antves

Not at the moment. Happy to run a task on your behalf if you'd like!

I agree, these mitigations alone can't be sufficient, but they are all necessary within a wider framework.

The only way to make this kind of agents safe is to work on every layer. Part of it is teaching the underlying model to see the dangers, part of it is building stronger critics, and part of it is hardening the systems they connect to. These aren’t alternatives, we need all of them.

Thanks!

This is exactly it! We built a browser agent and got awesome results by designing the context in a simplified/compact version + using small/efficient LLMs - it's smooth.sh if you'd like to try

This is a very valid concern. Here are some of our initial considerations:

1. Security of these agentic system is a hard and important problem to solve. We're indexing heavily on it, but it's definitely still early days and there is still a lot to figure out.

2. We have a critic LLM that assesses among other things whether the website content is leading a non-aligned initiative. This is still subject to the LLM intelligence, but it's a first step.

3. Our agents run in isolated browser sessions and, as per all software engineering, each session should be granted minimum access. Nothing more than strictly needed.

4. These attacks are starting to resemble social engineering attacks. There may be opportunities to shift some of the preventative approaches to the LLM world.

Thanks for asking this, we should probably share a write-up on this subject!

We don't support this yet, but we'd love to talk about it. Feel free to book a demo!

Thanks for trying it out! We rely on a mix of internal benchmarks and academic benchmarks like WebVoyager.

Thanks! It all boils down to (1) using small and efficient models, and (2) insisting on good context engineering. We describe the browser state in a way that's both compact and meaningful. This allows us to use tiny LLMs under the hood.

Thanks for sharing this! It sounds very interesting. We experimented with a similar tree setup some time ago and it was giving good results. We eventually decided to move towards graphs as a general case of trees. I think the notion of using embeddings similarity for "walking" the graph is key, and we're actively integrating it in FastGraphRAG too by weighting the edges by the query. It's very nice to see so many solutions landing on similar designs!

Thanks for trying it out! There are two options to use FastGraphRAG for free:

(1) Self-hosting our open-source package (2) Using the free tier of the managed service, which includes 100 requests

If you wish to upgrade your plan, you can reach out to us at support [at] circlemind.co

These are knobs that you can tune to make the graph construction more/less opinionated. Generally speaking, the more we make it opinionated the better it fits the task.

At a high-level:

(1) Domain: allows you to "talk to the graph constructor". If you care particularly about one aspect of your data, this is the place to say it. For reference, take a look at some of the example prompts on our website (https://circlemind.co/)

(2) Example Queries: if you know what class of questions users will ask, it'd be useful to give the system this information so that it will "keep these questions in mind" when designing the graph. If you don't know which kinds of questions, you can just put a couple of high-level questions that you think apply to your data.

(3) Entity Types: this has a very high impact on the final quality of the graph. Think of these as the types of entities that you want to extract from your data, e.g. person, place, event, etc

All of the above help construct the knowledge graph so that it is specifically designed for your use-case.

I completely agree that the README could do a better job explaining the implementation details and our reasoning behind key design choices. For instance, we should elaborate on why we believe using PageRank offers a more effective exploration strategy compared to other GraphRAG approaches.

FastGraphRAG is entirely free to use, even for commercial applications, and we’re happy to make it accessible to everyone. The managed service is how we sustain our business.

Yes. We already support this feature in our managed service (https://docs.circlemind.co/essentials/query#include-referenc...) and we'll include it in the next open-source release too!

Thanks! It sounds like we should be able to help. I'd love to chat more in detail, feel free to send me a note at antonio [at] circlemind.co.

Generally speaking RAG comes in the game when it is impractical to use large context windows for three reasons: (1) accuracy drops as you stuff the context windows, (2) currently, context windows do not scale past 1M tokens, and (3) even with caching, moving millions of tokens is wasteful and not viable both in terms of costs and latency.

So we should really compare this to other RAG approaches. If we compare it to vector databases RAG, knowledge graphs have the advantage that they model the connections between datapoints. This is super important when asking questions that requires to reason across multiple pieces of information, i.e. multi-hop reasoning.

