remove classic optimize

[klirichek]

Only progressive is in game from now

Type of Change (select one):

• Bug fix
• New feature
• Documentation update

Description of the Change:

Related Issue (provide the link):

[github-actions]

clt

❌ CLT tests in test/clt-tests/mcl/auto-embeddings-dml-test test/clt-tests/mcl/auto-embeddings-duplicate-id test/clt-tests/mcl/auto-embeddings-edge-cases test/clt-tests/mcl/auto-embeddings-endpoints test/clt-tests/mcl/auto-embeddings-error-handling test/clt-tests/mcl/auto-embeddings-from-vector-check test/clt-tests/mcl/auto-embeddings-hnsw-configs test/clt-tests/mcl/auto-embeddings-jina-remote test/clt-tests/mcl/auto-embeddings-json-api
✅ OK: 8
❌ Failed: 1
⏳ Duration: 575s
👉 Check Action Results for commit 53b1b9a

Failed tests:

🔧 Edit failed tests in UI:

• Edit test/clt-tests/mcl/auto-embeddings-jina-remote.rec

test/clt-tests/mcl/auto-embeddings-jina-remote.rec

––– input –––
rm -f /var/log/manticore/searchd.log; stdbuf -oL searchd --stopwait > /dev/null; stdbuf -oL searchd ${SEARCHD_ARGS:-} > /dev/null
––– output –––
OK
––– input –––
if timeout 10 grep -qm1 'accepting connections' <(tail -n 1000 -f /var/log/manticore/searchd.log); then echo 'Accepting connections!'; else echo 'Timeout or failed!'; fi
––– output –––
OK
––– input –––
cosine_similarity() {
    local file1="$1" file2="$2"

    awk '
    NR==FNR { a[NR]=$1; suma2+=$1*$1; next }
    {
        dot += a[FNR]*$1
        sumb2 += $1*$1
    }
    END {
        print dot / (sqrt(suma2) * sqrt(sumb2))
    }' "$file1" "$file2"
}
––– output –––
OK
––– input –––
export -f cosine_similarity
––– output –––
OK
––– input –––
mysql -h0 -P9306 -e "CREATE TABLE test_invalid_model (title TEXT, embedding FLOAT_VECTOR KNN_TYPE='hnsw' HNSW_SIMILARITY='l2' MODEL_NAME = 'jina/invalid-model-name-12345' FROM = 'title') " 2>&1
––– output –––
OK
––– input –––
mysql -h0 -P9306 -e "CREATE TABLE test_valid_model_no_api_key (title TEXT, embedding FLOAT_VECTOR KNN_TYPE='hnsw' HNSW_SIMILARITY='l2' MODEL_NAME = 'jina/jina-embeddings-v2-base-en' FROM = 'title') " 2>&1
––– output –––
OK
––– input –––
mysql -h0 -P9306 -e "CREATE TABLE test_jina_remote (title TEXT, content TEXT, description TEXT, embedding FLOAT_VECTOR KNN_TYPE='hnsw' HNSW_SIMILARITY='l2' MODEL_NAME = 'jina/jina-embeddings-v4' FROM = 'title, content' API_KEY='${JINA_API_KEY}') "; echo $?
––– output –––
OK
––– input –––
mysql -h0 -P9306 -E -e "SHOW CREATE TABLE test_jina_remote"
––– output –––
OK
––– input –––
mysql -h0 -P9306 -e "INSERT INTO test_jina_remote (id, title, content, description) VALUES(1, 'machine learning algorithms', 'deep neural networks and artificial intelligence', 'advanced AI research')"; echo $?
––– output –––
- 0
+ ERROR 1064 (42000) at line 1: Failed to send request to remote model
+ 1
––– input –––
mysql -h0 -P9306 -e "SELECT COUNT(*) as record_count FROM test_jina_remote WHERE id=1"
––– output –––
+--------------+
| record_count |
+--------------+
- |            1 |
+ |            0 |
+--------------+
––– input –––
mysql -h0 -P9306 -e "INSERT INTO test_jina_remote (id, title, content, description) VALUES(2, 'machine learning algorithms', 'deep neural networks and artificial intelligence', 'different description')"

mysql -h0 -P9306 -e "SELECT embedding FROM test_jina_remote WHERE id=1" | \
    grep -v embedding | \
    sed 's/[0-9]\+\(\.[0-9]\+\)\?/\n&\n/g' | \
    grep -E '^[0-9]+(\.[0-9]+)?$' | \
    awk '{printf "%.5f\n", $1}' > /tmp/vector1.txt

mysql -h0 -P9306 -e "SELECT embedding FROM test_jina_remote WHERE id=2" | \
    grep -v embedding | \
    sed 's/[0-9]\+\(\.[0-9]\+\)\?/\n&\n/g' | \
    grep -E '^[0-9]+(\.[0-9]+)?$' | \
    awk '{printf "%.5f\n", $1}' > /tmp/vector2.txt

