https://github.com/maihoangbichtram/multi_agentic_rag
Multi-agentic researcher (RAG)
https://github.com/maihoangbichtram/multi_agentic_rag
agentic-ai ai ai-deployment deployment google-cloud google-cloud-platform multiagent rag tavily terraform
Last synced: 7 months ago
JSON representation
Multi-agentic researcher (RAG)
- Host: GitHub
- URL: https://github.com/maihoangbichtram/multi_agentic_rag
- Owner: maihoangbichtram
- Created: 2025-03-05T15:04:01.000Z (8 months ago)
- Default Branch: main
- Last Pushed: 2025-03-21T13:51:37.000Z (7 months ago)
- Last Synced: 2025-03-21T14:24:59.639Z (7 months ago)
- Topics: agentic-ai, ai, ai-deployment, deployment, google-cloud, google-cloud-platform, multiagent, rag, tavily, terraform
- Language: Python
- Homepage: https://app-930736962858.europe-west3.run.app/docs
- Size: 4.2 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# 🔎 Multi Agentic Research (RAG)
- Multi-agentic researcher researches the query/topic from documents fetched from Tavily Search Engine.
- The output is the report about the query/topic based on the retrieved documents.
- The graph ends when the hallucination point is 1, or else the graph restarts from collecting documents from Tavily
for generated queries to retrieve related info.
## Demo
[](https://app-930736962858.europe-west3.run.app/docs)
- To improve performance and avoid reaching limit of free tier of Google Generative AI, I limited the length of the response/report to be min 200 words.
## Work in progress
1. INTERNAL DOCUMENTATION
2. Access to documents to reliable sources for academic sources (sciencedirect, elsevier, springer, ...)
3. Construct more detail report (e.g Write report for each query)
4. Human input (e.g research plan, sources to fetch documents for queries)
### Installation
Customize LLMs, retrievers and report length in `config.yaml`
1. Install Python 3.12 or later. [Guide](https://www.tutorialsteacher.com/python/install-python).
2. Clone the project and navigate to the directory:
```bash
git clone https://github.com/maihoangbichtram/multi_agentic_rag
cd multi_agentic_rag
```
3. Set up API keys by exporting them or storing them in a `.env` file.
```bash
Copy .env.example to .env
```
4. Create and Activate virtual environment
4.1 In terminal:
Create a virtual environment
```bash
python3 -m venv .venv
```
Activate the virtual environment
```bash
. .venv/bin/activate
```
4.2 Poetry
```bash
poetry shell
```
5. Install dependencies and start the server:
5.1 In terminal:
```bash
pip install -r requirements.txt
```
5.2 Poetry
```bash
poetry install
```
6. Start the application
6.1 In terminal:
```bash
python app/main.py
```
6.2 Poetry
```bash
poetry run uvicorn app.main:app --reload --timeout-keep-alive 720
```
## Deployment
### Google Cloud
#### Prerequisites
- Google Cloud Account
- Google CLI
- Service account under IAM (to access to Google Cloud services.)
- (Access) Key downloaded as json (for the service account)
#### Terraforming GC Components
##### Tf files
- main.tf
- variables.tf
- terraform.tfvars (not public): Declare values for variables
```bash
# GCP settings
project_id = "project_id"
# GCP region
region = "europe-west3"
# Artifact registry repository
registry_id = "registry_id"
```
##### Commands
Run commands in order
- `terraform init`
- `terraform plan`
- `terraform apply`: create the GCP resources
##### Note
Enable GCP APIs manually if Terraform reports errors with permission:
```bash
gcloud services enable artifactregistry.googleapis.com
gcloud services enable run.googleapis.com
```
#### Deploying to cloud
- Create `requirements.txt` for docker file
```bash
poetry export -f requirements.txt --output requirements.txt
```
##### Build and test docker image locally
```bash
docker build --pull --rm -f "Dockerfile" -t :latest "."
```
```bash
docker run --rm -it -p 8080:8080/tcp :latest
```
##### Build docker image for Cloud Run
- Create builder
```bash
docker buildx create --name --bootstrap --use
```
- Build the image
```bash
docker buildx build --file Dockerfile \
--platform linux/amd64 \
--builder \
--progress plain \
--build-arg DOCKER_REPO=-docker.pkg.dev/// \
--pull --push \
--tag -docker.pkg.dev///:latest .
```
##### Deploy
Added necessary API keys for the app to run probably.
If you configure OpenAI for `llm`, add env var `OPENAI_API_KEY`.
```bash
gcloud run deploy app \
--image -docker.pkg.dev///:latest \
--region \
--platform managed \
--allow-unauthenticated \
--set-env-vars GOOGLE_API_KEY=,TAVILY_API_KEY=,CO_API_KEY=
```