aiagents4pharma 1.46.3__tar.gz → 1.46.4__tar.gz

{aiagents4pharma-1.46.3 → aiagents4pharma-1.46.4}/.github/dependabot.yml

@@ -43,6 +43,26 @@ updates:
       - "github-actions"
     open-pull-requests-limit: 5
 
+  # JavaScript/TypeScript (npm)
+  - package-ecosystem: "npm"
+    directory: "/"
+    schedule:
+      interval: "monthly"
+      time: "09:00"
+    target-branch: "main"
+    assignees:
+      - "ansh-info"
+    commit-message:
+      prefix: "deps"
+      include: "scope"
+    labels:
+      - "dependencies"
+      - "npm"
+      - "security"
+    open-pull-requests-limit: 10
+    # Update both package.json and lockfile as needed
+    versioning-strategy: "increase"
+
   # Disabled for now: repo has no Dockerfiles or Kubernetes manifests
   # in the root directory, causing Dependabot's Docker updater to fail
   # with "No Dockerfiles nor Kubernetes YAML found". Re-enable when

{aiagents4pharma-1.46.3 → aiagents4pharma-1.46.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: aiagents4pharma
-Version: 1.46.3
+Version: 1.46.4
 Summary: AI Agents for drug discovery, drug development, and other pharmaceutical R&D.
 License-File: LICENSE
 Classifier: License :: OSI Approved :: MIT License

{aiagents4pharma-1.46.3 → aiagents4pharma-1.46.4}/aiagents4pharma/talk2knowledgegraphs/configs/utils/enrichments/ols_terms/default.yaml

@@ -1,3 +1,3 @@
 _target_: talk2knowledgegraphs.utils.ols_terms
-base_url: https://www.ebi.ac.uk/ols4/api/terms/
+base_url: https://www.ebi.ac.uk/ols/api/terms
 timeout: 10

{aiagents4pharma-1.46.3 → aiagents4pharma-1.46.4}/aiagents4pharma/talk2knowledgegraphs/datasets/biobridge_primekg.py

@@ -4,8 +4,8 @@ Class for loading BioBridgePrimeKG dataset.
 
 import json
 import os
-import pickle
 
+import joblib
 import numpy as np
 import pandas as pd
 import requests
@@ -161,8 +161,7 @@ class BioBridgePrimeKG(Dataset):
         processed_file_path = os.path.join(self.local_dir, "embeddings", "embedding_dict.pkl")
         if os.path.exists(processed_file_path):
             # Load the embeddings from the local directory
-            with open(processed_file_path, "rb") as f:
-                emb_dict_all = pickle.load(f)
+            emb_dict_all = joblib.load(processed_file_path)
         else:
             # Download the embeddings from the BioBridge repo and further process them
             # List of embedding source files
@@ -183,16 +182,14 @@ class BioBridgePrimeKG(Dataset):
             # Unified embeddings
             emb_dict_all = {}
             for file in file_list:
-                with open(os.path.join(self.local_dir, "embeddings", file), "rb") as f:
-                    emb = pickle.load(f)
+                emb = joblib.load(os.path.join(self.local_dir, "embeddings", file))
                 emb_ar = emb["embedding"]
                 if not isinstance(emb_ar, list):
                     emb_ar = emb_ar.tolist()
                 emb_dict_all.update(dict(zip(emb["node_index"], emb_ar, strict=False)))
 
-            # Store embeddings
-            with open(processed_file_path, "wb") as f:
-                pickle.dump(emb_dict_all, f)
+            # Store embeddings using secure joblib
+            joblib.dump(emb_dict_all, processed_file_path)
 
         return emb_dict_all
 

{aiagents4pharma-1.46.3 → aiagents4pharma-1.46.4}/aiagents4pharma/talk2knowledgegraphs/datasets/starkqa_primekg.py

@@ -3,10 +3,10 @@ Class for loading StarkQAPrimeKG dataset.
 """
 
 import os
-import pickle
 import shutil
 
 import gdown
+import joblib
 import numpy as np
 import pandas as pd
 import torch
@@ -110,8 +110,9 @@ class StarkQAPrimeKG(Dataset):
             )
 
