aiagents4pharma 1.18.0__py3-none-any.whl → 1.19.0__py3-none-any.whl

aiagents4pharma/talk2knowledgegraphs/tools/subgraph_summarization.py

@@ -0,0 +1,126 @@
+"""
+Tool for performing subgraph summarization.
+"""
+
+import logging
+from typing import Type, Annotated
+from pydantic import BaseModel, Field
+from langchain_core.output_parsers import StrOutputParser
+from langchain_core.prompts import ChatPromptTemplate
+from langchain_core.messages import ToolMessage
+from langchain_core.tools.base import InjectedToolCallId
+from langchain_core.tools import BaseTool
+from langgraph.types import Command
+from langgraph.prebuilt import InjectedState
+import hydra
+
+# Initialize logger
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+
+class SubgraphSummarizationInput(BaseModel):
+    """
+    SubgraphSummarizationInput is a Pydantic model representing an input for
+    summarizing a given textualized subgraph.
+
+    Args:
+        tool_call_id: Tool call ID.
+        state: Injected state.
+        prompt: Prompt to interact with the backend.
+        extraction_name: Name assigned to the subgraph extraction process
+    """
+
+    tool_call_id: Annotated[str, InjectedToolCallId] = Field(
+        description="Tool call ID."
+    )
+    state: Annotated[dict, InjectedState] = Field(description="Injected state.")
+    prompt: str = Field(description="Prompt to interact with the backend.")
+    extraction_name: str = Field(
+        description="""Name assigned to the subgraph extraction process
+                                 when the subgraph_extraction tool is invoked."""
+    )
+
+
+class SubgraphSummarizationTool(BaseTool):
+    """
+    This tool performs subgraph summarization over textualized graph to highlight the most
+    important information in responding to user's prompt.
+    """
+
+    name: str = "subgraph_summarization"
+    description: str = """A tool to perform subgraph summarization over textualized graph
+                        for responding to user's follow-up prompt(s)."""
+    args_schema: Type[BaseModel] = SubgraphSummarizationInput
+
+    def _run(
+        self,
+        tool_call_id: Annotated[str, InjectedToolCallId],
+        state: Annotated[dict, InjectedState],
+        prompt: str,
+        extraction_name: str,
+    ):
+        """
+        Run the subgraph summarization tool.
+
+        Args:
+            tool_call_id: The tool call ID.
+            state: The injected state.
+            prompt: The prompt to interact with the backend.
+            extraction_name: The name assigned to the subgraph extraction process.
+        """
+        logger.log(
+            logging.INFO, "Invoking subgraph_summarization tool for %s", extraction_name
+        )
+
+        # Load hydra configuration
+        with hydra.initialize(version_base=None, config_path="../configs"):
+            cfg = hydra.compose(
+                config_name="config", overrides=["tools/subgraph_summarization=default"]
+            )
+            cfg = cfg.tools.subgraph_summarization
+
+        # Load the extracted graph
+        extracted_graph = {dic["name"]: dic for dic in state["dic_extracted_graph"]}
+        # logger.log(logging.INFO, "Extracted graph: %s", extracted_graph)
+
+        # Prepare prompt template
+        prompt_template = ChatPromptTemplate.from_messages(
+            [
+                ("system", cfg.prompt_subgraph_summarization),
+                ("human", "{input}"),
+            ]
+        )
+
+        # Prepare chain
+        chain = prompt_template | state["llm_model"] | StrOutputParser()
+
+        # Return the subgraph and textualized graph as JSON response
+        response = chain.invoke(
+            {
+                "input": prompt,
+                "textualized_subgraph": extracted_graph[extraction_name]["graph_text"],
+            }
+        )
+
+        # Store the response as graph_summary in the extracted graph
+        for key, value in extracted_graph.items():
+            if key == extraction_name:
+                value["graph_summary"] = response
+
+        # Prepare the dictionary of updated state
+        dic_updated_state_for_model = {}
+        for key, value in {
+            "dic_extracted_graph": list(extracted_graph.values()),
+        }.items():
+            if value:
+                dic_updated_state_for_model[key] = value
+
+        # Return the updated state of the tool
+        return Command(
+            update=dic_updated_state_for_model
+            | {
+                # update the message history
+                "messages": [ToolMessage(content=response, tool_call_id=tool_call_id)]
+            }
+        )

