Vector embedding of relational code sets

A computer program product comprising:

• one or more computer readable storage media and program instructions stored on the one or more computer readable storage media, the stored program instructions comprising:
• program instructions to create a dictionary for each source code commit in a set of historical source code commits associated with a software deployment, wherein each dictionary comprises a commit level, an associated defect label, and associated logs;
• program instructions to generate a vector embedding for a source code commit pair based on a set of log differences between source code commit pairs, wherein the vector embedding is attached with a defect label, wherein the source code commit pair comprises a dictionary and a subsequent dictionary;
• program instructions to generate, responsive to a new source code commit, a new vector embedding based on a set of log differences between the new source code commit and a preceding source code commit, comprising:
• program instructions to suspend a push of the new source code commit;
• program instructions to push, responsive to the generated defect likelihood, the new source code commit to one or more environments;
• program instructions to generate a defect likelihood utilizing the generated new vector embedding;
• and
• program instructions to determine responsive to the generated defect likelihood exceeding a defect likelihood threshold, that the new source code commit contains defects.

A computer system comprising:

• one or more computer processors;
• one or more computer readable storage media;
• and
• program instructions stored on the computer readable storage media for execution by at least one of the one or more processors, the stored program instructions comprising:
• program instructions to create a dictionary for each source code commit in a set of historical source code commits associated with a software deployment, wherein each dictionary comprises a commit level, an associated defect label, and associated logs;
• program instructions to generate a vector embedding for a source code commit pair based on a set of log differences between source code commit pairs, wherein the vector embedding is attached with a defect label, wherein the source code commit pair comprises a dictionary and a subsequent dictionary;
• program instructions to generate, responsive to a new source code commit, a new vector embedding based on a set of log differences between the new source code commit and a preceding source code commit, comprising:
• program instructions to suspend a push of the new source code commit;
• program instructions to push, responsive to the generated defect likelihood, the new source code commit to one or more environments;
• program instructions to generate a defect likelihood utilizing the generated new vector embedding;
• and
• program instructions to determine responsive to the generated defect likelihood exceeding a defect likelihood threshold, that the new source code commit contains defects.