aiagents4pharma 1.46.3__py3-none-any.whl → 1.46.5__py3-none-any.whl

aiagents4pharma/talk2aiagents4pharma/install.md

@@ -11,10 +11,6 @@ If your machine has NVIDIA GPU(s), please install the following this:
 
 _This agent is available on Docker Hub._
 
-**Prerequisites**
-
-- [Milvus](https://milvus.io) (for a vector database)
-
 ---
 
 #### 1. Download files
@@ -61,7 +57,7 @@ MILVUS_HOST=localhost
 MILVUS_PORT=19530
 MILVUS_USER=root
 MILVUS_PASSWORD=Milvus
-MILVUS_DATABASE=your_database_name_here
+MILVUS_DATABASE=t2kg_primekg
 
 # Specify the data directory for multimodal data to your own data directory
 # DATA_DIR=/your_absolute_path_to_your_data_dir/

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/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/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/talk2knowledgegraphs/install.md

@@ -22,12 +22,6 @@ If your machine has NVIDIA GPU(s), please install the following this:
 
 _This agent is available on Docker Hub._
 
-**Prerequisites**
-
-- If your machine has NVIDIA GPU(s), please install [nvidia-container-toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/1.17.8/install-guide.html) (required for GPU support with Docker; enables containers to access NVIDIA GPUs for accelerated computing). After installing `nvidia-container-toolkit`, please restart Docker to ensure GPU support is enabled.
-
-- [Milvus](https://milvus.io) (for a vector database)
-
 ---
 
 #### 1. Download files
@@ -74,7 +68,7 @@ MILVUS_HOST=localhost
 MILVUS_PORT=19530
 MILVUS_USER=root
 MILVUS_PASSWORD=Milvus
-MILVUS_DATABASE=your_database_name_here
+MILVUS_DATABASE=t2kg_primekg
 
 # Specify the data directory for multimodal data to your own data directory
 # DATA_DIR=/your_absolute_path_to_your_data_dir/

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/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/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/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/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):

{aiagents4pharma-1.46.3.dist-info → aiagents4pharma-1.46.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: aiagents4pharma
-Version: 1.46.3
+Version: 1.46.5
 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.dist-info → aiagents4pharma-1.46.5.dist-info}/RECORD

