logdetective 0.2.0__tar.gz

logdetective-0.2.0/LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

logdetective-0.2.0/PKG-INFO

@@ -0,0 +1,90 @@
+Metadata-Version: 2.1
+Name: logdetective
+Version: 0.2.0
+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: Environment :: Console
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Natural Language :: English
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Internet :: Log Analysis
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Software Development :: Debuggers
+Requires-Dist: drain3 (>=0.9.11,<0.10.0)
+Requires-Dist: llama-cpp-python (>=0.2.56,<0.3.0)
+Requires-Dist: progressbar2 (>=4.0.0,<5.0.0)
+Requires-Dist: requests (>=2.31.0,<3.0.0)
+Requires-Dist: tiktoken (>=0.6.0,<0.7.0)
+Project-URL: homepage, https://github.com/fedora-copr/logdetective
+Project-URL: issues, https://github.com/fedora-copr/logdetective/issues
+Description-Content-Type: text/markdown
+
+Log Detective
+=============
+
+A Python tool to analyze logs using a Language Model (LLM) and Drain template miner.
+
+Installation
+------------
+
+    # optionaly when you prefer system packages
+    dnf install python3-jsonpickle python3-tiktoken
+    # install all remaining packages
+    pip install .
+
+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.
+- `--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: 5): The number of lines per chunk for LLM analysis. This only makes sense when you are summarizing with LLM.
+
+Example usage:
+
+    ~/.local/bin/logdetective https://example.com/logs.txt
+
+
+Contributing
+------------
+
+Contributions are welcome! Please submit a pull request if you have any improvements or new features to add. Make sure your changes pass all existing tests before submitting.
+
+To develop logdetective, you should fork this repository, clone your fork, and install dependencies using pip:
+
+    git clone https://github.com/yourusername/logdetective.git
+    cd logdetective
+    pip install .
+
+Make changes to the code as needed and run pre-commit.
+
+Tests
+-----
+
+The [tox](https://github.com/tox-dev/tox) is used to manage tests. Please install `tox` package into your distribution and run:
+
+    tox
+
+This will create a virtual environment with dependencies and run all the tests. For more information follow the tox help.
+
+To run only a specific test execute this:
+
+    tox run -e style # to run flake8
+
+or
+
+    tox run -e lint # to run pylint
+
+License
+-------
+
+This project is licensed under the Apache-2.0 License - see the LICENSE file for details.
+

logdetective-0.2.0/README.md

@@ -0,0 +1,61 @@
+Log Detective
+=============
+
+A Python tool to analyze logs using a Language Model (LLM) and Drain template miner.
+
+Installation
+------------
+
+    # optionaly when you prefer system packages
+    dnf install python3-jsonpickle python3-tiktoken
+    # install all remaining packages
+    pip install .
+
+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.
+- `--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: 5): The number of lines per chunk for LLM analysis. This only makes sense when you are summarizing with LLM.
+
+Example usage:
+
+    ~/.local/bin/logdetective https://example.com/logs.txt
+
+
+Contributing
+------------
+
+Contributions are welcome! Please submit a pull request if you have any improvements or new features to add. Make sure your changes pass all existing tests before submitting.
+
+To develop logdetective, you should fork this repository, clone your fork, and install dependencies using pip:
+
+    git clone https://github.com/yourusername/logdetective.git
+    cd logdetective
+    pip install .
+
+Make changes to the code as needed and run pre-commit.
+
+Tests
+-----
+
+The [tox](https://github.com/tox-dev/tox) is used to manage tests. Please install `tox` package into your distribution and run:
+
+    tox
+
+This will create a virtual environment with dependencies and run all the tests. For more information follow the tox help.
+
+To run only a specific test execute this:
+
+    tox run -e style # to run flake8
+
+or
+
+    tox run -e lint # to run pylint
+
+License
+-------
+
+This project is licensed under the Apache-2.0 License - see the LICENSE file for details.