aiagents4pharma/talk2knowledgegraphs/utils/__init__.py

@@ -1,5 +1,7 @@
 '''
-This file is used to import utlities.
+This file is used to import all the models in the package.
 '''
-from . import enrichments
 from . import embeddings
+from . import enrichments
+from . import extractions
+from . import kg_utils

aiagents4pharma/talk2knowledgegraphs/utils/embeddings/__init__.py

@@ -4,3 +4,4 @@ This file is used to import all the models in the package.
 from . import embeddings
 from . import sentence_transformer
 from . import huggingface
+from . import ollama

aiagents4pharma/talk2knowledgegraphs/utils/embeddings/ollama.py

@@ -0,0 +1,81 @@
+"""
+Embedding class using Ollama model based on LangChain Embeddings class.
+"""
+
+import time
+from typing import List
+import subprocess
+import ollama
+from langchain_ollama import OllamaEmbeddings
+from .embeddings import Embeddings
+
+class EmbeddingWithOllama(Embeddings):
+    """
+    Embedding class using Ollama model based on LangChain Embeddings class.
+    """
+    def __init__(self, model_name: str):
+        """
+        Initialize the EmbeddingWithOllama class.
+
+        Args:
+            model_name: The name of the Ollama model to be used.
+        """
+        # Setup the Ollama server
+        self.__setup(model_name)
+
+        # Set parameters
+        self.model_name = model_name
+
+        # Prepare model
+        self.model = OllamaEmbeddings(model=self.model_name)
+
+    def __setup(self, model_name: str) -> None:
+        """
+        Check if the Ollama model is available and run the Ollama server if needed.
+
+        Args:
+            model_name: The name of the Ollama model to be used.
+        """
+        try:
+            models_list = ollama.list()["models"]
+            if model_name not in [m['model'].replace(":latest", "") for m in models_list]:
+                ollama.pull(model_name)
+                time.sleep(30)
+                raise ValueError(f"Pulled {model_name} model")
+        except Exception as e:
+            with subprocess.Popen(
+                "ollama serve", shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE
+            ):
+                time.sleep(10)
+            raise ValueError(f"Error: {e} and restarted Ollama server.") from e
+
+    def embed_documents(self, texts: List[str]) -> List[float]:
+        """
+        Generate embedding for a list of input texts using Ollama model.
+
+        Args:
+            texts: The list of texts to be embedded.
+
+        Returns:
+            The list of embeddings for the given texts.
+        """
+
+        # Generate the embedding
+        embeddings = self.model.embed_documents(texts)
+
+        return embeddings
+
+    def embed_query(self, text: str) -> List[float]:
+        """
+        Generate embeddings for an input text using Ollama model.
+
+        Args:
+            text: A query to be embedded.
+        Returns:
+            The embeddings for the given query.
+        """
+
+        # Generate the embedding
+        embeddings = self.model.embed_query(text)
+
+        return embeddings

aiagents4pharma/talk2knowledgegraphs/utils/extractions/__init__.py

@@ -0,0 +1,4 @@
+'''
+This file is used to import all the models in the package.
+'''
+from . import pcst