         # Load the node info of PrimeKG preprocessed for StarkQA
-        with open(os.path.join(self.local_dir, "skb/prime/processed/node_info.pkl"), "rb") as f:
-            starkqa_node_info = pickle.load(f)
+        starkqa_node_info = joblib.load(
+            os.path.join(self.local_dir, "skb/prime/processed/node_info.pkl")
+        )
 
         return starkqa, starkqa_split_idx, starkqa_node_info
 

{aiagents4pharma-1.46.3 → aiagents4pharma-1.46.4}/aiagents4pharma/talk2knowledgegraphs/milvus_data_dump.py

@@ -107,8 +107,8 @@ class SystemDetector:
                         sys.exit(1)
                 else:
                     logger.info("Successfully installed: %s", package_cmd.split()[-1])
-            except subprocess.CalledProcessError as e:
-                logger.error("Failed to install %s: %s", package_cmd, e.stderr)
+            except subprocess.CalledProcessError:
+                logger.error("Failed to install package: %s", package_cmd.split()[-1])
                 if "cudf" in package_cmd:
                     logger.warning("GPU package installation failed, falling back to CPU mode")
                     self.use_gpu = False
@@ -198,12 +198,12 @@ class DynamicDataLoader:
                 self.cudf = cudf
                 self.cp = cp
                 logger.info("Successfully imported GPU libraries (cudf, cupy)")
-            except ImportError as e:
+            except ImportError:
                 logger.error(
                     "[DATA LOADER] cudf or cupy not found. "
                     "Please ensure they are installed correctly."
                 )
-                logger.error("Import error: %s", str(e))
+                logger.error("Import error occurred - GPU libraries not available")
                 # Match original script's exit behavior for critical GPU import failure
                 if not os.getenv("FORCE_CPU", "false").lower() == "true":
                     logger.error(
@@ -795,11 +795,9 @@ class DynamicDataLoader:
                 collection = self.pymilvus_modules["Collection"](name=coll)
                 logger.info("  %s: %d entities", coll, collection.num_entities)
 
-        except Exception as e:
-            logger.error("Error during data loading: %s", str(e))
-            import traceback
-
-            logger.error("Full traceback: %s", traceback.format_exc())
+        except Exception:
+            logger.error("Error occurred during data loading")
+            logger.debug("Detailed error information available in debug mode")
             raise
 
 
@@ -832,8 +830,10 @@ def main():
     logger.info("Configuration:")
     for key, value in config.items():
         # Don't log sensitive information
-        if "password" in key.lower():
-            logger.info("  %s: %s", key, "*" * len(str(value)))
+        if any(
+            sensitive in key.lower() for sensitive in ["password", "user", "token", "key", "secret"]
+        ):
+            logger.info("  %s: %s", key, "*" * min(8, len(str(value))))
         else:
             logger.info("  %s: %s", key, value)
 
@@ -866,11 +866,9 @@ def main():
     except KeyboardInterrupt:
         logger.info("Data loading interrupted by user")
         sys.exit(1)
-    except Exception as e:
-        logger.error("Fatal error during data loading: %s", str(e))
-        import traceback
-
-        logger.error("Full traceback: %s", traceback.format_exc())
+    except Exception:
+        logger.error("Fatal error occurred during data loading")
+        logger.debug("Detailed error information available in debug mode")
         sys.exit(1)
 
 

{aiagents4pharma-1.46.3 → aiagents4pharma-1.46.4}/aiagents4pharma/talk2knowledgegraphs/tests/test_utils_enrichments_ols.py

@@ -48,7 +48,7 @@ def test_enrich_documents(enrich_obj):
     assert UBERON_DESC in descriptions[2]
     assert HP_DESC in descriptions[3]
     assert MONDO_DESC in descriptions[4]
-    assert descriptions[5] is None
+    assert descriptions[5] == ""
 
 
 def test_enrich_documents_with_rag(enrich_obj):
@@ -67,4 +67,4 @@ def test_enrich_documents_with_rag(enrich_obj):
     assert UBERON_DESC in descriptions[2]
     assert HP_DESC in descriptions[3]
     assert MONDO_DESC in descriptions[4]
-    assert descriptions[5] is None
+    assert descriptions[5] == ""