@@ -3,7 +3,7 @@ aiagents4pharma/talk2aiagents4pharma/.dockerignore,sha256=-hAM7RzkGbjDeU411-kXOm
 aiagents4pharma/talk2aiagents4pharma/Dockerfile,sha256=J2QvwifcCxtz9EzPaq99zhSygHV9ADsB5ZQ_cmiwATI,3533
 aiagents4pharma/talk2aiagents4pharma/README.md,sha256=0eGxj7jxi_LrCvX-4I4KrQv-7T2ivo3pqLslG7suaCk,74
 aiagents4pharma/talk2aiagents4pharma/__init__.py,sha256=gjVTAhBHKPEFBbv_2T-MWuDdwHhAKfWIo-lQSrcsLNE,97
-aiagents4pharma/talk2aiagents4pharma/install.md,sha256=YYzY1vIEA6RrVUvNuv-h_YTarBp4khTWfFTzRQ3iKSA,4286
+aiagents4pharma/talk2aiagents4pharma/install.md,sha256=5oyy9P8fd03x3f_jOFZTGg2G1AzxMIOrH2vVd8ZS4Iw,4201
 aiagents4pharma/talk2aiagents4pharma/agents/__init__.py,sha256=NpNI6Vr9XIr5m0ZaO32c6NEUTDOZvJUqd8gKzNZhcSw,130
 aiagents4pharma/talk2aiagents4pharma/agents/main_agent.py,sha256=1nRIhj3huv9eVT7v3nhSvx1dDOEEaiApPi7AMRDviXE,2750
 aiagents4pharma/talk2aiagents4pharma/configs/__init__.py,sha256=hwLAR-uhZGEbD5R7mp4kiltSvxuKkG6-_ac17sF-4xU,68
@@ -96,8 +96,8 @@ aiagents4pharma/talk2knowledgegraphs/Dockerfile,sha256=qGy6I4oBvQonpDEANQaCW-5JM
 aiagents4pharma/talk2knowledgegraphs/README.md,sha256=0eGxj7jxi_LrCvX-4I4KrQv-7T2ivo3pqLslG7suaCk,74
 aiagents4pharma/talk2knowledgegraphs/__init__.py,sha256=ZztaRzRlovSXtVX3i9Rvf84ivIjPn8RMPiYRkbkEJ0E,114
 aiagents4pharma/talk2knowledgegraphs/entrypoint.sh,sha256=EK_jGau1VuW1uTmFWZcKhLMK9VanC5l3q9axF4ZYgmI,5758
-aiagents4pharma/talk2knowledgegraphs/install.md,sha256=6eZe9czZ8nRrsOHbRmn9WaAk9xgl2kxDZac4Exs1WqU,6022
-aiagents4pharma/talk2knowledgegraphs/milvus_data_dump.py,sha256=nLChVpn9KwJ2F5zgtb51zG2s81vOzc6o5Ut-xhkjpJI,35550
+aiagents4pharma/talk2knowledgegraphs/install.md,sha256=1rCv2e6ywb-kZOxtqFJ25qpWHl2MCa9bW6nHYHfxJMI,5555
+aiagents4pharma/talk2knowledgegraphs/milvus_data_dump.py,sha256=D5BB700QshEhY6paByXNLyMjOYyO4Csm4ODgbeeWfmc,35616
 aiagents4pharma/talk2knowledgegraphs/agents/__init__.py,sha256=ugUvVYEdjbZ3y_dogfF5hpQ3lFPFrAvLSydlcpbkGo0,93
 aiagents4pharma/talk2knowledgegraphs/agents/t2kg_agent.py,sha256=GDeSjJNhAqQWagZOxAWUKqDhzUohHViSsu444W9SzRQ,3240
 aiagents4pharma/talk2knowledgegraphs/configs/__init__.py,sha256=H-yhTbJ_RXBLe3XSto5x6FmVrgbi7y1WKEfiwmKzLAk,87
@@ -118,15 +118,15 @@ aiagents4pharma/talk2knowledgegraphs/configs/tools/subgraph_summarization/__init
 aiagents4pharma/talk2knowledgegraphs/configs/tools/subgraph_summarization/default.yaml,sha256=kiHerHXsGuohu_FLq58nXkY3bwlSFMw3kGqtQ68LMfA,562
 aiagents4pharma/talk2knowledgegraphs/configs/utils/database/milvus/__init__.py,sha256=fqQQ-GlRcbzru2KmEk3oMma0R6_SzGM8dOXzYeU4oVA,46
 aiagents4pharma/talk2knowledgegraphs/configs/utils/database/milvus/default.yaml,sha256=4J6cIguIy4Z794UM9EHwzwzwrwWv7qvsKTN8c5QucLc,2394
-aiagents4pharma/talk2knowledgegraphs/configs/utils/enrichments/ols_terms/default.yaml,sha256=7Fu03IkClglxbAzwTUdy-z-Tv6MZuo4oIdBYpQ7TPjI,107
+aiagents4pharma/talk2knowledgegraphs/configs/utils/enrichments/ols_terms/default.yaml,sha256=PKBc8BmnxVW4mosHFSyp05Ksw9zZ1_K8SaMQZXPC8rI,105
 aiagents4pharma/talk2knowledgegraphs/configs/utils/enrichments/reactome_pathways/default.yaml,sha256=gyYLJREMO1jDex8-0CcCPfsuD5KguY6fKDmDCL_S4Uc,125
