It finds similar-looking code with embeddings. This detects more than just copy-paste clones or even clones with minor changes. Similar code is often not a clone to refactor, and this is a trade-off. Initial results need to be verified, but coding agents can do this quickly. Example prompts are available on https://slopo.dev
Additionally, similar code distant in the codebase is ranked higher to focus on less obvious duplication.
The results differ a lot depending on the codebase. I noticed that sometimes most of the detected duplicates are false positives, but the remaining ones are strong candidates to refactor or even bugs. Sometimes it reveals much more real duplication.
I would also consider - perhaps as a separate pass, with scoring set differently - to analyze comments (especially docstrings in Python). If I read the code correctly, you're currently just stripping them, which is the right thing to do when looking for code duplication, but duplicated docstrings are also often a signal that something is wrong in the codebase. The "different scoring" is because we expect docstring to be structured similarly (at least more than normal code), so some tweaking would be needed.
Finally: very nice project, congrats! :)
[1] https://github.com/rafal-qa/slopo/blob/main/src/slopo/indexi...
Skipping the extraction of conditional branches was my decision to not overcomplicate the first versions, which was intended to validate the idea. I will add this in future versions because I agree it's needed for large functions.
I don't think it needs configurable granularity. In the current version, there is an analogous mechanism: when functions are nested, both outer and inner are embedded separately. When both are similar to each other, this pair is excluded. Inner or outer functions can appear in results depending on similarity to other units.
Regarding comments, they are removed and I will think about handling them. The challenge is not with extraction, but with how to present this in a report. This may be a nice addition because coding agents often add comments.
Thanks for the feedback.
Does the project you simply compute embeddings for every function unit and cluster them, or do we also mean-pool significant dependencies of a function? In other words, given the function
def a():
b()
c()
d()
[1] https://github.com/rafal-qa/slopo/blob/main/src/slopo/indexi...
Deduplication backend is the easiest part of the tool and it doesn't need any additional libraries. Just calculate embeddings and find close pairs. The complexity is everything around.
Using local models is worth considering and the tool already uses the LiteLLM wrapper, allowing it to configure different models, including local. I left this part for the user.
I also don't think the backend is the "easiest part" here, a lot of the scalability lives there, which is important for monorepos, or cases where you want to deduplicate across projects. For example, from looking at the implementation, you use exact brute-force similarity search (comparing every item to every other item) which is an O(n^2) operation. It also allocates large dense similarity blocks in memory, so memory use won’t scale well either.
The goal of the tool is to also detect code that is similar and behaves differently. There are not ideal duplicates, but still a code that can be refactored, abstracted, or fixed (because the variance may be the result of bug).
jscpd is advertised as "Copy/paste detector", Slopo is advertised as "non-exact code duplication".
Slopo also detects copy/pasted code, but this is not the main goal and the report focuses more on similar code units.
If you are interested in data, you can check my article. Analysis was done with this tool, but a previous version where exact-copy duplicates were excluded from analysis. https://rkochanowski.com/article/analysis-code-duplication/
But I plan to do my own analysis of different embedding models in the context of code similarity detection. Including BM25 in the comparison is a very good idea.
If by "more efficient" you mean to avoid embedding of the same code multiple times, this optimization is already implemented internally.
How do you handle chunking and parsing for different languages to make sure the embeddings capture semantic meaning effectively? For instance, do you chunk by functions/classes, or use a fixed token window? If a function is too long or too short, it can drastically skew the embedding similarity.
The chunk size has allowed range and those outside are simply ignored.
- Upper limit is hardcoded with a body size of 10k chars
- Lower limit is configurable with a default of 10 AST nodes inside the body
The chunking strategy is something that can be improved in future versions.
While testing this tool, one detected duplication was interesting for a use case. Permission check logic was duplicated and placed in different distant places in the codebase. The code was similar, but not identical, the logic was not the same. One version had stricter checks. I analyzed this with the coding agent, and we found out that both versions are used for the same thing, which means that in some cases validation is insufficient. Having only a single validation place, this bug could be prevented or easily detected.
If so - maintainability, testability. This is old software engineering best practice at this point.
You shouldn’t hyper optimize for deduplication, but it’s usually worth considering. Fewer places to fix issues or improve as well.
On testability: two implementations can be tested against each other, leading to greater coverage with less test code. It doesn't work that way for 3+ implementations, which is another reason not to have that many.
* cluster-01.md has the highest similarity, and jscpd probably will detect this too.
* cluster-10.md has the lowest similarity still above the threshold, and I don't think jscpd will detect this as clones. Because they are not clones, this is a false positive that needs to be discarded. But in other cases this kind of similar code may be worth acting on.
I didn't compare with jscpd because I don't consider it a competition. Embedding-based duplication detection works differently, gives different results and has its own trade-offs.
Embedding calculation is also outsourced externally: it's only a simple API call with a LiteLLM wrapper.
"brute-force similarity search" and O(n^2) may sound scary, but it works fine and this is not a bottleneck. For large projects, other parts are much slower, which has room for improvement. [1] is an implementation you probably saw. It uses NumPy, spreads work across all CPU cores and there is also a split into blocks (block_size = 1000). In larger sets, all vectors are not loaded into memory at once. Where I need to be honest, I didn't measure actual memory usage. I just tested this on large repos, so I'm aware of bottlenecks.
From my perspective, this is the easiest part. Code extraction, chunking, applying boost, clustering, generating report and designing everything as a single user-friendly tool is a real challenge. Architectural and product decisions are more difficult than implementation and solving performance issues.
[1] https://github.com/rafal-qa/slopo/blob/v0.3.0/src/slopo/anal...
"In larger sets, all vectors are not loaded into memory at once": this is also not correct, at least in the implementation you shared. The similarity matrix is processed in blocks, but the embeddings themselves are loaded all at once and stacked into one NumPy matrix, hence the memory peak.
So in larger projects, more than half of the time is spent on the similarity search step, and almost all the memory is spent there as well.
To give more context, the current version is already an optimized one I considered good enough and didn't spend more time on it. In the first attempt, I used a vector database with indexes, trying to query for similar vectors. This was uselessly slow even in medium-sized repos. The brute-force NumPy solution is a significant improvement, making it faster than other calculations like clustering.
"vectors are not loaded into memory at once" is not true, I had in mind splitting computation into blocks.
One possible simple optimization is to use 16-bit floats in vector instead of 32-bit. I used this in a different project (halfvec in pgvector) without affecting results.
1536-dim embeddings from your case also can be reduced. This large vector usually doesn't give much benefit compared to smaller ones. And this is something I will compare in my own tests.