Also, the graph construction is essentially an exercise in cleaning data to extract the knowledge. Let me give you a practical example. Let's pretend we're indexing customer tickets for creating an AI assistant. If we were to store the data on the tickets as it is, we would overwhelm the vector database with all the noise coming from the conversational nature of this data. With knowledge graphs, we extract only the relevant entities and relationships and store the distilled knowledge in our graph. At query time, we find the answer over a structured data model that contains only clean information

HippoRAG is an amazing work and it was a source of inspiration for us as noted in the references. There are a couple of differences:

(1) FastGraphRAG allows the user to make the graph construction opinionated and specialized on a given domain and for a given use-case; this allows to clear out all the noise in the data and yields better results; (2) Unlike HippoRAG, FastGraphRAG initializes PageRank with a mixture of semantic retrieval and entity extractions; (3) HippoRAG is the outcome of an academic paper, and we saw the need for a more robust and production-ready implementation. Our repo is fully typed, includes tests, handles retries with Instructor, uses structured outputs, and so on.

Moving forward, we see our implementation diverge from HippoRAG more radically as we start to introduce new mechanisms such as weighted edges and negative PageRank to model repulsors.

At the moment this repo is designed to handle more RAG-oriented use cases, i.e. that require to recall the "top pieces of information" relevant to a given question/context. In your specific example, right now, FastGraphRAG would select the nodes that represent podcasts that are connected to Hilary Clinton, feed them to an LLM which would then select the ones that are positively associated with her. As a next step, we plan to weight the connections between nodes given the query. This way, PageRank will explore only edges which carry the concept "positively associated with", and only the right podcasts would be selected and returned, without having to ask an LLM to classify them. Note that this is basically a fuzzy join and so it will produce only a "best-effort" answer rather than an exact one.

Yes, feel free to try it out! You can specialize the graph for the codebase use-case by configuring the graph prompt, entity types, and example questions accordingly.

Yes, it works out-of-the-box with any OpenAI compatible API, including Ollama.

You can check out our example at https://github.com/circlemind-ai/fast-graphrag/blob/main/exa...

I think the main bit here is that the knowledge graph is entirely constructed by LLMs. It's not just using a pre-existing knowledge graph. It's creating a knowledge graph on the fly based on your data.

Navigating the graph, on the other hand, is the perfect task for PageRank.

You're right! Static knowledge is definitely one of the main limitations of other rag methods. Encoding information that changes over time is such a powerful feature of graphrag

In the past few weeks we’ve been working on implementing a fast and cheap version of graphrag. I hope that it can be helpful for your projects and it’d be great to have feedback to keep improving it and keep moving in the right direction.

We’re trying to keep the code tidy and organized. We enforced typing, and we’re raising the bar on test coverage. We’re still working on the docs, but the readme should help you get started.

Check it out here on GitHub: https://github.com/circlemind-ai/fast-graphrag

We’re still adding features and improving it based on the latest research and community input. We’d love to get feedback and see what people build with it. Any contribution is welcomed.

Is it really annoying though? It takes 5 seconds to respond to a pulse question and it is not disruptive at all. And you will have to respond just once a day.

On the flip side, it provides a structural mechanism for sharing feedback about what's working and what's not.

Hi! I’m Antonio, and I’m super excited to launch OfficeBird for the community. OfficeBird helps your team understand what matters to your team and develop your people.

The Problem — People are the most valuable asset to your team. OfficeBird is the best way to identify obstacles, celebrate strengths, and surface issues before they materialize. Especially for startups, maintaining a great relationship between people is crucial to your success. Moreover, many first-time founders don’t have enough people-management experience.

Our Solution — OfficeBird offers you daily pulse surveys delivered directly into your browser. We collect and aggregate these responses to deliver real-time insights and suggestions on what areas need care. All responses are 100% anonymous and confidential.

How does it work?

1. All team members install our Chrome extension, which will show them a new question every day directly in the browser.

2. We collect and aggregate these responses to deliver real-time insights and suggestions on what needs care. Are your people happy? Do they feel treated well? Do they think their work is meaningful?

3. We indicate the best learning material to help you and your team to work better together.

How to get started?

1. Head to http://officebird.co/auth/register and create an account

2. On the dashboard, go to the “Team Members” page and add all your team members*

3. Ask all your team members to install the OfficeBird Chrome Extension

4. Share their secret codes with them to let them join the team

* you won’t be able to add more than 5 team members. Please let me know if you need more people on board.