{aiagents4pharma-1.46.3 → aiagents4pharma-1.46.4}/aiagents4pharma/talk2knowledgegraphs/tools/multimodal_subgraph_extraction.py

@@ -3,10 +3,10 @@ Tool for performing multimodal subgraph extraction.
 """
 
 import logging
-import pickle
 from typing import Annotated
 
 import hydra
+import joblib
 import networkx as nx
 import numpy as np
 import pandas as pd
@@ -319,11 +319,9 @@ class MultimodalSubgraphExtractionTool(BaseTool):
         initial_graph["source"] = state["dic_source_graph"][-1]  # The last source graph as of now
         # logger.log(logging.INFO, "Source graph: %s", source_graph)
 
-        # Load the knowledge graph
-        with open(initial_graph["source"]["kg_pyg_path"], "rb") as f:
-            initial_graph["pyg"] = pickle.load(f)
-        with open(initial_graph["source"]["kg_text_path"], "rb") as f:
-            initial_graph["text"] = pickle.load(f)
+        # Load the knowledge graph using secure joblib
+        initial_graph["pyg"] = joblib.load(initial_graph["source"]["kg_pyg_path"])
+        initial_graph["text"] = joblib.load(initial_graph["source"]["kg_text_path"])
 
         # Prepare the query embeddings and modalities
         query_df = self._prepare_query_modalities(

{aiagents4pharma-1.46.3 → aiagents4pharma-1.46.4}/aiagents4pharma/talk2knowledgegraphs/tools/subgraph_extraction.py

@@ -3,10 +3,10 @@ Tool for performing subgraph extraction.
 """
 
 import logging
-import pickle
 from typing import Annotated
 
 import hydra
+import joblib
 import networkx as nx
 import numpy as np
 import pandas as pd
@@ -220,11 +220,9 @@ class SubgraphExtractionTool(BaseTool):
         initial_graph["source"] = state["dic_source_graph"][-1]  # The last source graph as of now
         # logger.log(logging.INFO, "Source graph: %s", source_graph)
 
-        # Load the knowledge graph
-        with open(initial_graph["source"]["kg_pyg_path"], "rb") as f:
-            initial_graph["pyg"] = pickle.load(f)
-        with open(initial_graph["source"]["kg_text_path"], "rb") as f:
-            initial_graph["text"] = pickle.load(f)
+        # Load the knowledge graph using secure joblib
+        initial_graph["pyg"] = joblib.load(initial_graph["source"]["kg_pyg_path"])
+        initial_graph["text"] = joblib.load(initial_graph["source"]["kg_text_path"])
 
         # Prepare prompt construction along with a list of endotypes
         if len(state["uploaded_files"]) != 0 and "endotype" in [

{aiagents4pharma-1.46.3 → aiagents4pharma-1.46.4}/aiagents4pharma/talk2knowledgegraphs/utils/enrichments/ols_terms.py

@@ -54,7 +54,7 @@ class EnrichmentWithOLS(Enrichments):
             response_body = json.loads(r.text)
             # if the response body is empty
             if "_embedded" not in response_body:
-                descriptions.append(None)
+                descriptions.append("")
                 continue
             # Add the description to the list
             description = []
@@ -65,13 +65,15 @@ class EnrichmentWithOLS(Enrichments):
                 description += term.get("synonyms", [])
                 # Add the label to the description
                 # Label is not provided as list, so we need to convert it to a list
-                description += [term.get("label", [])]
+                label = term.get("label", "")
+                if label:
+                    description += [label]
             # Make unique the description
             description = list(set(description))
             # Join the description with new line
             description = "\n".join(description)
-            # Add the description to the list
-            descriptions.append(description)
+            # Ensure we always return a string, even if empty
+            descriptions.append(description if description else "")
         return descriptions
 
     def enrich_documents_with_rag(self, texts, docs):