feat: Add local development setup with Docker Compose

[ZaidAli3642]

Summary

• Add Docker Compose configuration to run the full stack locally (Milvus + API server)
• Add .env.example with environment variable template
• Add scripts/local_ingest.py for local data ingestion without Kubeflow Pipelines
• Add root Dockerfile for local development
• Update README.md with Local Development Setup section

Problem

Currently there is no way to run the project locally. The README assumes a Kubernetes cluster with GPU nodes, KServe, and Kubeflow Pipelines. This makes it difficult for new contributors to set up and test the project.

Solution

Provide a Docker Compose setup that runs the full stack locally with 4 commands:

cp .env.example .env
ollama pull llama3.1:8b
docker-compose up --build -d
docker exec docs-agent-api python local_ingest.py

This uses:

- Docker Compose for Milvus (instead of Helm + Kubernetes)
- Ollama for LLM inference (instead of KServe + vLLM which requires NVIDIA GPUs)
- local_ingest.py for data ingestion (instead of Kubeflow Pipelines)


## Test plan

- [ ] docker-compose up --build -d starts all 4 services
- [ ] docker exec docs-agent-api python local_ingest.py ingests docs
- [ ] curl test returns a valid response
- [ ] Existing Kubernetes deployment files are not modified

[google-oss-prow]

[APPROVALNOTIFIER] This PR is NOT APPROVED

This pull-request has been approved by:
Once this PR has been reviewed and has the lgtm label, please assign franciscojavierarceo for approval. For more information see the Kubernetes Code Review Process.

The full list of commands accepted by this bot can be found here.

Details

Needs approval from an approver in each of these files:

• OWNERS

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment