aurelian 0.1.0__py3-none-any.whl

aurelian/utils/pytest_report_to_markdown.py

@@ -0,0 +1,67 @@
+import json
+from pathlib import Path
+from collections import defaultdict
+import re
+from typing import Iterator
+
+import click
+
+
+def report_md(log_path: str) -> str:
+    return '\n'.join(list(report_md_iter(log_path)))
+
+def report_md_iter(log_path: str) -> Iterator[str]:
+    """
+    Parse pytest-reportlog output into structured format.
+
+    Args:
+        log_path:
+
+    Returns:
+
+    """
+
+    with open(log_path) as f:
+        outcome = None
+        duration = None
+        for line in f:
+            entry = json.loads(line)
+
+            # Only process TestReport entries
+            if entry.get('$report_type') != 'TestReport':
+                continue
+
+            nodeid = entry['nodeid']
+            outcome = entry.get('outcome')
+            duration = entry.get('duration')
+
+            if not outcome:
+                continue
+
+            yield f"## {nodeid}\n"
+
+
+
+            for p in entry.get('user_properties', []):
+                k = p[0]
+                v = p[1]
+
+                yield f"### {k}\n\n"
+                yield f"{v}\n"
+
+        yield "## Stats\n\n"
+        if outcome:
+            yield f"* Outcome: {outcome}\n"
+        if duration:
+            yield f"* Duration: {duration}\n"
+
+
+
+@click.command()
+@click.argument("log_path", type=click.Path(exists=True))
+def main(log_path: str):
+    markdown = report_md(log_path)
+    print(markdown)
+
+if __name__ == "__main__":
+    main()

aurelian/utils/robot_ontology_utils.py

@@ -0,0 +1,112 @@
+from typing import Dict, Optional, List, Tuple
+
+from aurelian.dependencies.workdir import WorkDir
+
+MERGED_IMPORT_PATH = "_imports_.owl"
+
+def run(cmd: str):
+    """
+    Run a command, raising an error if the command fails,
+    returning stdout
+
+    Args:
+        cmd:
+
+    Returns:
+
+    """
+    import subprocess
+    result = subprocess.run(cmd, shell=True, capture_output=True)
+    if result.returncode != 0:
+        stdout = result.stdout.decode()
+        stderr = result.stderr.decode()
+        raise Exception(f"Command failed: {cmd}\nError: {stderr}\nOutput: {stdout}")
+    return result.stdout.decode()
+
+def parse_component_name(name: str) -> Tuple[str, Optional[str]]:
+    """
+    Parse file name
+
+    Example:
+
+        >>> parse_component_name("foo.owl")
+        ('foo', 'owl')
+        >>> parse_component_name("foo")
+        ('foo', None)
+
+
+    Args:
+        name:
+
+    Returns:
+
+    """
+    parts = name.split(".")
+    if len(parts) == 1:
+        return name, None
+    return ".".join(parts[:-1]), parts[-1]
+
+
+def depends_on_csv(workdir: WorkDir, name: str) -> Optional[str]:
+    base, suffix = parse_component_name(name)
+    if not suffix:
+        suffix = "owl"
+        base = name
+    if suffix == "owl":
+        for d_suffix in ("tsv", "csv"):
+            d_name = f"{base}.{d_suffix}"
+            if workdir.check_file_exists(d_name):
+                return d_name
+    return None
+
+def run_robot_template_command(workdir: WorkDir, template_path: str, prefix_map: Dict[str, str], output_path: Optional[str] = None, import_ontologies: Optional[List[str]] = None) -> str:
+    """
+    Generate a robot template command
+
+    Args:
+        workdir:
+        template_path:
+        prefix_map:
+        output_path:
+        import_ontologies:
+
+    Returns:
+
+    """
+    if output_path is None:
+        output_path = template_path.replace(".csv", ".owl")
+    prefixes = " ".join([f"--prefix '{k}: {v}'" for k, v in prefix_map.items()])
+    if not import_ontologies:
+        import_ontologies = []
+    import_owls = []
+    for import_ontology in import_ontologies:
+        local_name, suffix = parse_component_name(import_ontology)
+        if suffix == "owl":
+            import_ontology_owl = import_ontology
+            if not workdir.check_file_exists(import_ontology_owl):
+                depends_on = depends_on_csv(workdir, import_ontology_owl)
+                if not workdir.check_file_exists(depends_on):
+                    raise Exception(f"Cannot make owl file {import_ontology_owl} as no {depends_on}")
+                run_robot_template_command(
+                    workdir,
+                    depends_on,
+                    prefix_map=prefix_map,
+                    output_path=import_ontology_owl,
+                )
+        else:
+            if suffix:
+                import_ontology_owl = import_ontology.replace(suffix, "owl")
+            else:
+                import_ontology_owl = import_ontology + ".owl"
+            run_robot_template_command(workdir, import_ontology, prefix_map=prefix_map, output_path=import_ontology_owl)
+        import_owls.append(import_ontology_owl)
+    if import_owls:
+        input_opts = [f"--input {owl}" for owl in import_owls]
+        cmd = f"cd {workdir.location} && robot merge {' '.join(input_opts)} --output {MERGED_IMPORT_PATH}"
+        run(cmd)
+        import_ontology_opt = f"--input {MERGED_IMPORT_PATH}"
+    else:
+        import_ontology_opt = ""
+    cmd = f"cd {workdir.location} && robot template {import_ontology_opt} --template {template_path} {prefixes} reason --output {output_path}"
+    run(cmd)
+    return output_path

