logdetective 0.2.2__tar.gz → 0.2.3__tar.gz

{logdetective-0.2.2 → logdetective-0.2.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: logdetective
-Version: 0.2.2
+Version: 0.2.3
 Summary: Log using LLM AI to search for build/test failures and provide ideas for fixing these.
 License: Apache-2.0
 Author: Jiri Podivin

{logdetective-0.2.2 → logdetective-0.2.3}/logdetective/constants.py

@@ -5,11 +5,16 @@ DEFAULT_ADVISOR = "TheBloke/Mistral-7B-Instruct-v0.2-GGUF"
 PROMPT_TEMPLATE = """
 Given following log snippets, and nothing else, explain what failure, if any, occured during build of this package.
 
-{}
+Analysis of the snippets must be in a format of [X] : [Y], where [X] is a log snippet, and [Y] is the explanation.
+Snippets themselves must not be altered in any way whatsoever.
+
+Snippets are delimited with '================'.
 
-Analysis of the failure must be in a format of [X] : [Y], where [X] is a log snippet, and [Y] is the explanation.
+Finally, drawing on information from all snippets, provide complete explanation of the issue and recommend solution.
 
-Finally, drawing on information from all snippets, provide complete explanation of the issue.
+Snippets:
+
+{}
 
 Analysis:
 

{logdetective-0.2.2 → logdetective-0.2.3}/logdetective/extractors.py

@@ -21,7 +21,7 @@ class LLMExtractor:
         self.grammar = LlamaGrammar.from_string(
             "root ::= (\"Yes\" | \"No\")", verbose=False)
 
-    def __call__(self, log: str, n_lines: int = 2, neighbors: bool = False) -> str:
+    def __call__(self, log: str, n_lines: int = 2, neighbors: bool = False) -> list[str]:
         chunks = self.rate_chunks(log)
         out = self.create_extract(chunks, neighbors)
         return out
@@ -43,11 +43,11 @@ class LLMExtractor:
 
         return results
 
-    def create_extract(self, chunks: list[tuple], neighbors: bool = False) -> str:
+    def create_extract(self, chunks: list[tuple], neighbors: bool = False) -> list[str]:
         """Extract interesting chunks from the model processing.
         """
         interesting = []
-        summary = ""
+        summary = []
         # pylint: disable=consider-using-enumerate
         for i in range(len(chunks)):
             if chunks[i][1].startswith("Yes"):
@@ -58,7 +58,7 @@ class LLMExtractor:
         interesting = set(interesting)
 
         for i in interesting:
-            summary += chunks[i][0] + "\n"
+            summary.append(chunks[i][0])
 
         return summary
 
@@ -75,8 +75,8 @@ class DrainExtractor:
         self.verbose = verbose
         self.context = context
 
-    def __call__(self, log: str) -> str:
-        out = ""
+    def __call__(self, log: str) -> list[str]:
+        out = []
         for chunk in get_chunks(log):
             processed_line = self.miner.add_log_message(chunk)
             LOG.debug(processed_line)
@@ -84,6 +84,6 @@ class DrainExtractor:
         for chunk in get_chunks(log):
             cluster = self.miner.match(chunk, "always")
             if cluster in sorted_clusters:
-                out += f"{chunk}\n"
+                out.append(chunk)
                 sorted_clusters.remove(cluster)
         return out

{logdetective-0.2.2 → logdetective-0.2.3}/logdetective/logdetective.py

@@ -3,7 +3,7 @@ import logging
 import sys
 
 from logdetective.constants import DEFAULT_ADVISOR
-from logdetective.utils import process_log, initialize_model, retrieve_log_content
+from logdetective.utils import process_log, initialize_model, retrieve_log_content, format_snippets
 from logdetective.extractors import LLMExtractor, DrainExtractor
 
 LOG = logging.getLogger("logdetective")
@@ -64,11 +64,15 @@ def main():
     log = retrieve_log_content(args.file)
     log_summary = extractor(log)
 
-    ratio = len(log_summary.split('\n')) / len(log.split('\n'))
-    LOG.debug("Log summary: \n %s", log_summary)
+    ratio = len(log_summary) / len(log.split('\n'))
+
     LOG.info("Compression ratio: %s", ratio)
 
     LOG.info("Analyzing the text")
+
+    log_summary = format_snippets(log_summary)
+    LOG.info("Log summary: \n %s", log_summary)
+
     print(f"Explanation: \n{process_log(log_summary, model)}")
 
 

{logdetective-0.2.2 → logdetective-0.2.3}/logdetective/server.py

@@ -37,7 +37,7 @@ async def analyze_log(build_log: BuildLog):
     log = requests.get(build_log.url, timeout=int(LOG_SOURCE_REQUEST_TIMEOUT)).text
     log_summary = extractor(log)
 
-    ratio = len(log_summary.split('\n')) / len(log.split('\n'))
+    ratio = len(log_summary) / len(log.split('\n'))
     LOG.debug("Log summary: \n %s", log_summary)
     LOG.info("Compression ratio: %s", ratio)
 

{logdetective-0.2.2 → logdetective-0.2.3}/logdetective/utils.py

@@ -81,6 +81,7 @@ def process_log(log: str, model: Llama) -> str:
     """
     return model(PROMPT_TEMPLATE.format(log), max_tokens=0)["choices"][0]["text"]
 
+
 def retrieve_log_content(log_path: str) -> str:
     """Get content of the file on the log_path path."""
     parsed_url = urlparse(log_path)
@@ -97,3 +98,18 @@ def retrieve_log_content(log_path: str) -> str:
         log = requests.get(log_path, timeout=60).text
 
     return log
+
+
+def format_snippets(snippets: list[str]) -> str:
+    """Format snippets, giving them separator, id and finally
+    concatenating them.
+    """
+    summary = ""
+    for i, s in enumerate(snippets):
+        summary += f"""
+        Snippet No. {i}:
+
+        {s}
+        ================
+        """
+    return summary

{logdetective-0.2.2 → logdetective-0.2.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "logdetective"
-version = "0.2.2"
+version = "0.2.3"
 description = "Log using LLM AI to search for build/test failures and provide ideas for fixing these."
 authors = ["Jiri Podivin <jpodivin@gmail.com>"]
 license = "Apache-2.0"