aiagents4pharma/talk2knowledgegraphs/utils/extractions/pcst.py

@@ -0,0 +1,225 @@
+"""
+Exctraction of subgraph using Prize-Collecting Steiner Tree (PCST) algorithm.
+"""
+
+from typing import Tuple, NamedTuple
+import numpy as np
+import torch
+import pcst_fast
+from torch_geometric.data.data import Data
+
+class PCSTPruning(NamedTuple):
+    """
+    Prize-Collecting Steiner Tree (PCST) pruning algorithm implementation inspired by G-Retriever
+    (He et al., 'G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and
+    Question Answering', NeurIPS 2024) paper.
+    https://arxiv.org/abs/2402.07630
+    https://github.com/XiaoxinHe/G-Retriever/blob/main/src/dataset/utils/retrieval.py
+
+    Args:
+        topk: The number of top nodes to consider.
+        topk_e: The number of top edges to consider.
+        cost_e: The cost of the edges.
+        c_const: The constant value for the cost of the edges computation.
+        root: The root node of the subgraph, -1 for unrooted.
+        num_clusters: The number of clusters.
+        pruning: The pruning strategy to use.
+        verbosity_level: The verbosity level.
+    """
+    topk: int = 3
+    topk_e: int = 3
+    cost_e: float = 0.5
+    c_const: float = 0.01
+    root: int = -1
+    num_clusters: int = 1
+    pruning: str = "gw"
+    verbosity_level: int = 0
+
+    def compute_prizes(self, graph: Data, query_emb: torch.Tensor) -> np.ndarray:
+        """
+        Compute the node prizes based on the cosine similarity between the query and nodes,
+        as well as the edge prizes based on the cosine similarity between the query and edges.
+        Note that the node and edge embeddings shall use the same embedding model and dimensions
+        with the query.
+
+        Args:
+            graph: The knowledge graph in PyTorch Geometric Data format.
+            query_emb: The query embedding in PyTorch Tensor format.
+
+        Returns:
+            The prizes of the nodes and edges.
+        """
+        # Compute prizes for nodes
+        n_prizes = torch.nn.CosineSimilarity(dim=-1)(query_emb, graph.x)
+        topk = min(self.topk, graph.num_nodes)
+        _, topk_n_indices = torch.topk(n_prizes, topk, largest=True)
+        n_prizes = torch.zeros_like(n_prizes)
+        n_prizes[topk_n_indices] = torch.arange(topk, 0, -1).float()
+
+        # Compute prizes for edges
+        # e_prizes = torch.nn.CosineSimilarity(dim=-1)(query_emb, graph.edge_attr)
+        # topk_e = min(self.topk_e, e_prizes.unique().size(0))
+        # topk_e_values, _ = torch.topk(e_prizes.unique(), topk_e, largest=True)
+        # e_prizes[e_prizes < topk_e_values[-1]] = 0.0
+        # last_topk_e_value = topk_e
+        # for k in range(topk_e):
+        #     indices = e_prizes == topk_e_values[k]
+        #     value = min((topk_e - k) / sum(indices), last_topk_e_value)
+        #     e_prizes[indices] = value
+        #     last_topk_e_value = value * (1 - self.c_const)
+
+        # Optimized version of the above code
+        e_prizes = torch.nn.CosineSimilarity(dim=-1)(query_emb, graph.edge_attr)
+        unique_prizes, inverse_indices = e_prizes.unique(return_inverse=True)
+        topk_e = min(self.topk_e, unique_prizes.size(0))
+        topk_e_values, _ = torch.topk(unique_prizes, topk_e, largest=True)
+        e_prizes[e_prizes < topk_e_values[-1]] = 0.0
+        last_topk_e_value = topk_e
+        for k in range(topk_e):
+            indices = inverse_indices == (
+                unique_prizes == topk_e_values[k]
+            ).nonzero(as_tuple=True)[0]
+            value = min((topk_e - k) / indices.sum().item(), last_topk_e_value)
+            e_prizes[indices] = value
+            last_topk_e_value = value * (1 - self.c_const)
+
+        return {"nodes": n_prizes, "edges": e_prizes}
+
+    def compute_subgraph_costs(
+        self, graph: Data, prizes: dict
+    ) -> Tuple[np.ndarray, np.ndarray, np.ndarray]:
+        """
+        Compute the costs in constructing the subgraph proposed by G-Retriever paper.
+
+        Args:
+            graph: The knowledge graph in PyTorch Geometric Data format.
+            prizes: The prizes of the nodes and the edges.
+
+        Returns:
+            edges: The edges of the subgraph, consisting of edges and number of edges without
+                virtual edges.
+            prizes: The prizes of the subgraph.
+            costs: The costs of the subgraph.
+        """
+        # Logic to reduce the cost of the edges such that at least one edge is selected
+        updated_cost_e = min(
+            self.cost_e,
+            prizes["edges"].max().item() * (1 - self.c_const / 2),
+        )
+
+        # Initialize variables
+        edges = []
+        costs = []
+        virtual = {
+            "n_prizes": [],
+            "edges": [],