logdetective-0.2.0/logdetective/drain3.ini

@@ -0,0 +1,32 @@
+[SNAPSHOT]
+snapshot_interval_minutes = 10
+compress_state = True
+
+[MASKING]
+masking = [
+          {"regex_pattern":"((?<=[^A-Za-z0-9])|^)(([0-9a-f]{2,}:){3,}([0-9a-f]{2,}))((?=[^A-Za-z0-9])|$)", "mask_with": "ID"},
+          {"regex_pattern":"((?<=[^A-Za-z0-9])|^)(\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}\\.\\d{1,3})((?=[^A-Za-z0-9])|$)", "mask_with": "IP"},
+          {"regex_pattern":"((?<=[^A-Za-z0-9])|^)([0-9a-f]{6,} ?){3,}((?=[^A-Za-z0-9])|$)", "mask_with": "SEQ"},
+          {"regex_pattern":"((?<=[^A-Za-z0-9])|^)([0-9A-F]{4} ?){4,}((?=[^A-Za-z0-9])|$)", "mask_with": "SEQ"},
+          {"regex_pattern":"((?<=[^A-Za-z0-9])|^)(0x[a-f0-9A-F]+)((?=[^A-Za-z0-9])|$)", "mask_with": "HEX"},
+          {"regex_pattern":"((?<=[^A-Za-z0-9])|^)([\\-\\+]?\\d+)((?=[^A-Za-z0-9])|$)", "mask_with": "NUM"},
+          {"regex_pattern":"(?<=executed cmd )(\".+?\")", "mask_with": "CMD"},
+          {"regex_pattern":"/usr/bin/systemd-nspawn.*", "mask_with":"CMD"},
+          {"regex_pattern":"INFO: .*", "mask_with": "INFO"}
+          ]
+mask_prefix = <:
+mask_suffix = :>
+
+[DRAIN]
+# engine is Optional parameter. Engine will be "Drain" if the engine argument is not specified.
+# engine has two options: 'Drain' and 'JaccardDrain'.
+# engine = Drain
+sim_th = 0.4
+depth = 4
+max_children = 10000
+max_clusters = 16
+extra_delimiters = ["_"]
+
+[PROFILING]
+enabled = False
+report_sec = 30

