation for element in result],
            )
        )

        # Stream the response from the LLM
        async for chunk in self.llm.generate_streaming(prompt):
            yield self.create_text_response(chunk)


if __name__ == "__main__":
    RagbitsAPI(MyChat).run()

Rapid development

Create Ragbits projects from templates:

`1`	`uvx create-ragbits-app`

Explore create-ragbits-app repo here. If you have a new idea for a template, feel free to contribute!

Documentation

Quickstart - Get started with Ragbits in a few minutes
How-to - Learn how to use Ragbits in your projects
CLI - Learn how to run Ragbits in your terminal
API reference - Explore the underlying Ragbits API

Contributing

We welcome contributions! Please read CONTRIBUTING.md for more information.

License

Ragbits is licensed under the MIT License.

FastGPT

Thu, 29 May 2025 15:29:58 +0800

labring/FastGPT

FastGPT

English | 简体中文 | 日语

FastGPT 是一个 AI Agent 构建平台，提供开箱即用的数据处理、模型调用等能力，同时可以通过 Flow 可视化进行工作流编排，从而实现复杂的应用场景！

https://github.com/labring/FastGPT/assets/15308462/7d3a38df-eb0e-4388-9250-2409bd33f6d4

🛸 在线使用

🌍 国际版：tryfastgpt.ai

💡 RoadMap

1 应用编排能力

对话工作流、插件工作流
工具调用
Code sandbox
循环调用
用户选择
表单输入

2 知识库能力

多库复用，混用
chunk 记录修改和删除
支持手动输入，直接分段，QA 拆分导入
支持 txt，md，html，pdf，docx，pptx，csv，xlsx (有需要更多可 PR file loader)，支持 url 读取、CSV 批量导入
混合检索 & 重排
API 知识库
自定义文件读取服务
自定义分块服务

3 应用调试能力

知识库单点搜索测试
对话时反馈引用并可修改与删除
完整上下文呈现
完整模块中间值呈现
高级编排 DeBug 模式

4 OpenAPI 接口

completions 接口 (chat 模式对齐 GPT 接口)
知识库 CRUD
对话 CRUD

5 运营能力

免登录分享窗口
Iframe 一键嵌入
聊天窗口嵌入支持自定义 Icon，默认打开，拖拽等功能
统一查阅对话记录，并对数据进行标注

6 其他

可视化模型配置。
支持语音输入和输出 (可配置语音输入语音回答)
模糊输入提示
模板市场

👨‍💻 开发

项目技术栈：NextJs + TS + ChakraUI + MongoDB + PostgreSQL (PG Vector 插件)/Milvus

⚡ 快速部署

使用 Sealos 服务，无需采购服务器、无需域名，支持高并发 & 动态伸缩，并且数据库应用采用 kubeblocks 的数据库，在 IO 性能方面，远超于简单的 Docker 容器部署。

点击查看 Sealos 一键部署 FastGPT 教程

🏘️ 加入我们

我们正在寻找志同道合的小伙伴，加速 FastGPT 的发展。你可以通过 FastGPT 2025 招聘了解 FastGPT 的招聘信息。

💪 相关项目

🌿 第三方生态

🏘️ 社区交流群

扫码加入飞书话题群：

👀 其他

🤝 参与贡献

我们非常欢迎各种形式的贡献。如果你对贡献代码感兴趣，可以查看我们的 GitHub Issues，大展身手，向我们展示你的奇思妙想。


****

🌟 Star History

使用协议

本仓库遵循 FastGPT Open Source License 开源协议。

允许作为后台服务直接商用，但不允许提供 SaaS 服务。
未经商业授权，任何形式的商用服务均需保留相关版权信息。
完整请查看 FastGPT Open Source License
联系方式：Dennis@sealos.io，点击查看商业版定价策略