+            "costs": [],
+        }
+        mapping = {"nodes": {}, "edges": {}}
+
+        # Compute the costs, edges, and virtual variables based on the prizes
+        for i, (src, dst) in enumerate(graph.edge_index.T.numpy()):
+            prize_e = prizes["edges"][i]
+            if prize_e <= updated_cost_e:
+                mapping["edges"][len(edges)] = i
+                edges.append((src, dst))
+                costs.append(updated_cost_e - prize_e)
+            else:
+                virtual_node_id = graph.num_nodes + len(virtual["n_prizes"])
+                mapping["nodes"][virtual_node_id] = i
+                virtual["edges"].append((src, virtual_node_id))
+                virtual["edges"].append((virtual_node_id, dst))
+                virtual["costs"].append(0)
+                virtual["costs"].append(0)
+                virtual["n_prizes"].append(prize_e - updated_cost_e)
+        prizes = np.concatenate([prizes["nodes"], np.array(virtual["n_prizes"])])
+        edges_dict = {}
+        edges_dict["edges"] = edges
+        edges_dict["num_prior_edges"] = len(edges)
+        # Final computation of the costs and edges based on the virtual costs and virtual edges
+        if len(virtual["costs"]) > 0:
+            costs = np.array(costs + virtual["costs"])
+            edges = np.array(edges + virtual["edges"])
+            edges_dict["edges"] = edges
+
+        return edges_dict, prizes, costs, mapping
+
+    def get_subgraph_nodes_edges(
+        self, graph: Data, vertices: np.ndarray, edges_dict: dict, mapping: dict,
+    ) -> dict:
+        """
+        Get the selected nodes and edges of the subgraph based on the vertices and edges computed
+        by the PCST algorithm.
+
+        Args:
+            graph: The knowledge graph in PyTorch Geometric Data format.
+            vertices: The vertices of the subgraph computed by the PCST algorithm.
+            edges_dict: The dictionary of edges of the subgraph computed by the PCST algorithm,
+                and the number of prior edges (without virtual edges).
+            mapping: The mapping dictionary of the nodes and edges.
+            num_prior_edges: The number of edges before adding virtual edges.
+
+        Returns:
+            The selected nodes and edges of the extracted subgraph.
+        """
+        # Get edges information
+        edges = edges_dict["edges"]
+        num_prior_edges = edges_dict["num_prior_edges"]
+        # Retrieve the selected nodes and edges based on the given vertices and edges
+        subgraph_nodes = vertices[vertices < graph.num_nodes]
+        subgraph_edges = [mapping["edges"][e] for e in edges if e < num_prior_edges]
+        virtual_vertices = vertices[vertices >= graph.num_nodes]
+        if len(virtual_vertices) > 0:
+            virtual_vertices = vertices[vertices >= graph.num_nodes]
+            virtual_edges = [mapping["nodes"][i] for i in virtual_vertices]
+            subgraph_edges = np.array(subgraph_edges + virtual_edges)
+        edge_index = graph.edge_index[:, subgraph_edges]
+        subgraph_nodes = np.unique(
+            np.concatenate(
+                [subgraph_nodes, edge_index[0].numpy(), edge_index[1].numpy()]
+            )
+        )
+
+        return {"nodes": subgraph_nodes, "edges": subgraph_edges}
+
+    def extract_subgraph(self, graph: Data, query_emb: torch.Tensor) -> dict:
+        """
+        Perform the Prize-Collecting Steiner Tree (PCST) algorithm to extract the subgraph.
+
+        Args:
+            graph: The knowledge graph in PyTorch Geometric Data format.
+            query_emb: The query embedding.
+
+        Returns:
+            The selected nodes and edges of the subgraph.
+        """
+        # Assert the topk and topk_e values for subgraph retrieval
+        assert self.topk > 0, "topk must be greater than or equal to 0"
+        assert self.topk_e > 0, "topk_e must be greater than or equal to 0"
+
+        # Retrieve the top-k nodes and edges based on the query embedding
+        prizes = self.compute_prizes(graph, query_emb)
+
+        # Compute costs in constructing the subgraph
+        edges_dict, prizes, costs, mapping = self.compute_subgraph_costs(
+            graph, prizes
+        )
+
+        # Retrieve the subgraph using the PCST algorithm
+        result_vertices, result_edges = pcst_fast.pcst_fast(
+            edges_dict["edges"],
+            prizes,
+            costs,
+            self.root,
+            self.num_clusters,
+            self.pruning,
+            self.verbosity_level,
+        )
+
+        subgraph = self.get_subgraph_nodes_edges(
+            graph,
+            result_vertices,
+            {"edges": result_edges, "num_prior_edges": edges_dict["num_prior_edges"]},
+            mapping)
+
+        return subgraph