logdetective-0.2.0/logdetective/logdetective.py

@@ -0,0 +1,275 @@
+import argparse
+import logging
+import os
+import sys
+from urllib.request import urlretrieve
+
+import drain3
+import numpy as np
+import progressbar
+import requests
+from drain3.template_miner_config import TemplateMinerConfig
+from llama_cpp import Llama, LlamaGrammar
+
+# pylint: disable=line-too-long
+DEFAULT_ADVISOR = "https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GGUF/resolve/main/mistral-7b-instruct-v0.2.Q4_K_S.gguf?download=true"
+
+# pylint: disable=line-too-long
+DEFAULT_LLM_RATER = "https://huggingface.co/TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF/resolve/main/tinyllama-1.1b-chat-v1.0.Q4_K_S.gguf?download=true"
+
+PROMPT_TEMPLATE = """
+Given following log snippets, and nothing else, explain what failure, if any occured during build of this package.
+Ignore strings wrapped in <: :>, such as <:*:>.
+
+{}
+
+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.
+
+Analysis:
+
+"""
+
+SUMMARIZE_PROPT_TEMPLATE = """
+Does following log contain error or issue?
+
+Log:
+
+{}
+
+Answer:
+
+"""
+
+CACHE_LOC = "~/.cache/logdetective/"
+
+LOG = logging.getLogger("logdetective")
+
+
+class MyProgressBar():
+    """Show progress when downloading model."""
+    def __init__(self):
+        self.pbar = None
+
+    def __call__(self, block_num, block_size, total_size):
+        if not self.pbar:
+            self.pbar = progressbar.ProgressBar(maxval=total_size)
+            self.pbar.start()
+
+        downloaded = block_num * block_size
+        if downloaded < total_size:
+            self.pbar.update(downloaded)
+        else:
+            self.pbar.finish()
+
+
+def chunk_continues(text: str, index: int) -> bool:
+    """Set of heuristics for determining whether or not
+    does the current chunk of log text continue on next line.
+    """
+    conditionals = [
+        lambda i, string: string[i + 1].isspace(),
+        lambda i, string: string[i - 1] == "\\"
+    ]
+
+    for c in conditionals:
+        y = c(index, text)
+        if y:
+            return True
+
+    return False
+
+
+def get_chunks(text: str):
+    """Split log into chunks according to heuristic
+    based on whitespace and backslash presence.
+    """
+    text_len = len(text)
+    i = 0
+    chunk = ""
+    while i < text_len:
+        chunk += text[i]
+        if text[i] == '\n':
+            if i + 1 < text_len and chunk_continues(text, i):
+                i += 1
+                continue
+            yield chunk
+            chunk = ""
+        i += 1
+
+
+class LLMExtractor:
+    """
+    A class that extracts relevant information from logs using a language model.
+    """
+    def __init__(self, model_path: str, verbose: bool):
+        self.model = Llama(
+            model_path=model_path,
+            n_ctx=0,
+            verbose=verbose)
+        self.grammar = LlamaGrammar.from_string(
+            "root ::= (\"Yes\" | \"No\")", verbose=False)
+
+    def __call__(self, log: str, n_lines: int = 2, neighbors: bool = False) -> str:
+        chunks = self.rate_chunks(log, n_lines)
+        out = self.create_extract(chunks, neighbors)
+        return out
+
+    def rate_chunks(self, log: str, n_lines: int = 2) -> list[tuple]:
+        """Scan log by the model and store results.
+
+        :param log: log file content
+        :param n_lines: How many lines should the model take into consideration
+        """
+        results = []
+        log_lines = log.split("\n")
+
+        for i in range(0, len(log_lines), n_lines):
+            block = '\n'.join(log_lines[i:i + n_lines])
+            prompt = SUMMARIZE_PROPT_TEMPLATE.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) -> 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 = np.unique(interesting)
+
+        for i in interesting:
+            summary += chunks[i][0] + "\n"
+
+        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):
+        config = TemplateMinerConfig()
+        config.load(f"{os.path.dirname(__file__)}/drain3.ini")
+        config.profiling_enabled = verbose
+        self.miner = drain3.TemplateMiner(config=config)
+        self.verbose = verbose
+        self.context = context
+
+    def __call__(self, log: str) -> str:
+        out = ""
+        for chunk in get_chunks(log):
+            procesed_line = self.miner.add_log_message(chunk)
+            LOG.debug(procesed_line)
+        sorted_clusters = sorted(self.miner.drain.clusters, key=lambda it: it.size, reverse=True)
+        for chunk in get_chunks(log):
+            cluster = self.miner.match(chunk, "always")
