Learnt from: generall
Repo: qdrant/qdrant PR: 6854
File: lib/segment/src/index/query_estimator.rs:320-327
Timestamp: 2025-07-11T11:35:21.549Z
Learning: In test code for Qdrant's query estimator (lib/segment/src/index/query_estimator.rs), simplified ID resolution logic using `id.to_string().parse().unwrap()` is acceptable for testing purposes and doesn't need to match production code's `id_tracker.internal_id()` approach. Test code can use mock implementations that serve the testing goals.

Learnt from: generall
Repo: qdrant/qdrant PR: 7100
File: lib/segment/src/index/field_index/full_text_index/inverted_index/mutable_inverted_index.rs:82-100
Timestamp: 2025-08-20T15:03:18.522Z
Learning: The merge_postings_iterator function in lib/segment/src/index/field_index/full_text_index/inverted_index/postings_iterator.rs handles deduplication internally, so there's no need to add .dedup() when using it for OR-merge operations in inverted indexes.

Learnt from: generall
Repo: qdrant/qdrant PR: 7400
File: lib/segment/src/id_tracker/simple_id_tracker.rs:234-241
Timestamp: 2025-10-13T22:58:03.121Z
Learning: SimpleIdTracker in lib/segment/src/id_tracker/simple_id_tracker.rs is being deprecated and should not receive fixes related to version tracking or recovery logic, as it has a different version storage structure that is incompatible with newer trackers.

Learnt from: generall
Repo: qdrant/qdrant PR: 7006
File: lib/collection/src/operations/verification/update.rs:158-174
Timestamp: 2025-08-10T18:30:02.986Z
Learning: In Qdrant's strict mode verification code (lib/collection/src/operations/verification/update.rs), exhaustive pattern matching without `..` is intentionally used for structs like PointsBatch and PointsList. This design pattern ensures compilation fails when new fields are added, forcing developers to explicitly consider how new fields should be handled in the indexed_filter_write method. This provides visibility and compile-time safety for struct evolution.

Learnt from: IvanPleshkov
Repo: qdrant/qdrant PR: 7193
File: lib/segment/src/vector_storage/quantized/quantized_chunked_mmap_storage.rs:17-30
Timestamp: 2025-09-01T11:19:26.371Z
Learning: In lib/segment/src/vector_storage/quantized/quantized_chunked_mmap_storage.rs, the ChunkedMmapVectors underlying implementation does not validate against zero-sized vectors, so adding such validation in QuantizedChunkedMmapStorage::new is unnecessary and would be redundant.

Learnt from: IvanPleshkov
Repo: qdrant/qdrant PR: 6986
File: lib/segment/src/vector_storage/quantized/quantized_ram_storage.rs:46-55
Timestamp: 2025-08-11T00:37:34.100Z
Learning: In `lib/segment/src/vector_storage/quantized/quantized_ram_storage.rs`, the `ChunkedVectors` used in `QuantizedRamStorage` is intentionally designed to be non-persistent during updates. The `push_vector` method only updates the in-memory vectors without flushing to disk, and this is expected behavior rather than a bug.

Learnt from: generall
Repo: qdrant/qdrant PR: 6854
File: lib/segment/src/index/query_estimator.rs:320-327
Timestamp: 2025-07-11T11:35:21.549Z
Learning: In test code for Qdrant's query estimator (lib/segment/src/index/query_estimator.rs), simplified ID resolution logic using `id.to_string().parse().unwrap()` is acceptable for testing purposes and doesn't need to match production code's `id_tracker.internal_id()` approach. Test code can use mock implementations that serve the testing goals.

Learnt from: IvanPleshkov
Repo: qdrant/qdrant PR: 6986
File: lib/segment/src/vector_storage/quantized/quantized_vectors.rs:81-84
Timestamp: 2025-08-11T07:57:01.399Z
Learning: In `lib/segment/src/vector_storage/quantized/quantized_vectors.rs`, the BitsStoreType parameter difference between single-vector and multi-vector Binary quantization is intentional: single-vector storage uses `EncodedVectorsBin<u128, ...>` to enable 128-bit SIMD/popcount optimizations for longer vectors, while multi-vector storage uses `EncodedVectorsBin<u8, ...>` because multivectors are typically shorter and benefit from byte-granular storage.

Learnt from: IvanPleshkov
Repo: qdrant/qdrant PR: 7043
File: lib/segment/src/vector_storage/quantized/quantized_mmap_storage.rs:86-90
Timestamp: 2025-08-15T11:42:00.297Z
Learning: In lib/segment/src/vector_storage/quantized/quantized_mmap_storage.rs, overflow protection for encoded_storage_size computation (quantized_vector_size * vectors_count) is implemented in PR #7048, using checked_mul with u64 casting to prevent silent overflow.