{aiagents4pharma-1.18.0.dist-info → aiagents4pharma-1.19.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: aiagents4pharma
-Version: 1.18.0
+Version: 1.19.0
 Summary: AI Agents for drug discovery, drug development, and other pharmaceutical R&D.
 Classifier: Programming Language :: Python :: 3
 Classifier: License :: OSI Approved :: MIT License
@@ -12,6 +12,7 @@ Requires-Dist: copasi_basico==0.78
 Requires-Dist: coverage==7.6.4
 Requires-Dist: einops==0.8.0
 Requires-Dist: gdown==5.2.0
+Requires-Dist: gravis==0.1.0
 Requires-Dist: huggingface_hub==0.26.5
 Requires-Dist: hydra-core==1.3.2
 Requires-Dist: joblib==1.4.2
@@ -27,6 +28,7 @@ Requires-Dist: matplotlib==3.9.2
 Requires-Dist: openai==1.59.4
 Requires-Dist: ollama==0.4.6
 Requires-Dist: pandas==2.2.3
+Requires-Dist: pcst_fast==1.0.10
 Requires-Dist: plotly==5.24.1
 Requires-Dist: pydantic==2.9.2
 Requires-Dist: pylint==3.3.1

{aiagents4pharma-1.18.0.dist-info → aiagents4pharma-1.19.0.dist-info}/RECORD

@@ -55,31 +55,63 @@ aiagents4pharma/talk2cells/tools/__init__.py,sha256=38nK2a_lEFRjO3qD6Fo9a3983ZCY
 aiagents4pharma/talk2cells/tools/scp_agent/__init__.py,sha256=s7g0lyH1lMD9pcWHLPtwRJRvzmTh2II7DrxyLulpjmQ,163
 aiagents4pharma/talk2cells/tools/scp_agent/display_studies.py,sha256=6q59gh_NQaiOU2rn55A3sIIFKlXi4SK3iKgySvUDrtQ,600
 aiagents4pharma/talk2cells/tools/scp_agent/search_studies.py,sha256=MLe-twtFnOu-P8P9diYq7jvHBHbWFRRCZLcfpUzqPMg,2806
-aiagents4pharma/talk2knowledgegraphs/__init__.py,sha256=4smVQoSMM6rflVnNkABqlDAAlSn4bYsq7rMVWjRGvis,103
+aiagents4pharma/talk2knowledgegraphs/__init__.py,sha256=Z0Eo7LTiKk0STsr8VI7wkCLq7PHrK1vYlH4I1hSNLiA,165
+aiagents4pharma/talk2knowledgegraphs/agents/__init__.py,sha256=iOAzuy_8A03tQDFtSBhC9dldUo62z5gfxcVtXAdLOJs,92
+aiagents4pharma/talk2knowledgegraphs/agents/t2kg_agent.py,sha256=j6MA1LB28mqpb6ZEmNLGcvDZvOnlGbJB9r7VXyEGask,3079
+aiagents4pharma/talk2knowledgegraphs/configs/__init__.py,sha256=Y49ucO22v9oe9EwFiXN6MU2wvyB3_ZBpmHwHbeh-ZVQ,106
+aiagents4pharma/talk2knowledgegraphs/configs/config.yaml,sha256=rwUIZ2t5j5hlFyre7VnV8zMsP0qpPTwvAFExgvQD6q0,196
+aiagents4pharma/talk2knowledgegraphs/configs/agents/t2kg_agent/__init__.py,sha256=-fAORvyFmG2iSvFOFDixmt9OTQRR58y89uhhu2EgbA8,46
+aiagents4pharma/talk2knowledgegraphs/configs/agents/t2kg_agent/default.yaml,sha256=ENCGROwYFpR6g4QD518h73sshdn3vPVpotBMk1QJcpU,4830
+aiagents4pharma/talk2knowledgegraphs/configs/app/__init__.py,sha256=fKfc3FR7g5KjY9b6jzrU6cwKTVVpkoVZQS3dvUowu34,69
+aiagents4pharma/talk2knowledgegraphs/configs/app/frontend/__init__.py,sha256=-fAORvyFmG2iSvFOFDixmt9OTQRR58y89uhhu2EgbA8,46
+aiagents4pharma/talk2knowledgegraphs/configs/app/frontend/default.yaml,sha256=4azC4cH-_-zt-bRVgNjkFM24mjNke6Rgn9pNl7XWrPQ,912
