logdetective 1.4.0__tar.gz → 1.5.0__tar.gz

{logdetective-1.4.0 → logdetective-1.5.0}/PKG-INFO

@@ -1,12 +1,12 @@
 Metadata-Version: 2.3
 Name: logdetective
-Version: 1.4.0
+Version: 1.5.0
 Summary: Log using LLM AI to search for build/test failures and provide ideas for fixing these.
 License: Apache-2.0
 Author: Jiri Podivin
 Author-email: jpodivin@gmail.com
 Requires-Python: >=3.11,<4.0
-Classifier: Development Status :: 4 - Beta
+Classifier: Development Status :: 5 - Production/Stable
 Classifier: Environment :: Console
 Classifier: Intended Audience :: Developers
 Classifier: License :: OSI Approved :: Apache Software License
@@ -87,8 +87,8 @@ Usage
 To analyze a log file, run the script with the following command line arguments:
 - `url` (required): The URL of the log file to be analyzed.
 - `--model` (optional, default: "Mistral-7B-Instruct-v0.2-GGUF"): The path or URL of the language model for analysis. As we are using LLama.cpp we want this to be in the `gguf` format. You can include the download link to the model here. If the model is already on your machine it will skip the download.
-- `--summarizer` (optional, default: "drain"): Choose between LLM and Drain template miner as the log summarizer. You can also provide the path to an existing language model file instead of using a URL.
-- `--n_lines` (optional, default: 8): The number of lines per chunk for LLM analysis. This only makes sense when you are summarizing with LLM.
+- `--summarizer` DISABLED: LLM summarization option was removed. Argument is kept for backward compatibility only.(optional, default: "drain"): Choose between LLM and Drain template miner as the log summarizer. You can also provide the path to an existing language model file instead of using a URL.
+- `--n_lines` DISABLED: LLM summarization option was removed. Argument is kept for backward compatibility only. (optional, default: 8): The number of lines per chunk for LLM analysis. This only makes sense when you are summarizing with LLM.
 - `--n_clusters` (optional, default 8): Number of clusters for Drain to organize log chunks into. This only makes sense when you are summarizing with Drain
 
 Example usage:
@@ -376,6 +376,9 @@ HTTPS certificate generated through:
 certbot certonly --standalone -d logdetective01.fedorainfracloud.org
 ```
 
+Certificates need to be be placed into location specified by the`LOGDETECTIVE_CERTDIR`
+env var and the service should be restarted.
+
 Querying statistics
 -------------------
 

{logdetective-1.4.0 → logdetective-1.5.0}/README.md

@@ -43,8 +43,8 @@ Usage
 To analyze a log file, run the script with the following command line arguments:
 - `url` (required): The URL of the log file to be analyzed.
 - `--model` (optional, default: "Mistral-7B-Instruct-v0.2-GGUF"): The path or URL of the language model for analysis. As we are using LLama.cpp we want this to be in the `gguf` format. You can include the download link to the model here. If the model is already on your machine it will skip the download.
-- `--summarizer` (optional, default: "drain"): Choose between LLM and Drain template miner as the log summarizer. You can also provide the path to an existing language model file instead of using a URL.
-- `--n_lines` (optional, default: 8): The number of lines per chunk for LLM analysis. This only makes sense when you are summarizing with LLM.
+- `--summarizer` DISABLED: LLM summarization option was removed. Argument is kept for backward compatibility only.(optional, default: "drain"): Choose between LLM and Drain template miner as the log summarizer. You can also provide the path to an existing language model file instead of using a URL.
+- `--n_lines` DISABLED: LLM summarization option was removed. Argument is kept for backward compatibility only. (optional, default: 8): The number of lines per chunk for LLM analysis. This only makes sense when you are summarizing with LLM.
 - `--n_clusters` (optional, default 8): Number of clusters for Drain to organize log chunks into. This only makes sense when you are summarizing with Drain
 
 Example usage:
@@ -332,6 +332,9 @@ HTTPS certificate generated through:
 certbot certonly --standalone -d logdetective01.fedorainfracloud.org
 ```
 