SIMILARITY=$(cosine_similarity /tmp/vector1.txt /tmp/vector2.txt)

echo "Cosine similarity: $SIMILARITY"

RESULT=$(awk -v sim="$SIMILARITY" 'BEGIN {
    if (sim > 0.99)
        print "SUCCESS: Same FROM fields produce similar vectors (similarity: " sim ")"
    else
        print "FAIL: Different vectors (FROM does not include description field and should not change generated vector value) (similarity: " sim ")"
}')

echo "$RESULT"

rm -f /tmp/vector1.txt /tmp/vector2.txt
––– output –––
- Cosine similarity: #!/(1|0\.[0-9]+)/!#
+ ERROR 1064 (42000) at line 1: Failed to send request to remote model
- SUCCESS: Same FROM fields produce similar vectors (similarity: #!/(1|0\.[0-9]+)/!#)
+ Cosine similarity: -nan
+ FAIL: Different vectors (FROM does not include description field and should not change generated vector value) (similarity: -nan)
––– input –––
mysql -h0 -P9306 -e "CREATE TABLE test_jina_title_only (title TEXT, content TEXT, embedding FLOAT_VECTOR KNN_TYPE='hnsw' HNSW_SIMILARITY='l2' MODEL_NAME = 'jina/jina-embeddings-v4' FROM = 'title' API_KEY='${JINA_API_KEY}') "; mysql -h0 -P9306 -e "INSERT INTO test_jina_title_only (id, title, content) VALUES(1, 'machine learning algorithms', 'completely different content here')"; MD5_MULTI=$(mysql -h0 -P9306 -e "SELECT embedding FROM test_jina_remote WHERE id=1" | grep -v embedding | md5sum | awk '{print $1}'); MD5_SINGLE=$(mysql -h0 -P9306 -e "SELECT embedding FROM test_jina_title_only WHERE id=1" | grep -v embedding | md5sum | awk '{print $1}'); echo "multi_field_md5: $MD5_MULTI"; echo "single_field_md5: $MD5_SINGLE"; if [ "$MD5_MULTI" != "$MD5_SINGLE" ]; then echo "SUCCESS: Different FROM specifications produce different vectors"; else echo "INFO: FROM field comparison result"; fi
––– output –––
- multi_field_md5: #!/[0-9a-f]{32}/!#
+ ERROR 1064 (42000) at line 1: Failed to send request to remote model
- single_field_md5: #!/[0-9a-f]{32}/!#
+ multi_field_md5: d41d8cd98f00b204e9800998ecf8427e
- SUCCESS: Different FROM specifications produce different vectors
+ single_field_md5: d41d8cd98f00b204e9800998ecf8427e
+ INFO: FROM field comparison result
––– input –––
mysql -h0 -P9306 -e "CREATE TABLE test_jina_invalid_field (title TEXT, embedding FLOAT_VECTOR KNN_TYPE='hnsw' HNSW_SIMILARITY='l2' MODEL_NAME = 'jina/text-embedding-ada-002' FROM = 'nonexistent_field') " 2>&1
––– output –––
OK
––– input –––
if mysql -h0 -P9306 -e "SHOW TABLES LIKE 'test_jina_no_from'" | grep -q test_jina_no_from; then mysql -h0 -P9306 -e "INSERT INTO test_jina_no_from (id, title, embedding) VALUES(1, 'test title', '(0.1, 0.2, 0.3, 0.4, 0.5)')"; echo "insert_result: $?"; else echo "insert_result: skipped (table not created)"; fi
––– output –––
OK
––– input –––
if mysql -h0 -P9306 -e "SHOW TABLES LIKE 'test_jina_no_from'" | grep -q test_jina_no_from; then mysql -h0 -P9306 -e "SHOW CREATE TABLE test_jina_no_from"; else echo "table_structure: skipped (table not created)"; fi
––– output –––
OK
––– input –––
if [ -n "$JINA_API_KEY" ] && [ "$JINA_API_KEY" != "dummy_key_for_testing" ]; then echo "API key is available for testing"; else echo "API key not available - using dummy for error testing"; fi
––– output –––
OK