public/maritime-logistics
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add Maritime/Logistics support assistant with safety/eval layer

Browse Source
This commit is contained in:
majid
2026-09-19 18:01:28 +02:00
parent 93e92a1210
commit 6b737a3295
58 changed files with 7570 additions and 69 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+114 -69
View File
@@ -1,93 +1,138 @@
# Maritime Logistics
# Maritime/Logistics Support Assistant
A RAG + multi-agent support assistant for a fictional shipping company
(Meridian Sea Logistics), built with a safety/eval layer as the headline
feature rather than an afterthought. Written in Rust.
## Why this exists
## Getting started
This is a portfolio piece modeled on real maritime-logistics support work,
scoped to be publishable: its own fictional company, own documents, own
IP. The interesting part isn't the RAG pipeline (that's table stakes) --
it's the guardrail and regression-eval layer wrapped around it, and the
trade-offs documented in [`docs/SAFETY_WRITEUP.md`](docs/SAFETY_WRITEUP.md).
To make it easy for you to get started with GitLab, here's a list of recommended next steps.
## Architecture
Already a pro? Just edit this README.md and make it your own. Want to make it easy? [Use the template at the bottom](#editing-this-readme)!
Three narrow agents behind a deterministic supervisor:
## Add your files
```mermaid
flowchart TD
Q["Customer Query"] --> REGEX{{"Regex injection scan"}}
REGEX -- clean --> SEM{{"Embed query -> cosine similarity<br/>vs. known injection examples"}}
SEM -- score < threshold --> RET["Retrieval Agent<br/>vector search + LLM relevance filter"]
SEM -- score >= threshold --> JUDGE{{"LLM Injection Judge"}}
JUDGE -- not injection --> RET
JUDGE -- injection --> FINAL
REGEX -- match --> FINAL["Final Answer + Citations -> Customer"]
RET <--> QD[("Qdrant Vector Store<br/>chunked KB docs")]
RET --> DRAFT["Drafting Agent<br/>tool-calling loop"]
DRAFT -- lookup_shipment --> SHIP[("Shipment Repository")]
DRAFT -- escalate_to_human --> ESC[("Escalation Desk")]
DRAFT --> POL["Policy-Compliance Agent"]
POL --> DOCS[("acceptable_use.md +<br/>tracking_policy.md")]
POL --> POST{{"Guardrail: Post-check<br/>PII/injection scan + policy verdict"}}
POST -- allow / escalate --> FINAL
REGEX -.-> AUDIT[("Audit Log<br/>JSONL, append-only")]
JUDGE -.-> AUDIT
POST -.-> AUDIT
* [Create](https://docs.gitlab.com/user/project/repository/web_editor/#create-a-file) or [upload](https://docs.gitlab.com/user/project/repository/web_editor/#upload-a-file) files
* [Add files using the command line](https://docs.gitlab.com/topics/git/add_files/#add-files-to-a-git-repository) or push an existing Git repository with the following command:
classDef agent fill:#eef2ff,stroke:#4f46e5,color:#312e81
classDef guardrail fill:#fff7ed,stroke:#ea580c,color:#7c2d12
classDef store fill:#f1f5f9,stroke:#64748b,color:#334155
classDef audit fill:#f0fdf4,stroke:#16a34a,color:#14532d
classDef io fill:#f8fafc,stroke:#334155,color:#0f172a
```
cd existing_repo
git remote add origin https://gitlab.gfuse.it/gfuse-show-cases/maritime-logistics.git
git branch -M main
git push -uf origin main
class RET,DRAFT,POL agent
class REGEX,SEM,JUDGE,POST guardrail
class QD,SHIP,ESC,DOCS store
class AUDIT audit
class Q,FINAL io
```
## Integrate with your tools
The pre-check is three layers, cheapest first: a regex scan catches fixed
wordings for free; if that's clean, the query is embedded and compared
against a small corpus of known injection examples so paraphrases that
dodge the regexes still get caught; only if that similarity score clears a
threshold does the pipeline pay for an LLM call to judge intent, since
embedding similarity alone is too noisy to block a customer on. See
`src/guardrails/semantic_guardrail.rs` and `src/guardrails/injection_judge.rs`.
* [Set up project integrations](https://gitlab.gfuse.it/gfuse-show-cases/maritime-logistics/-/settings/integrations)
The supervisor (`src/agents/supervisor.rs`) is what runs this graph -- plain
Rust control flow, not another LLM call, so *what's allowed through* is
never itself something the model can be talked out of. The dashed edges are
the audit trail: every guardrail decision is logged, not just the blocked
ones.
## Collaborate with your team
Every LLM call asks for a schema-validated structured output (via a forced
tool-call, see `src/llm/client.rs`) rather than free text -- there's no
Rust equivalent of pydantic-ai, so this is a small hand-rolled agent loop
against the raw Anthropic Messages API.
* [Invite team members and collaborators](https://docs.gitlab.com/user/project/members/)
* [Create a new merge request](https://docs.gitlab.com/user/project/merge_requests/creating_merge_requests/)
* [Automatically close issues from merge requests](https://docs.gitlab.com/user/project/issues/managing_issues/#closing-issues-automatically)
* [Enable merge request approvals](https://docs.gitlab.com/user/project/merge_requests/approvals/)
* [Set auto-merge](https://docs.gitlab.com/user/project/merge_requests/auto_merge/)
The crate is organized as a dependency-injected module tree (see
`src/cli.rs`, the composition root) -- no global/static singletons
anywhere; every component is constructed explicitly and passed to its
collaborators through the constructor.