 aiagents4pharma/talk2knowledgegraphs/configs/utils/enrichments/uniprot_proteins/default.yaml,sha256=JlmawYim5ECgAKCZta3UrPD2YIjkD2d5TvLmR5V6wXM,184
 aiagents4pharma/talk2knowledgegraphs/configs/utils/pubchem_utils/default.yaml,sha256=J9261xMxU8Bq0x9J5YNz21gnxXpzUBbBgCQc4OIkn-w,384
 aiagents4pharma/talk2knowledgegraphs/datasets/__init__.py,sha256=jNa-ehuOVOthQuGHigYuQN4moUEQKfn5WsdnrX0WQVc,135
-aiagents4pharma/talk2knowledgegraphs/datasets/biobridge_primekg.py,sha256=w3H_cwSpZyZUhiFUcg9tbTSSmnb3ttLU3ho7GgkTyyo,23739
+aiagents4pharma/talk2knowledgegraphs/datasets/biobridge_primekg.py,sha256=M6NtpMTmSahqKzk0WYG9JEi7Yu7YORqUKgtsA21W_4M,23632
 aiagents4pharma/talk2knowledgegraphs/datasets/dataset.py,sha256=ls0e15uudIbb4zwHMHxjEovmH145RJ_hPeZni89KSnM,411
 aiagents4pharma/talk2knowledgegraphs/datasets/primekg.py,sha256=1WHlQCAyKjpBiX3JnIsSohUZe8Yi5pY-VDP4tCugxkg,7709
-aiagents4pharma/talk2knowledgegraphs/datasets/starkqa_primekg.py,sha256=rM1FnlOfQA6Vn7iPuCEW-aP70zSMsEP99Zm6VeNUXL8,7498
+aiagents4pharma/talk2knowledgegraphs/datasets/starkqa_primekg.py,sha256=JtP-jNIFDA3xQbzy5DkK2OHin5NnbWUGa_EJ_1OH6vE,7483
 aiagents4pharma/talk2knowledgegraphs/docker-compose/cpu/.env.example,sha256=twsuiEN-FczXfka40_bVoSQXaMDR_3J3ESKCqU4qSkg,585
 aiagents4pharma/talk2knowledgegraphs/docker-compose/cpu/docker-compose.yml,sha256=7BNUIkwP0cAUH1jznun5-RgsIAZisegLFGiiUZG9F1Y,2631
 aiagents4pharma/talk2knowledgegraphs/docker-compose/gpu/.env.example,sha256=twsuiEN-FczXfka40_bVoSQXaMDR_3J3ESKCqU4qSkg,585
@@ -152,7 +152,7 @@ aiagents4pharma/talk2knowledgegraphs/tests/test_utils_embeddings_ollama.py,sha25
 aiagents4pharma/talk2knowledgegraphs/tests/test_utils_embeddings_sentencetransformer.py,sha256=Xkuf2UFGCXldj1zcsh6kqfQYLDf5i0B6KP3KcmNLSzQ,1452
 aiagents4pharma/talk2knowledgegraphs/tests/test_utils_enrichments_enrichments.py,sha256=JoSRfz6vXLnLY6INxYm731Pu5pGdQy4r3KYlIwV8cog,1428
 aiagents4pharma/talk2knowledgegraphs/tests/test_utils_enrichments_ollama.py,sha256=dJS9wXE1pmgqNSnudYkSgU_TgdFBDNBdIhnO24a-1vE,3021
-aiagents4pharma/talk2knowledgegraphs/tests/test_utils_enrichments_ols.py,sha256=YTWDJfpmkKhAduAv8sncMMhmlIYnLeYX6yu3hBu7uNI,2281
+aiagents4pharma/talk2knowledgegraphs/tests/test_utils_enrichments_ols.py,sha256=ysy6W-UfUFiXFHoYptpySmk3dO2lv7mviUoFOG3j8CE,2277
 aiagents4pharma/talk2knowledgegraphs/tests/test_utils_enrichments_pubchem.py,sha256=USHsjpfHxAktxjc5Q8INZ7qQJDWn_XFQYsS6mpeTLv0,1704
 aiagents4pharma/talk2knowledgegraphs/tests/test_utils_enrichments_reactome.py,sha256=eseSw3flQLQAmXLS2R-bobN3QGEs_i6iId8l4bLEitE,1658
 aiagents4pharma/talk2knowledgegraphs/tests/test_utils_enrichments_uniprot.py,sha256=8JqptVypftx4IrObzxGPDjQ1C7I24f3zUUx69D8svAo,1615
@@ -163,8 +163,8 @@ aiagents4pharma/talk2knowledgegraphs/tools/__init__.py,sha256=unrqqDUAmfTpgiJSV6
 aiagents4pharma/talk2knowledgegraphs/tools/graphrag_reasoning.py,sha256=cCPBH1tKs9MjX1q9v6BXi-dInz_gxKwMyIVA-XdKocg,5251
 aiagents4pharma/talk2knowledgegraphs/tools/load_arguments.py,sha256=zhmsRp-8vjB5rRekqTA07d3yb-42HWqng9dDMkvK6hM,623
 aiagents4pharma/talk2knowledgegraphs/tools/milvus_multimodal_subgraph_extraction.py,sha256=chyHEOlbzLwPd8IXwgA4B2YMWbJAyBikBkf2-x_XH1E,39730