+aiagents4pharma/talk2knowledgegraphs/configs/tools/__init__.py,sha256=C1yyRZW8hqWw46p_bh1vAJp2z9aVvn4HpKjKkjlWIqY,150
+aiagents4pharma/talk2knowledgegraphs/configs/tools/graphrag_reasoning/__init__.py,sha256=-fAORvyFmG2iSvFOFDixmt9OTQRR58y89uhhu2EgbA8,46
+aiagents4pharma/talk2knowledgegraphs/configs/tools/graphrag_reasoning/default.yaml,sha256=Ua99yECXiwp4ZCUDgsDskYbKzcJrv7roQuLj31Zky4c,1037
+aiagents4pharma/talk2knowledgegraphs/configs/tools/subgraph_extraction/__init__.py,sha256=-fAORvyFmG2iSvFOFDixmt9OTQRR58y89uhhu2EgbA8,46
+aiagents4pharma/talk2knowledgegraphs/configs/tools/subgraph_extraction/default.yaml,sha256=U8HvMsYbaOwDwQPATj7EFvLtTy7XZEplE5WMoNjgYYc,1469
+aiagents4pharma/talk2knowledgegraphs/configs/tools/subgraph_summarization/__init__.py,sha256=-fAORvyFmG2iSvFOFDixmt9OTQRR58y89uhhu2EgbA8,46
+aiagents4pharma/talk2knowledgegraphs/configs/tools/subgraph_summarization/default.yaml,sha256=OOSlPpJVwJK4_lu4lhA2E48yhFFbEYpyHsoi9Orgm00,561
 aiagents4pharma/talk2knowledgegraphs/datasets/__init__.py,sha256=L3gPuHskSegmtXskVrLIYr7FXe_ibKgJ2GGr1_Wok6k,173
 aiagents4pharma/talk2knowledgegraphs/datasets/biobridge_primekg.py,sha256=QlzDXmXREoa9MA6-GwzqRjdzndQeGBAF11Td6NFk_9Y,23426
 aiagents4pharma/talk2knowledgegraphs/datasets/dataset.py,sha256=-LaPLse8BkALqwFetNK7wch2dt9Dz6QKGKZKBKM6bIk,409
 aiagents4pharma/talk2knowledgegraphs/datasets/primekg.py,sha256=KBMhCJ7yjMWqQJJctFYdpjYAlwv48Jl6i1dddXP4f08,7599
 aiagents4pharma/talk2knowledgegraphs/datasets/starkqa_primekg.py,sha256=Y-6-nORsnBJlU6rH0skyfr9S9J4PfTWK-af_p5UuknQ,7483
+aiagents4pharma/talk2knowledgegraphs/states/__init__.py,sha256=XaqorSvx634dWRRlXUdzlisHtYMyqgJ2q7TanzsKlhw,108
+aiagents4pharma/talk2knowledgegraphs/states/state_talk2knowledgegraphs.py,sha256=6HqGo-awqoyNJG0igm5so5A4Tq8RPkCsjPg8Go38csE,1066
 aiagents4pharma/talk2knowledgegraphs/tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+aiagents4pharma/talk2knowledgegraphs/tests/test_agents_t2kg_agent.py,sha256=CCN6cyhEaiXSvIC-4y3ueDSzjDCBYDsmSmOor-DMeF4,3928
 aiagents4pharma/talk2knowledgegraphs/tests/test_datasets_biobridge_primekg.py,sha256=crH0eFA3P8P6IYzi1UWNa4YvRVrtlBzoScf9NaE1lDk,9827
 aiagents4pharma/talk2knowledgegraphs/tests/test_datasets_dataset.py,sha256=NFUlsZvhfIrkF4YenWfahrLK93Xhm5UYEGG_uYN2LVM,566
 aiagents4pharma/talk2knowledgegraphs/tests/test_datasets_primekg.py,sha256=Pvu0r93CpnhjkfMxc-EiVLpAJ04FdW9iTamCnetu654,2272
 aiagents4pharma/talk2knowledgegraphs/tests/test_datasets_starkqa_primekg.py,sha256=TuIsqcN1Mww3DTqGk6ebgJBWzUWdMWEq2yRQuYSFqvA,4416
+aiagents4pharma/talk2knowledgegraphs/tests/test_tools_graphrag_reasoning.py,sha256=aOKHTber2Cg3mjNjfIa6RZU7XdFj5C2ps1YEUXw76CI,10650