## Test and Deploy
```
src/
config.rs Settings, loaded once in cli.rs
models/ domain types + structured agent I/O + eval types
knowledge/ the fictional company's markdown knowledge base
data/ seed shipment records
embeddings/ EmbeddingProvider trait + local fastembed impl
retrieval/ chunking, Qdrant wrapper, reference extraction
tools/ shipment lookup + human escalation (as LLM tools)
llm/ Anthropic client, tool trait, agentic loop
agents/ retrieval / policy / drafting agents + supervisor
guardrails/ rule-based scanner, audit log, decision pipeline
eval/ golden dataset loader, scoring, regression harness
cli.rs composition root + subcommands
```
Use the built-in continuous integration in GitLab.
## Running it
* [Get started with GitLab CI/CD](https://docs.gitlab.com/ci/quick_start/)
* [Analyze your code for known vulnerabilities with Static Application Security Testing (SAST)](https://docs.gitlab.com/user/application_security/sast/)
* [Deploy to Kubernetes, Amazon EC2, or Amazon ECS using Auto Deploy](https://docs.gitlab.com/topics/autodevops/requirements/)
* [Use pull-based deployments for improved Kubernetes management](https://docs.gitlab.com/user/clusters/agent/)
* [Set up protected environments](https://docs.gitlab.com/ci/environments/protected_environments/)
Requires a Qdrant instance and an Anthropic API key. Embeddings run
locally via `fastembed` (ONNX Runtime) -- the model downloads once on
first use, then runs fully offline.
***
```bash
docker run -p 6334:6334 qdrant/qdrant
cp .env.example .env # fill in ANTHROPIC_API_KEY
# Editing this README
cargo run -- ingest # chunk + embed + index the knowledge base
cargo run -- ask "Where is my container MSCU7654321?"
cargo run -- eval # run the golden dataset, print the report
```
When you're ready to make this README your own, just edit this file and use the handy template below (or feel free to structure it however you want - this is just a starting point!). Thanks to [makeareadme.com](https://www.makeareadme.com/) for this template.
## Testing
## Suggestions for a good README
```bash
cargo test # pure-logic unit + integration tests, no network required
cargo clippy --all-targets
```
Every project is different, so consider which of these sections apply to yours. The sections used in the template are suggestions for most open source projects. Also keep in mind that while a README can be too long and detailed, too long is better than too short. If you think your README is too long, consider utilizing another form of documentation rather than cutting out information.
The `eval` command exercises the live model and Qdrant; `cargo test`
deliberately does not, so CI-style checks don't need API keys.
## Name
Choose a self-explaining name for your project.
## The safety/eval layer
## Description
Let people know what your project can do specifically. Provide context and add a link to any reference visitors might be unfamiliar with. A list of Features or a Background subsection can also be added here. If there are alternatives to your project, this is a good place to list differentiating factors.
- **Golden dataset** (`data/golden_dataset.jsonl`, 44 examples): normal
queries, prompt-injection attempts, policy-violation requests,
hallucination bait (asking about shipments that don't exist), and
out-of-scope requests.
- **Regression harness** (`src/eval/harness.rs`): scores retrieval
accuracy, generation accuracy, and guardrail correctness *separately*
per example and per category, so a failing run points at where the
failure originated instead of just "test 17 failed."
- **Guardrail pipeline** (`src/guardrails/`): a fast rule-based scan runs
before and after the LLM agents, independent of what the policy agent
concludes; the pre-check also embeds the query and escalates
high-similarity matches against known injection phrasings to an LLM
judge before blocking, catching paraphrases the regexes miss without
paying for an LLM call on every query. Every decision -- allow or
block -- is written to an append-only audit log.
## Badges
On some READMEs, you may see small images that convey metadata, such as whether or not all the tests are passing for the project. You can use Shields to add some to your README. Many services also have instructions for adding a badge.
## Visuals
Depending on what you are making, it can be a good idea to include screenshots or even a video (you'll frequently see GIFs rather than actual videos). Tools like ttygif can help, but check out Asciinema for a more sophisticated method.
## Installation
Within a particular ecosystem, there may be a common way of installing things, such as using Yarn, NuGet, or Homebrew. However, consider the possibility that whoever is reading your README is a novice and would like more guidance. Listing specific steps helps remove ambiguity and gets people to using your project as quickly as possible. If it only runs in a specific context like a particular programming language version or operating system or has dependencies that have to be installed manually, also add a Requirements subsection.
## Usage
Use examples liberally, and show the expected output if you can. It's helpful to have inline the smallest example of usage that you can demonstrate, while providing links to more sophisticated examples if they are too long to reasonably include in the README.
## Support
Tell people where they can go to for help. It can be any combination of an issue tracker, a chat room, an email address, etc.
## Roadmap
If you have ideas for releases in the future, it is a good idea to list them in the README.
## Contributing
State if you are open to contributions and what your requirements are for accepting them.
For people who want to make changes to your project, it's helpful to have some documentation on how to get started. Perhaps there is a script that they should run or some environment variables that they need to set. Make these steps explicit. These instructions could also be useful to your future self.
You can also document commands to lint the code or run tests. These steps help to ensure high code quality and reduce the likelihood that the changes inadvertently break something. Having instructions for running tests is especially helpful if it requires external setup, such as starting a Selenium server for testing in a browser.
## Authors and acknowledgment
Show your appreciation to those who have contributed to the project.
## License
For open source projects, say how it is licensed.
## Project status
If you have run out of energy or time for your project, put a note at the top of the README saying that development has slowed down or stopped completely. Someone may choose to fork your project or volunteer to step in as a maintainer or owner, allowing your project to keep going. You can also make an explicit request for maintainers.
See [`docs/SAFETY_WRITEUP.md`](docs/SAFETY_WRITEUP.md) for the failure
modes this was designed for, the trade-offs made, and what would need to
change for real production scale.