+Certificates need to be be placed into location specified by the`LOGDETECTIVE_CERTDIR`
+env var and the service should be restarted.
+
 Querying statistics
 -------------------
 

{logdetective-1.4.0 → logdetective-1.5.0}/logdetective/constants.py

@@ -26,17 +26,6 @@ Analysis:
 
 """
 
-SUMMARIZATION_PROMPT_TEMPLATE = """
-Does following log contain error or issue?
-
-Log:
-
-{}
-
-Answer:
-
-"""
-
 SNIPPET_PROMPT_TEMPLATE = """
 Analyse following RPM build log snippet. Describe contents accurately, without speculation or suggestions for resolution.
 

logdetective-1.5.0/logdetective/extractors.py

@@ -0,0 +1,42 @@
+import os
+import logging
+from typing import Tuple
+
+import drain3
+from drain3.template_miner_config import TemplateMinerConfig
+
+from logdetective.utils import get_chunks
+
+LOG = logging.getLogger("logdetective")
+
+
+class DrainExtractor:
+    """A class that extracts information from logs using a template miner algorithm."""
+
+    def __init__(self, verbose: bool = False, context: bool = False, max_clusters=8):
+        config = TemplateMinerConfig()
+        config.load(f"{os.path.dirname(__file__)}/drain3.ini")
+        config.profiling_enabled = verbose
+        config.drain_max_clusters = max_clusters
+        self.miner = drain3.TemplateMiner(config=config)
+        self.verbose = verbose
+        self.context = context
+
+    def __call__(self, log: str) -> list[Tuple[int, str]]:
+        out = []
+        # First pass create clusters
+        for _, chunk in get_chunks(log):
+            processed_chunk = self.miner.add_log_message(chunk)
+            LOG.debug(processed_chunk)
+        # Sort found clusters by size, descending order
+        sorted_clusters = sorted(
+            self.miner.drain.clusters, key=lambda it: it.size, reverse=True
+        )
+        # Second pass, only matching lines with clusters,
+        # to recover original text
+        for chunk_start, chunk in get_chunks(log):
+            cluster = self.miner.match(chunk, "always")
+            if cluster in sorted_clusters:
+                out.append((chunk_start, chunk))
+                sorted_clusters.remove(cluster)
+        return out

{logdetective-1.4.0 → logdetective-1.5.0}/logdetective/logdetective.py

@@ -15,7 +15,7 @@ from logdetective.utils import (
     compute_certainty,
     load_prompts,
 )
-from logdetective.extractors import LLMExtractor, DrainExtractor
+from logdetective.extractors import DrainExtractor
 
 LOG = logging.getLogger("logdetective")
 
@@ -49,16 +49,16 @@ def setup_args():
         "--summarizer",
         type=str,
         default="drain",
-        help="Choose between LLM and Drain template miner as the log summarizer.\
-                                LLM must be specified as path to a model, URL or local file.",
+        help="DISABLED: LLM summarization option was removed. \
+                Argument is kept for backward compatibility only.",
     )
     parser.add_argument(
         "-N",
         "--n_lines",
         type=int,
-        default=8,
-        help="The number of lines per chunk for LLM analysis.\
-                            This only makes sense when you are summarizing with LLM.",
+        default=None,
+        help="DISABLED: LLM summarization option was removed. \
+                Argument is kept for backward compatibility only.",
     )
     parser.add_argument(
         "-C",
@@ -74,13 +74,13 @@ def setup_args():
         "--prompts",
         type=str,
         default=f"{os.path.dirname(__file__)}/prompts.yml",
-        help="Path to prompt configuration file."
+        help="Path to prompt configuration file.",
     )
     parser.add_argument(
         "--temperature",
         type=float,
         default=DEFAULT_TEMPERATURE,
-        help="Temperature for inference."
+        help="Temperature for inference.",
     )
     return parser.parse_args()
 