+aiagents4pharma/talk2knowledgegraphs/tests/test_tools_subgraph_extraction.py,sha256=zRi2j9Dm3VFywhhrPjVoJ7z_zJpAEM74MJRXapnhwVE,6246
+aiagents4pharma/talk2knowledgegraphs/tests/test_tools_subgraph_summarization.py,sha256=oBqfspXXOxH04OQuPb8BCW0liIQTGKXtaPNSrPpQtFc,7597
 aiagents4pharma/talk2knowledgegraphs/tests/test_utils_embeddings_embeddings.py,sha256=uYFoE_6zeU10_1mLLAHUr5c4S2XZMSc0Q_860o-KWEw,1517
-aiagents4pharma/talk2knowledgegraphs/tests/test_utils_embeddings_huggingface.py,sha256=EINWyXg_3AMHF3WzFLhIUiFDuaEhTVHBvVAJr8VtMDg,1624
+aiagents4pharma/talk2knowledgegraphs/tests/test_utils_embeddings_huggingface.py,sha256=hzX84pheZdEsTtikF2KtBFiH44_xPjYXxLA6p4Ax1CY,1623
+aiagents4pharma/talk2knowledgegraphs/tests/test_utils_embeddings_ollama.py,sha256=jn-TrPwF0aR9kVoerwkbMZa3U6Hc6HjV6Zoau4qSH4g,1834
 aiagents4pharma/talk2knowledgegraphs/tests/test_utils_embeddings_sentencetransformer.py,sha256=Qxo6WeIDRy8aLh1tNKw0kSlzmUj3MtTak63oW2YwB24,1327
 aiagents4pharma/talk2knowledgegraphs/tests/test_utils_enrichments_enrichments.py,sha256=N6HRr4lWHXY7bTHe2uXJe4D_EG9WqZPibZne6qLl9_k,1447
-aiagents4pharma/talk2knowledgegraphs/tests/test_utils_enrichments_ollama.py,sha256=kMuB_vci6hKr2qJgXBmcje7yxeJ2nY2ImXw-NSJpts0,3912
-aiagents4pharma/talk2knowledgegraphs/utils/__init__.py,sha256=X8kSpmDTMkeE0fA5D0CWMsQ52YKoM5rRSXrjnali3IM,97
+aiagents4pharma/talk2knowledgegraphs/tests/test_utils_enrichments_ollama.py,sha256=JhY7axvVULLywDJ2ctA-gob5YPeaJYWsaMNjHT6L9CU,3021
+aiagents4pharma/talk2knowledgegraphs/tests/test_utils_kg_utils.py,sha256=pal76wi7WgQWUNk56BrzfFV8jKpbDaHHdbwtgx_gXLI,2410
+aiagents4pharma/talk2knowledgegraphs/tools/__init__.py,sha256=zpD4h7EYtyq0QNOqLd6bkxrPlPb2XN64ceI9ncgESrA,171
+aiagents4pharma/talk2knowledgegraphs/tools/graphrag_reasoning.py,sha256=OEuOFncDRdb7TQEGq4rkT5On-jI-R7Nt8K5EBzaND8w,5338
+aiagents4pharma/talk2knowledgegraphs/tools/load_arguments.py,sha256=zhmsRp-8vjB5rRekqTA07d3yb-42HWqng9dDMkvK6hM,623
+aiagents4pharma/talk2knowledgegraphs/tools/subgraph_extraction.py,sha256=te06QMFQfgJWrjaGrqpcOYeaV38jwm0KY_rXVSMHkeI,11468
+aiagents4pharma/talk2knowledgegraphs/tools/subgraph_summarization.py,sha256=mDSBOxopDfNhEJeU8fVI8b5lXTYrRzcc97aLbFgYSy4,4413
+aiagents4pharma/talk2knowledgegraphs/utils/__init__.py,sha256=Q9mzcSmkmhdnOn13fxGh1fNECYoUR5Y5CCuEJTIxwAI,167
 aiagents4pharma/talk2knowledgegraphs/utils/kg_utils.py,sha256=6vQnPkeOWae_8jePjhma3sJuMTngy0I0tqzdFt6OqKg,2507
-aiagents4pharma/talk2knowledgegraphs/utils/embeddings/__init__.py,sha256=xRb0x7SoAb0nSVZYgjrqxWvENOMDuqIdL43NMjoOaCs,153
+aiagents4pharma/talk2knowledgegraphs/utils/embeddings/__init__.py,sha256=4TGK0XIVkkfGOyrSVwFQ-Lp-rzH9CCl-fWcqkFJKRLc,174