+            if cluster in sorted_clusters:
+                out += f"{chunk}\n"
+                sorted_clusters.remove(cluster)
+        return out
+
+
+def download_model(url: str, verbose: bool = False) -> str:
+    """ Downloads a language model from a given URL and saves it to the cache directory.
+
+    Args:
+        url (str): The URL of the language model to be downloaded.
+
+    Returns:
+        str: The local file path of the downloaded language model.
+    """
+    path = os.path.join(
+        os.path.expanduser(CACHE_LOC), url.split('/')[-1])
+
+    LOG.info("Downloading model from %s to %s", url, path)
+    if not os.path.exists(path):
+        if verbose:
+            path, _status = urlretrieve(url, path, MyProgressBar())
+        else:
+            path, _status = urlretrieve(url, path)
+
+    return path
+
+
+def process_log(log: str, model: Llama) -> str:
+    """
+    Processes a given log using the provided language model and returns its summary.
+
+    Args:
+        log (str): The input log to be processed.
+        model (Llama): The language model used for processing the log.
+
+    Returns:
+        str: The summary of the given log generated by the language model.
+    """
+    return model(PROMPT_TEMPLATE.format(log), max_tokens=0)["choices"][0]["text"]
+
+
+def main():
+    """Main execution function."""
+    parser = argparse.ArgumentParser("logdetective")
+    parser.add_argument("url", type=str, default="")
+    parser.add_argument("-M", "--model", type=str, default=DEFAULT_ADVISOR)
+    parser.add_argument("-S", "--summarizer", type=str, default="drain")
+    parser.add_argument("-N", "--n_lines", type=int, default=5)
+    parser.add_argument("-v", "--verbose", action='count', default=0)
+    parser.add_argument("-q", "--quiet", action='store_true')
+
+    args = parser.parse_args()
+
+    if args.verbose and args.quiet:
+        sys.stderr.write("Error: --quiet and --verbose is mutually exclusive.\n")
+        sys.exit(2)
+    log_level = logging.INFO
+    if args.verbose >= 1:
+        log_level = logging.DEBUG
+    if args.quiet:
+        log_level = 0
+    logging.basicConfig(stream=sys.stdout)
+    LOG.setLevel(log_level)
+
+    if not os.path.exists(CACHE_LOC):
+        os.makedirs(os.path.expanduser(CACHE_LOC), exist_ok=True)
+
+    if not os.path.isfile(args.model):
+        model_pth = download_model(args.model, not args.quiet)
+    else:
+        model_pth = args.model
+
+    if args.summarizer == "drain":
+        extractor = DrainExtractor(args.verbose > 1, context=True)
+    elif os.path.isfile(args.summarizer):
+        extractor = LLMExtractor(args.summarizer, args.verbose > 1)
+    else:
+        summarizer_pth = download_model(args.summarizer, not args.quiet)
+        extractor = LLMExtractor(summarizer_pth, args.verbose > 1)
+
+    LOG.info("Getting summary")
+    model = Llama(
+        model_path=model_pth,
+        n_ctx=0,
+        verbose=args.verbose > 2)
+
+    log = requests.get(args.url, timeout=60).text
+    log_summary = extractor(log)
+
+    ratio = len(log_summary.split('\n')) / len(log.split('\n'))
+    LOG.debug("Log summary: \n %s", log_summary)
+    LOG.info("Compression ratio: %s", ratio)
+
+    LOG.info("Analyzing the text")
+    print(f"Explanation: \n{process_log(log_summary, model)}")
+
+
+if __name__ == "__main__":
+    main()

logdetective-0.2.0/pyproject.toml

@@ -0,0 +1,46 @@
+[tool.poetry]
+name = "logdetective"
+version = "0.2.0"
+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"
+readme = "README.md"
+include = ["logdetective/drain3.ini"]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Environment :: Console",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: Apache Software License",
+    "Natural Language :: English",
+    "Programming Language :: Python :: 3",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+    "Topic :: Software Development :: Debuggers",
+    "Topic :: Internet :: Log Analysis"
+]
+
+[tool.poetry.urls]
+homepage = "https://github.com/fedora-copr/logdetective"
+issues = "https://github.com/fedora-copr/logdetective/issues"
+
+[tool.poetry.dependencies]
+python = "^3.11"
+requests = "^2.31.0"
+llama-cpp-python = "^0.2.56"
+tiktoken = "^0.6.0"
+drain3 = "^0.9.11"
+progressbar2 = "^4.0.0"
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"
+
+[tool.poetry.scripts]
+logdetective = 'logdetective.logdetective:main'
+
+[tool.pylint]
+disable = [
+    "inconsistent-return-statements",
+    "missing-module-docstring",
+    "too-few-public-methods",
+    "unspecified-encoding",
+]