@@ -93,6 +93,10 @@ async def run():  # pylint: disable=too-many-statements,too-many-locals
         sys.stderr.write("Error: --quiet and --verbose is mutually exclusive.\n")
         sys.exit(2)
 
+    # Emit warning about use of discontinued args
+    if args.n_lines or args.summarizer != "drain":
+        LOG.warning("LLM based summarization was removed. Drain will be used instead.")
+
     # Logging facility setup
     log_level = logging.INFO
     if args.verbose >= 1:
@@ -116,18 +120,10 @@ async def run():  # pylint: disable=too-many-statements,too-many-locals
         LOG.error("You likely do not have enough memory to load the AI model")
         sys.exit(3)
 
-    # Log file summarizer selection and initialization
-    if args.summarizer == "drain":
-        extractor = DrainExtractor(
-            args.verbose > 1, context=True, max_clusters=args.n_clusters
-        )
-    else:
-        summarizer_model = initialize_model(args.summarizer, verbose=args.verbose > 2)
-        extractor = LLMExtractor(
-            summarizer_model,
-            args.verbose > 1,
-            prompts_configuration.summarization_prompt_template,
-        )
+    # Log file summarizer initialization
+    extractor = DrainExtractor(
+        args.verbose > 1, context=True, max_clusters=args.n_clusters
+    )
 
     LOG.info("Getting summary")
 
@@ -151,7 +147,8 @@ async def run():  # pylint: disable=too-many-statements,too-many-locals
 
     prompt = (
         f"{prompts_configuration.default_system_prompt}\n"
-        f"{prompts_configuration.prompt_template}")
+        f"{prompts_configuration.prompt_template}"
+    )
 
     stream = True
     if args.no_stream:
@@ -191,7 +188,7 @@ async def run():  # pylint: disable=too-many-statements,too-many-locals
 
 
 def main():
-    """ Evaluate logdetective program and wait for it to finish """
+    """Evaluate logdetective program and wait for it to finish"""
     asyncio.run(run())
 
 

{logdetective-1.4.0 → logdetective-1.5.0}/logdetective/models.py

@@ -4,7 +4,6 @@ from pydantic import BaseModel
 from logdetective.constants import (
     PROMPT_TEMPLATE,
     PROMPT_TEMPLATE_STAGED,
-    SUMMARIZATION_PROMPT_TEMPLATE,
     SNIPPET_PROMPT_TEMPLATE,
     DEFAULT_SYSTEM_PROMPT,
 )
@@ -14,7 +13,6 @@ class PromptConfig(BaseModel):
     """Configuration for basic log detective prompts."""
 
     prompt_template: str = PROMPT_TEMPLATE
-    summarization_prompt_template: str = SUMMARIZATION_PROMPT_TEMPLATE
     snippet_prompt_template: str = SNIPPET_PROMPT_TEMPLATE
     prompt_template_staged: str = PROMPT_TEMPLATE_STAGED
 
@@ -27,9 +25,6 @@ class PromptConfig(BaseModel):
         if data is None:
             return
         self.prompt_template = data.get("prompt_template", PROMPT_TEMPLATE)
-        self.summarization_prompt_template = data.get(
-            "summarization_prompt_template", SUMMARIZATION_PROMPT_TEMPLATE
-        )
         self.snippet_prompt_template = data.get(
             "snippet_prompt_template", SNIPPET_PROMPT_TEMPLATE
         )

{logdetective-1.4.0 → logdetective-1.5.0}/logdetective/prompts.yml

@@ -21,17 +21,6 @@ prompt_template: |
 
   Analysis:
 
-
-summarization_prompt_template: |
-  Does following log contain error or issue?
-
-  Log:
-
-  {}
-
-  Answer:
-
-
 snippet_prompt_template: |
   Analyse following RPM build log snippet. Describe contents accurately, without speculation or suggestions for resolution.
 

