idinsight / aaq-core Goto Github PK

Trustworthy question-answering AI plugin for chatbots in the social sector with advanced content performance analysis.

License: BSD 3-Clause "New" or "Revised" License

Dockerfile 0.47% Python 68.28% Mako 0.07% Shell 0.04% Makefile 0.86% CSS 0.71% TypeScript 26.67% JavaScript 0.01% HCL 2.91%

faq faq-chatbot faq-system fastapi guardrails llms mkdocs-material rag react

aaq-core's Introduction

Developer Docs | Features | Usage | Architecture | Funders and Partners

Ask A Question is a free and open-source tool created to help non-profit organizations, governments in developing nations, and social sector organizations use Large Language Models for responding to citizen inquiries in their native languages.

🤸‍♀️ Features

❓ LLM-powered search

Match your questions to content in the database using embeddings from LLMs.

🤖 LLM responses

Craft a custom reponse to the question using LLM chat and the content in your database

🔌 Integrate with your own chatbot

Connect to your own chatbot on platforms like Turn.io, Glific, and Typebot using our APIs.

📚 Manage content

Use the AAQ App to add, edit, and delete content in the database (Sign up for a demo here)

🚨 Message Triaging

Identify urgent or important messages based on your own criteria.

🧑‍💼 Content manager dashboard

See which content is the most sought after, the kinds of questions that receive poor feedback, identify missing content, and more

🚧 Upcoming

💬 Conversation capability

Refine or clarify your question through conversation

📹 Multimedia content

Respond with not just text but voice, images, and videos as well.

🧑‍💻 Engineering dashboard

Monitor uptime, response rates, throughput HTTP reponse codes and more

Note

Looking for other features? Please raise an issue with [FEATURE REQUEST] before the title.

Usage

To get answers from your database of contents, you can use the /search endpoint. This endpoint returns the following:

Search results: Finds the most similar content in the database using cosine distance between embeddings.
(Optionally) LLM generated response: Crafts a custom response using LLM chat using the most similar content.

See docs or API docs for more details and other API endpoints.

❓ Simple content search

curl -X 'POST' \
  'https://[DOMAIN]/api/search' \
  -H 'accept: application/json' \
  -H 'Authorization: Bearer <BEARER TOKEN>' \
  -H 'Content-Type: application/json' \
  -d '{
  "query_text": "how are you?",
  "generate_llm_response": false,
  "query_metadata": {}
}'

🤖 With LLM response

The query looks the same as above, except generate_llm_response is set to true:

curl -X 'POST' \
  'https://[DOMAIN]/api/search' \
  -H 'accept: application/json' \
  -H 'Authorization: Bearer <BEARER TOKEN>' \
  -H 'Content-Type: application/json' \
  -d '{
  "query_text": "this is my question",
  "generate_llm_response": true,
  "query_metadata": {}
}'

📚 Manage content

You can access the admin console at

https://[DOMAIN]/

Architecture

We use docker-compose to orchestrate containers with a reverse proxy that manages all incoming traffic to the service. The database and LiteLLM proxy are only accessed by the core app.

Documentation

See here for full documentation.

Funders and Partners

aaq-core's People

Contributors

Stargazers

Watchers

Forkers

signpostproduct sulochan-khadka kartiklove31 srinivas2030

aaq-core's Issues

[DMP 2024]: Voice API

Ticket Contents

Description

[Provide a brief description of the feature, including why it is needed and what it will accomplish.]
Ask A Question is a free and open-source tool created to help non-profit organizations, governments in developing nations, and social sector organizations utilize Large Language Models for responding to citizen inquiries in their native languages.

Create new voice response API: the API will allow users to send questions and receive responses from AAQ using voice notes. This will increase the accessibility of AAQ to users for whom speaking/listening is easier than writing/reading.

Goals & Mid-Point Milestone

Goals

By mid-point

Develop an API endpoint in AAQ for sending queries in text and receiving responses in voice (text-to-speech, TTS). The first iteration may use an external TTS API
Develop a TTS service for AAQ using an open-source model that can replace an external TTS API

By project end

Develop an API endpoint for sending questions as voice notes and receiving responses as voice notes (speech-to-text, text-to-speech)
Integrate the TTS service into AAQ infrastructure on AWS
Publish a short blog post on AAQ website about the changes

For every goal listed, there will be a few rounds of design-feedback-implementation with support from the mentors and wider AAQ team.

Setup/Installation

AAQ contribution guide is here: https://idinsight.github.io/aaq-core/develop/contributing/

You will be given access to our testing environment on AWS.

Expected Outcome

AAQ users can query the voice endpoints for voice questions and/or voice response. This can be seamlessly integrated into AAQ’s chat flow manager of choice, Typebot.io.
AAQ users have an option to use an open-source TTS/STT model instead of an external API.

Acceptance Criteria

No response

Implementation Details

You will build the APIs in our core_backend component, which is built in Python, using FastAPI.

Our database is PostgreSQL + pgvector for managing document embeddings (contents) as well as other transactional data.

For the TTS/STT service that serves open-sourced models, you will make it as platform-agnostic as possible, which often means using Docker, but the integration will be to AWS, as our demo environment sits in AWS. You will be able to lead the architecture design for such a service. Of course, our mentors and the wider AAQ team will be available to support and think it through together.

Mockups/Wireframes

No response

Product Name

Ask A Question

Organisation Name

IDinsight

Domain

Open Source Library

Tech Skills Needed

AWS, Database, Python

Mentor(s)

@amiraliemami @lickem22 are Data Scientists at IDinsight!

idinsight / aaq-core Goto Github PK

aaq-core's Introduction

🤸‍♀️ Features

❓ LLM-powered search

🤖 LLM responses

🔌 Integrate with your own chatbot

📚 Manage content

🚨 Message Triaging

🧑‍💼 Content manager dashboard

🚧 Upcoming

💬 Conversation capability

📹 Multimedia content

🧑‍💻 Engineering dashboard

Usage

❓ Simple content search

🤖 With LLM response

📚 Manage content

Architecture

Documentation

Funders and Partners

aaq-core's People

Contributors

Stargazers

Watchers

Forkers

aaq-core's Issues

Ticket Contents

Description

Goals & Mid-Point Milestone

Goals

By mid-point

By project end

Setup/Installation

Expected Outcome

Acceptance Criteria

Implementation Details

Mockups/Wireframes

Product Name

Organisation Name

Domain

Tech Skills Needed

Mentor(s)

Category

Recommend Projects

Recommend Topics

Recommend Org