Learnt from: generall
Repo: qdrant/qdrant PR: 7400
File: lib/segment/src/id_tracker/simple_id_tracker.rs:234-241
Timestamp: 2025-10-13T22:58:03.121Z
Learning: SimpleIdTracker in lib/segment/src/id_tracker/simple_id_tracker.rs is being deprecated and should not receive fixes related to version tracking or recovery logic, as it has a different version storage structure that is incompatible with newer trackers.

Learnt from: IvanPleshkov
Repo: qdrant/qdrant PR: 7043
File: lib/segment/src/vector_storage/quantized/quantized_vectors.rs:857-857
Timestamp: 2025-08-15T11:41:10.629Z
Learning: In `lib/segment/src/vector_storage/quantized/quantized_vectors.rs`, the multivector offset storage has two different patterns: for RAM storage, offsets are collected into Vec<MultivectorOffset> and used directly; for MMAP storage, offsets are consumed to create a file via create_offsets_file_from_iter, then the file is loaded back as MultivectorOffsetsStorageMmap. The direct consumption of offsets iterator in the MMAP case is intentional.

Learnt from: IvanPleshkov
Repo: qdrant/qdrant PR: 7048
File: lib/quantization/src/encoded_storage.rs:61-79
Timestamp: 2025-08-14T11:31:21.777Z
Learning: In test storage implementations (like TestEncodedStorage in lib/quantization/src/encoded_storage.rs), IvanPleshkov prefers to keep the code simple rather than adding complex overflow protection, since test storage is not used in production and can be allowed to panic on edge cases.

Learnt from: coszio
Repo: qdrant/qdrant PR: 6609
File: lib/gridstore/src/blob.rs:46-59
Timestamp: 2025-06-02T18:10:47.203Z
Learning: In the Qdrant codebase, zerocopy crate is extensively used for safe byte-level operations across GPU operations, HNSW indices, memory-mapped structures, and serialization. When implementing Blob trait for generic Vec<T>, using zerocopy's FromBytes and IntoBytes traits is preferred over size_of::<T>() because it guarantees memory layout equals byte representation, making serialization safe and correct.

Learnt from: coszio
Repo: qdrant/qdrant PR: 7368
File: lib/shard/src/query/mod.rs:313-341
Timestamp: 2025-10-16T13:00:46.809Z
Learning: In the Qdrant codebase, for the `Feedback` query variant in `lib/shard/src/query/mod.rs`, validation for sparse vectors should happen down the line rather than early in the `query_enum_from_grpc_raw_query` function. The `Nearest` variant is treated as a special case where early validation with better error messages is acceptable.

Learnt from: IvanPleshkov
Repo: qdrant/qdrant PR: 7043
File: lib/segment/src/vector_storage/quantized/quantized_multivector_storage.rs:340-347
Timestamp: 2025-08-18T10:56:43.707Z
Learning: In lib/segment/src/vector_storage/quantized/quantized_multivector_storage.rs, the create_offsets_file_from_iter function intentionally requires paths to have a parent directory and returns an error if path.parent() is None. This was a conscious design decision to ensure proper path validation.

Learnt from: generall
Repo: qdrant/qdrant PR: 6323
File: lib/segment/src/vector_storage/quantized/quantized_mmap_storage.rs:12-16
Timestamp: 2025-04-07T23:31:22.515Z
Learning: The `populate()` method in `QuantizedMmapStorage` correctly returns void instead of a `Result` because it directly implements the `Madviseable` trait which defines `populate(&self)` without a return type. Adding an unnecessary `Ok(())` return would trigger Clippy warnings about unnecessary Result wrapping.

Learnt from: generall
Repo: qdrant/qdrant PR: 7006
File: lib/collection/src/operations/verification/update.rs:158-174
Timestamp: 2025-08-10T18:30:02.986Z
Learning: In Qdrant's strict mode verification code (lib/collection/src/operations/verification/update.rs), exhaustive pattern matching without `..` is intentionally used for structs like PointsBatch and PointsList. This design pattern ensures compilation fails when new fields are added, forcing developers to explicitly consider how new fields should be handled in the indexed_filter_write method. This provides visibility and compile-time safety for struct evolution.

Learnt from: timvisee
Repo: qdrant/qdrant PR: 7526
File: src/wal_pop.rs:7-8
Timestamp: 2025-11-14T10:01:31.926Z
Learning: In the Qdrant codebase, development binaries (like src/wal_pop.rs) don't require explicit bounds checking for command-line arguments. Rust's built-in out-of-bounds panic is acceptable for these development tools.