{logdetective-1.4.0 → logdetective-1.5.0}/logdetective/remote_log.py

@@ -64,6 +64,4 @@ class RemoteLog:
         try:
             return await self.get_url_content()
         except RuntimeError as ex:
-            raise HTTPBadRequest(
-                reason=f"We couldn't obtain the logs: {ex}"
-            ) from ex
+            raise HTTPBadRequest(reason=f"We couldn't obtain the logs: {ex}") from ex

{logdetective-1.4.0 → logdetective-1.5.0}/logdetective/server/config.py

@@ -52,11 +52,10 @@ def get_log(config: Config):
 
 
 def get_openai_api_client(ineference_config: InferenceConfig):
-    """Set up AsyncOpenAI client with default configuration.
-    """
+    """Set up AsyncOpenAI client with default configuration."""
     return AsyncOpenAI(
-        api_key=ineference_config.api_token,
-        base_url=ineference_config.url)
+        api_key=ineference_config.api_token, base_url=ineference_config.url
+    )
 
 
 SERVER_CONFIG_PATH = os.environ.get("LOGDETECTIVE_SERVER_CONF", None)

{logdetective-1.4.0 → logdetective-1.5.0}/logdetective/server/emoji.py

@@ -51,7 +51,9 @@ async def _handle_gitlab_operation(func: Callable, *args):
         else:
             LOG.exception(log_msg)
     except Exception as e:  # pylint: disable=broad-exception-caught
-        LOG.exception("Unexpected error during GitLab operation %s(%s): %s", func, args, e)
+        LOG.exception(
+            "Unexpected error during GitLab operation %s(%s): %s", func, args, e
+        )
 
 
 async def collect_emojis_in_comments(  # pylint: disable=too-many-locals

{logdetective-1.4.0 → logdetective-1.5.0}/logdetective/server/plot.py

@@ -340,7 +340,7 @@ def _plot_emoji_data(  # pylint: disable=too-many-locals
         )
         all_counts.extend(counts)
 
-    colors = [cm.viridis(i) for i in numpy.linspace(0, 1, len(reactions_values_dict))]    # pylint: disable=no-member
+    colors = [cm.viridis(i) for i in numpy.linspace(0, 1, len(reactions_values_dict))]  # pylint: disable=no-member
 
     first_emoji = True
     for i, (emoji, dict_counts) in enumerate(reactions_values_dict.items()):

{logdetective-1.4.0 → logdetective-1.5.0}/logdetective/utils.py

@@ -179,7 +179,7 @@ def format_snippets(snippets: list[str] | list[Tuple[int, str]]) -> str:
             summary += f"""
             Snippet No. {i}:
 
-            {s[1]}
+            {s}
             ================
             """
     return summary
@@ -198,8 +198,11 @@ def load_prompts(path: str | None) -> PromptConfig:
 
 
 def prompt_to_messages(
-        user_message: str, system_prompt: str | None = None,
-        system_role: str = "developer", user_role: str = "user") -> List[Dict[str, str]]:
+    user_message: str,
+    system_prompt: str | None = None,
+    system_role: str = "developer",
+    user_role: str = "user",
+) -> List[Dict[str, str]]:
     """Turn prompt into list of message dictionaries.
     If `system_role` and `user_role` are the same, only a single message is created,
     as concatenation of `user_message` and `system_prompt`. This is useful for models which
@@ -208,22 +211,15 @@ def prompt_to_messages(
 
     if system_role == user_role:
         messages = [
-            {
-                "role": system_role,
-                "content": f"{system_prompt}\n{user_message}"
-            }
+            {"role": system_role, "content": f"{system_prompt}\n{user_message}"}
         ]
     else:
-
         messages = [
-            {
-                "role": system_role,
-                "content": system_prompt
-            },
+            {"role": system_role, "content": system_prompt},
             {
                 "role": user_role,
                 "content": user_message,
-            }
+            },
         ]
 