aurelian/utils/search_utils.py

@@ -0,0 +1,95 @@
+import re
+
+import requests
+from duckduckgo_search import DDGS
+from markdownify import markdownify
+
+from aurelian.utils.pubmed_utils import doi_to_pmid, extract_doi_from_url, get_pmcid_text, get_pmid_text
+
+MAX_LENGTH_TRUNCATE_CONTENT = 20000
+
+
+def web_search(query: str, max_results=10, **kwargs) -> str:
+    """Search the web using DuckDuckGo
+
+    Example:
+        >>> result = web_search("Winner of 2024 nobel prize in chemistry")
+        >>> assert "Baker" in result
+
+
+    Args:
+        query:
+        max_results:
+        **kwargs:
+
+    Returns:
+
+    """
+    ddgs = DDGS(**kwargs)
+    results = ddgs.text(query, max_results=max_results)
+    if len(results) == 0:
+        return "No results found! Try a less restrictive/shorter query."
+    postprocessed_results = [f"[{result['title']}]({result['href']})\n{result['body']}" for result in results]
+    return "## Search Results\n\n" + "\n\n".join(postprocessed_results)
+
+
+def retrieve_web_page(url: str) -> str:
+    """Retrieve the text of a web page.
+
+    Example:
+        >>> url = "https://en.wikipedia.org/wiki/COVID-19"
+        >>> text = retrieve_web_page(url)
+        >>> assert "COVID-19" in text
+
+    PMCs are redirected:
+
+        >>> url = "https://pmc.ncbi.nlm.nih.gov/articles/PMC5048378/"
+        >>> text = retrieve_web_page(url)
+        >>> assert "integrated stress response (ISR)" in text
+
+    URLs with DOIs:
+
+        >>> url = "https://microbiomejournal.biomedcentral.com/articles/10.1186/s40168-020-00889-8"
+        >>> text = retrieve_web_page(url)
+        >>> assert "photosynthesis" in text
+
+    Args:
+        url: URL of the web page
+
+    Returns:
+        str: The text of the web page
+
+    """
+    if url.startswith("https://pmc.ncbi.nlm.nih.gov/articles/PMC"):
+        url = url.strip("/")
+        pmc_id = url.split("/")[-1]
+        # print(f"REWIRING URL: Fetching PMC ID: {pmc_id}")
+        return get_pmcid_text(pmc_id)
+
+    doi = extract_doi_from_url(url)
+    if doi:
+        # print(f"REWIRING URL: Fetching DOI: {doi}")
+        pmid = doi_to_pmid(doi)
+        return get_pmid_text(pmid)
+
+    response = requests.get(url, timeout=20)
+    response.raise_for_status()  # Raise an exception for bad status codes
+
+    # Convert the HTML content to Markdown
+    markdown_content = markdownify(response.text).strip()
+
+    # Remove multiple line breaks
+    markdown_content = re.sub(r"\n{3,}", "\n\n", markdown_content)
+
+    return truncate_content(markdown_content, 10000)
+
+
+def truncate_content(content: str, max_length: int = MAX_LENGTH_TRUNCATE_CONTENT) -> str:
+    if len(content) <= max_length:
+        return content
+    else:
+        return (
+            content[: max_length // 2]
+            + f"\n..._This content has been truncated to stay below {max_length} characters_...\n"
+            + content[-max_length // 2 :]
+        )

aurelian-0.1.0.dist-info/LICENSE

@@ -0,0 +1,22 @@
+
+The MIT License (MIT)
+
+Copyright (c) 2025 Monarch Initiative
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.