 aiagents4pharma/talk2knowledgegraphs/utils/embeddings/embeddings.py,sha256=1nGznrAj-xT0xuSMBGz2dOujJ7M_IwSR84njxtxsy9A,2523
 aiagents4pharma/talk2knowledgegraphs/utils/embeddings/huggingface.py,sha256=2vi_elf6EgzfagFAO5QnL3a_aXZyN7B1EBziu44MTfM,3806
+aiagents4pharma/talk2knowledgegraphs/utils/embeddings/ollama.py,sha256=8w0sjt3Ex5YJ_XvpKl9UbhdTiiaoMIarbPUxLBU-1Uw,2378
 aiagents4pharma/talk2knowledgegraphs/utils/embeddings/sentence_transformer.py,sha256=36iKlisOpMtGR5xfTAlSHXWvPqVC_Jbezod8kbBBMVg,2136
 aiagents4pharma/talk2knowledgegraphs/utils/enrichments/__init__.py,sha256=tW426knki2DBIHcWyF_K04iMMdbpIn_e_TpPmTgz2dI,113
 aiagents4pharma/talk2knowledgegraphs/utils/enrichments/enrichments.py,sha256=Bx8x6zzk5614ApWB90N_iv4_Y_Uq0-KwUeBwYSdQMU4,924
 aiagents4pharma/talk2knowledgegraphs/utils/enrichments/ollama.py,sha256=8eoxR-VHo0G7ReQIwje7xEhE-SJlHdef7_wJRpnvFIc,4116
+aiagents4pharma/talk2knowledgegraphs/utils/extractions/__init__.py,sha256=7gwwtfzKhB8GuOBD47XRi0NprwEXkOzwNl5eeu-hDTI,86
+aiagents4pharma/talk2knowledgegraphs/utils/extractions/pcst.py,sha256=m5p0yoJb7I19ua5yeQfXPf7c4r6S1XPwttsrM7Qoy94,9336
 aiagents4pharma/talk2scholars/__init__.py,sha256=gphERyVKZHvOnMQsml7TIHlaIshHJ75R1J3FKExkfuY,120
 aiagents4pharma/talk2scholars/agents/__init__.py,sha256=ykszlVGxz3egLHZAttlNoTPxIrnQJZYva_ssR8fwIFk,117
 aiagents4pharma/talk2scholars/agents/main_agent.py,sha256=etPQUCjHtD-in-kD7Wg_UD6jRtCHj-mj41y03PYbAQM,4616
@@ -112,8 +144,8 @@ aiagents4pharma/talk2scholars/tools/s2/display_results.py,sha256=B8JJGohi1Eyx8C3
 aiagents4pharma/talk2scholars/tools/s2/multi_paper_rec.py,sha256=0Y3q8TkF_Phng9L7g1kk9Fhyit9UNitWurp03H0GZv8,4455
 aiagents4pharma/talk2scholars/tools/s2/search.py,sha256=CcgFN7YuuQ9Vl1DJcldnnvPrswABKjNxeauK1rABps8,4176
 aiagents4pharma/talk2scholars/tools/s2/single_paper_rec.py,sha256=irS-igdG8BZbVb0Z4VlIjzsyBlUfREd0v0_RlUM-0_U,4994
-aiagents4pharma-1.18.0.dist-info/LICENSE,sha256=IcIbyB1Hyk5ZDah03VNQvJkbNk2hkBCDqQ8qtnCvB4Q,1077
-aiagents4pharma-1.18.0.dist-info/METADATA,sha256=0DruGN7wacwsdocwdBJoIYnwqd6aGxii98DHkPkCu48,6991
-aiagents4pharma-1.18.0.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-aiagents4pharma-1.18.0.dist-info/top_level.txt,sha256=-AH8rMmrSnJtq7HaAObS78UU-cTCwvX660dSxeM7a0A,16
-aiagents4pharma-1.18.0.dist-info/RECORD,,
+aiagents4pharma-1.19.0.dist-info/LICENSE,sha256=IcIbyB1Hyk5ZDah03VNQvJkbNk2hkBCDqQ8qtnCvB4Q,1077
+aiagents4pharma-1.19.0.dist-info/METADATA,sha256=jMpgcCw7eRa0gUr_cCMCX38iit_D0LQE2VdzHliAk_M,7053
+aiagents4pharma-1.19.0.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+aiagents4pharma-1.19.0.dist-info/top_level.txt,sha256=-AH8rMmrSnJtq7HaAObS78UU-cTCwvX660dSxeM7a0A,16
+aiagents4pharma-1.19.0.dist-info/RECORD,,