     return messages

{logdetective-1.4.0 → logdetective-1.5.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "logdetective"
-version = "1.4.0"
+version = "1.5.0"
 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"
@@ -15,7 +15,7 @@ packages = [
     { include = "logdetective" }
 ]
 classifiers = [
-    "Development Status :: 4 - Beta",
+    "Development Status :: 5 - Production/Stable",
     "Environment :: Console",
     "Intended Audience :: Developers",
     "License :: OSI Approved :: Apache Software License",

logdetective-1.4.0/logdetective/extractors.py

@@ -1,105 +0,0 @@
-import os
-import logging
-from typing import Tuple
-
-import drain3
-from drain3.template_miner_config import TemplateMinerConfig
-from llama_cpp import Llama, LlamaGrammar
-
-from logdetective.constants import SUMMARIZATION_PROMPT_TEMPLATE
-from logdetective.utils import get_chunks
-
-LOG = logging.getLogger("logdetective")
-
-
-class LLMExtractor:
-    """
-    A class that extracts relevant information from logs using a language model.
-    """
-
-    def __init__(
-        self,
-        model: Llama,
-        n_lines: int = 2,
-        prompt: str = SUMMARIZATION_PROMPT_TEMPLATE,
-    ):
-        self.model = model
-        self.n_lines = n_lines
-        self.grammar = LlamaGrammar.from_string(
-            'root ::= ("Yes" | "No")', verbose=False
-        )
-        self.prompt = prompt
-
-    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
-
-    def rate_chunks(self, log: str) -> list[tuple]:
-        """Scan log by the model and store results.
-
-        :param log: log file content
-        """
-        results = []
-        log_lines = log.split("\n")
-
-        for i in range(0, len(log_lines), self.n_lines):
-            block = "\n".join(log_lines[i: i + self.n_lines])
-            prompt = self.prompt.format(log)
-            out = self.model(prompt, max_tokens=7, grammar=self.grammar)
-            out = f"{out['choices'][0]['text']}\n"
-            results.append((block, out))
-
-        return results
-
-    def create_extract(self, chunks: list[tuple], neighbors: bool = False) -> list[str]:
-        """Extract interesting chunks from the model processing."""
-        interesting = []
-        summary = []
-        # pylint: disable=consider-using-enumerate
-        for i in range(len(chunks)):
-            if chunks[i][1].startswith("Yes"):
-                interesting.append(i)
-                if neighbors:
-                    interesting.extend([max(i - 1, 0), min(i + 1, len(chunks) - 1)])
-
-        interesting = set(interesting)
-
-        for i in interesting:
-            summary.append(chunks[i][0])
-
-        return summary
-
-
-class DrainExtractor:
-    """A class that extracts information from logs using a template miner algorithm."""
-
-    def __init__(self, verbose: bool = False, context: bool = False, max_clusters=8):
-        config = TemplateMinerConfig()
-        config.load(f"{os.path.dirname(__file__)}/drain3.ini")
-        config.profiling_enabled = verbose
-        config.drain_max_clusters = max_clusters
-        self.miner = drain3.TemplateMiner(config=config)
-        self.verbose = verbose
-        self.context = context
-
-    def __call__(self, log: str) -> list[Tuple[int, str]]:
-        out = []
-        # First pass create clusters
-        for _, chunk in get_chunks(log):
-            processed_chunk = self.miner.add_log_message(chunk)
-            LOG.debug(processed_chunk)
-        # Sort found clusters by size, descending order
-        sorted_clusters = sorted(
-            self.miner.drain.clusters, key=lambda it: it.size, reverse=True
-        )
-        # Second pass, only matching lines with clusters,
-        # to recover original text
-        for chunk_start, chunk in get_chunks(log):
-            cluster = self.miner.match(chunk, "always")
-            if cluster in sorted_clusters:
-                out.append((chunk_start, chunk))
-                sorted_clusters.remove(cluster)
-        return out