insight chat Download - insight chat Source code download

insight chat

Other source code

1.0.0

Download

Insight-Chat

Build with

FastAPI - FastAPI is a modern, fast (high-performance), web framework for building APIs with Python 3.7+ based on standard Python type hints.
LlamaIndex - LlamaIndex is a data framework for LLM-based applications which benefit from context augmentation. Such LLM systems have been termed as RAG systems, standing for “Retrieval-Augemented Generation”. LlamaIndex provides the essential abstractions to more easily ingest, structure, and access private or domain-specific data in order to inject these safely and reliably into LLMs for more accurate text generation.
MongoDB Atlas - MongoDB Atlas is a fully-managed cloud database developed by the same people that build MongoDB.
Atlas Vector Search - Atlas Vector Search lets you search unstructured data. You can create vector embeddings with machine learning models like OpenAI and Hugging Face, and store and index them in Atlas for retrieval augmented generation (RAG), semantic search, recommendation engines, dynamic personalization, and other use cases.

Note: You need creating a knn index to use Atlas Vector Search.

Log in to your Atlas account and locate the collection corresponding to the Vector Store. If you are using the default names, it should be “default_store/default_db”.
Create a Search index for the collection in tab Atlas Search. Choose the “Json Editor” mode and set index with following content:

{
  "mappings": {
    "dynamic": true,
    "fields": {
      "embedding": {
        "dimensions": 1536,
        "similarity": "cosine",
        "type": "knnVector"
      }
    }
  }
}

Wait for a few seconds to let the new index take effect.

Run app with uvicorn

Requires

Python >= 3.10

Install with poetry:

pip install poetry
poetry config virtualenvs.in-project true
poetry shell
poetry install

uvicorn app.main:app --host 127.0.0.1 --port 9080

Run app with docker ?

docker build -t insight-chat .
docker run -d --name insight-chat -p 8080:8080 insight-chat

Features:

1. Chat

alt text

Chat with document
Conversation chat with document

2. Ingest data

alt text

You can ingest data from a file, link website, or youtube.

3. Message

alt text

Manage message for conversation chat.

4. Chat Session

alt text

Manage chat session for conversation chat.

5. User

alt text

Manage user for application.

6. Authentication

alt text

Authentication for application.

Knowledges

LlamaIndex’s Storage System

In short, LlamaIndex uses the following pattern to store document information:

The text of a document is divided into several Nodes, also known as “chunks”; Using the document ID as the primary key, the objects representing each document, mainly metadata such as file name and hash, are stored in the Document Store, along with the list of Nodes for that document; Using the Node ID as the primary key, the Node’s embedding is stored in the Vector Store.

alt text