-aiagents4pharma/talk2knowledgegraphs/tools/multimodal_subgraph_extraction.py,sha256=cAsRkBklFxitBDNvhOIqmqd0ZTjtRYKsgb-rySC0PTk,14774
-aiagents4pharma/talk2knowledgegraphs/tools/subgraph_extraction.py,sha256=DSUucfzKf3LoOo1v9snp6-Zk1vTGB9jeH-hshatd0PY,11161
+aiagents4pharma/talk2knowledgegraphs/tools/multimodal_subgraph_extraction.py,sha256=GC950xmnd5ZKq9Eru-wZl4LKZ_xdPbOPTscd2t-rE2s,14718
+aiagents4pharma/talk2knowledgegraphs/tools/subgraph_extraction.py,sha256=JW14u3w4m-2GtQxFLgyKpT0GCUPMgojE2aMJZEmUDPE,11107
 aiagents4pharma/talk2knowledgegraphs/tools/subgraph_summarization.py,sha256=mXuKTahLXXFYFMS-0HkmiP7o6MSLjE_REEEsxPwCF7c,4372
 aiagents4pharma/talk2knowledgegraphs/utils/__init__.py,sha256=OwsMjDLRsVdHm6jS_oKbUP9tUKOwGt2yOjz5EgWCv_M,144
 aiagents4pharma/talk2knowledgegraphs/utils/kg_utils.py,sha256=IeCekDG__hjvIBXk4geLLBzlrLJukVg2y8IZfXTosQ0,2188
@@ -180,7 +180,7 @@ aiagents4pharma/talk2knowledgegraphs/utils/embeddings/sentence_transformer.py,sh
 aiagents4pharma/talk2knowledgegraphs/utils/enrichments/__init__.py,sha256=VvW-zb7hdE1oIZloKDMszAJbLQr5lzofzLxshGxUC44,195
 aiagents4pharma/talk2knowledgegraphs/utils/enrichments/enrichments.py,sha256=gCd0dLfozemOZxgtFVI5dE4dsQ9YmREcvU-a2us_zvw,925
 aiagents4pharma/talk2knowledgegraphs/utils/enrichments/ollama.py,sha256=1WiOQm8OCuhMFV4SmF85cUe4m940HCNRTghvHzp0ELI,4137
-aiagents4pharma/talk2knowledgegraphs/utils/enrichments/ols_terms.py,sha256=c4jJG7H6PiemzTD4zoCvMImC0uk6AuEBnYAV1jSomxc,2691
+aiagents4pharma/talk2knowledgegraphs/utils/enrichments/ols_terms.py,sha256=asn0Ko5sULojZyjz6ouTfEuc_FEeZDKsBtXqURrA-xY,2788
 aiagents4pharma/talk2knowledgegraphs/utils/enrichments/pubchem_strings.py,sha256=9CyDA0aRYmfdR-ZiSQA5edh8hBWVEKjvPNkzVKWxnK4,2578
 aiagents4pharma/talk2knowledgegraphs/utils/enrichments/reactome_pathways.py,sha256=8iyrT1p01GJpi7k7FCuwZBqn-hyueRWYxPqabM5U80Q,1990
 aiagents4pharma/talk2knowledgegraphs/utils/enrichments/uniprot_proteins.py,sha256=0mTFX5sVgBZHkEuf057lCFNciTBapn9CqPi2-YublUg,3013
@@ -328,7 +328,7 @@ aiagents4pharma/talk2scholars/tools/zotero/utils/review_helper.py,sha256=-q-UuzP
 aiagents4pharma/talk2scholars/tools/zotero/utils/write_helper.py,sha256=K1EatPfC-riGyFmkOAS3ReNBaGPY-znne1KqOnFahkI,7339
 aiagents4pharma/talk2scholars/tools/zotero/utils/zotero_path.py,sha256=sKkfJu3u4LKSZjfoQRfeqz26IESHRwBtcSDzLMLlJMo,6311
 aiagents4pharma/talk2scholars/tools/zotero/utils/zotero_pdf_downloader.py,sha256=DBrF5IiF7VRP58hUK8T9LST3lQWLFixLUfnpMSTccoQ,4614
-aiagents4pharma-1.46.3.dist-info/METADATA,sha256=Meyuvauy5hfSodpwNdv5AqHVcjglDxZNBuLLIKzl7m8,17035
-aiagents4pharma-1.46.3.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-aiagents4pharma-1.46.3.dist-info/licenses/LICENSE,sha256=IcIbyB1Hyk5ZDah03VNQvJkbNk2hkBCDqQ8qtnCvB4Q,1077
-aiagents4pharma-1.46.3.dist-info/RECORD,,
+aiagents4pharma-1.46.5.dist-info/METADATA,sha256=Tnoq6TWzRepVimi-VimoYIP_hTsz24Z9jk328UuAfxw,17035
+aiagents4pharma-1.46.5.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+aiagents4pharma-1.46.5.dist-info/licenses/LICENSE,sha256=IcIbyB1Hyk5ZDah03VNQvJkbNk2hkBCDqQ8qtnCvB4Q,1077
+aiagents4pharma-1.46.5.dist-info/RECORD,,