aurelian-0.1.0.dist-info/METADATA

@@ -0,0 +1,109 @@
+Metadata-Version: 2.3
+Name: aurelian
+Version: 0.1.0
+Summary: aurelian
+License: MIT
+Author: Author 1
+Author-email: author@org.org
+Requires-Python: >=3.11,<4.0
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Provides-Extra: bioservices
+Provides-Extra: chem
+Provides-Extra: gocam
+Provides-Extra: gradio
+Provides-Extra: linkml
+Provides-Extra: pdfminer
+Provides-Extra: pypaperbot
+Provides-Extra: rdkit
+Requires-Dist: bioservices (>=1.12.0) ; extra == "bioservices"
+Requires-Dist: bs4 (>=0.0.2)
+Requires-Dist: cairosvg (>=2.7.1,<3.0.0)
+Requires-Dist: click
+Requires-Dist: duckduckgo-search (>=7.3.2)
+Requires-Dist: gocam ; extra == "gocam"
+Requires-Dist: gradio (>=5.23.3,<6.0.0) ; extra == "gradio"
+Requires-Dist: importlib-metadata (>=8.2.0)
+Requires-Dist: linkml ; extra == "linkml"
+Requires-Dist: linkml-store[llm,mongodb] (>=0.2.4)
+Requires-Dist: logfire (>=3.5.3)
+Requires-Dist: markdownify (>=0.14.1)
+Requires-Dist: markitdown (>=0.1.1)
+Requires-Dist: mcp[cli] (>=1.3.0,<2.0.0)
+Requires-Dist: oaklib (>=0.6.19)
+Requires-Dist: onnxruntime (<=1.19.0)
+Requires-Dist: paper-qa (>=5.20.0,<6.0.0)
+Requires-Dist: pdfminer-six ; extra == "pdfminer"
+Requires-Dist: pydantic-ai (>=0.2.0)
+Requires-Dist: pypaperbot (>=1.4.1) ; extra == "pypaperbot"
+Requires-Dist: pytest-asyncio (>=0.25.3,<0.26.0)
+Requires-Dist: rdkit ; extra == "rdkit" or extra == "chem"
+Requires-Dist: tabulate (>=0.9.0)
+Requires-Dist: undetected-chromedriver (>=3.5.5)
+Requires-Dist: wikipedia (>=1.4.0)
+Description-Content-Type: text/markdown
+
+[![DOI](https://zenodo.org/badge/932483388.svg)](https://doi.org/10.5281/zenodo.15299996)
+
+# Aurelian: Agentic Universal Research Engine for Literature, Integration, Annotation, and Navigation
+
+| [Documentation](https://monarch-initiative.github.io/aurelian) |
+
+```
+aurelian --help
+```
+
+Most commands will start up a different AI agent.
+
+## Examples of use
+
+### TALISMAN
+
+gene set enrichment
+
+### Aria
+
+checking papers against checklists
+
+### GO-CAM agent
+
+This agent is for exploring, chatting with, and reviewing GO-CAMs
+
+Docs: [gocam_agent](https://monarch-initiative.github.io/aurelian/agents/gocam_agent/)
+
+It can be used to generate reviews according to guidelines for GO-CAMs:
+
+* [GO-CAM Reviews](https://cmungall.github.io/go-cam-reviews/)
+
+It can also generate SVGs, demonstrating innate knowledge of both the visual grammar of pathway diagrams and the semantics of the underlying biology.
+
+
+<img alt="img" src="https://cmungall.github.io/go-cam-reviews/figures/FIG-646ff70100005137-IL33_signaling_pathway__Human_.svg" />
+
+### GO-Ann agent
+
+This agent is for exploring, chatting with, and reviewing standard annotations
+
+
+Docs: [go_ann_agent](https://monarch-initiative.github.io/aurelian/agents/go_ann_agent/)
+
+Example review using TF guidelines:
+
+https://github.com/geneontology/go-annotation/issues/5743
+
+## Troubleshooting
+
+### Installing linkml-store
+
+Some agents require linkml-store pre-indexed. E.g. a mongodb with gocams for cam agent.
+Consult the [linkml-store documentation](https://linkml.io/linkml-store/) for more information.
+
+### Semantic search over ontologies
+
+If an agent requires ontology search it will use the semsql/OAK sqlite database.
+The first time querying it will use linkml-store to create an LLM index. Requires OAI key.
+This may be slow first iteration. Will be cached until your pystow cache regenerates.
+