Merge branch 'main' into feat/COG-544-eval-on-swe-bench
This commit is contained in:
Rita Aleksziev
commit
4d6229bf7e
18 changed files with 719 additions and 546 deletions
|
|
@ -62,3 +62,8 @@ class GraphDBInterface(Protocol):
|
|||
async def delete_graph(
|
||||
self,
|
||||
): raise NotImplementedError
|
||||
|
||||
@abstractmethod
|
||||
async def get_graph_data(
|
||||
self
|
||||
): raise NotImplementedError
|
||||
|
|
|
|||
|
|
@ -27,9 +27,6 @@ class Neo4jAdapter(GraphDBInterface):
|
|||
max_connection_lifetime = 120
|
||||
)
|
||||
|
||||
async def close(self) -> None:
|
||||
await self.driver.close()
|
||||
|
||||
@asynccontextmanager
|
||||
async def get_session(self) -> AsyncSession:
|
||||
async with self.driver.session() as session:
|
||||
|
|
|
|||
|
|
@ -112,10 +112,18 @@ class LanceDBAdapter(VectorDBInterface):
|
|||
for (data_point_index, data_point) in enumerate(data_points)
|
||||
]
|
||||
|
||||
await collection.merge_insert("id") \
|
||||
.when_matched_update_all() \
|
||||
.when_not_matched_insert_all() \
|
||||
.execute(lance_data_points)
|
||||
# TODO: This enables us to work with pydantic version but shouldn't
|
||||
# stay like this, existing rows should be updated
|
||||
|
||||
await collection.delete("id IS NOT NULL")
|
||||
|
||||
original_size = await collection.count_rows()
|
||||
await collection.add(lance_data_points)
|
||||
new_size = await collection.count_rows()
|
||||
|
||||
if new_size <= original_size:
|
||||
raise ValueError(
|
||||
"LanceDB create_datapoints error: data points did not get added.")
|
||||
|
||||
|
||||
async def retrieve(self, collection_name: str, data_point_ids: list[str]):
|
||||
|
|
|
|||
|
|
@ -17,6 +17,7 @@ class TextChunker():
|
|||
self.get_text = get_text
|
||||
|
||||
def read(self):
|
||||
self.paragraph_chunks = []
|
||||
for content_text in self.get_text():
|
||||
for chunk_data in chunk_by_paragraph(
|
||||
content_text,
|
||||
|
|
|
|||
|
|
@ -1,84 +0,0 @@
|
|||
import random
|
||||
|
||||
from datasets import load_dataset
|
||||
|
||||
from dspy.datasets.dataset import Dataset
|
||||
|
||||
|
||||
class HotPotQA(Dataset):
|
||||
def __init__(self, *args, only_hard_examples=True, keep_details='dev_titles', unofficial_dev=True, **kwargs) -> None:
|
||||
super().__init__(*args, **kwargs)
|
||||
assert only_hard_examples, "Care must be taken when adding support for easy examples." \
|
||||
"Dev must be all hard to match official dev, but training can be flexible."
|
||||
|
||||
hf_official_train = load_dataset("hotpot_qa", 'fullwiki', split='train')
|
||||
hf_official_dev = load_dataset("hotpot_qa", 'fullwiki', split='validation')
|
||||
|
||||
official_train = []
|
||||
for raw_example in hf_official_train:
|
||||
if raw_example['level'] == 'hard':
|
||||
if keep_details is True:
|
||||
keys = ['id', 'question', 'answer', 'type', 'supporting_facts', 'context']
|
||||
elif keep_details == 'dev_titles':
|
||||
keys = ['question', 'answer', 'supporting_facts']
|
||||
else:
|
||||
keys = ['question', 'answer']
|
||||
|
||||
example = {k: raw_example[k] for k in keys}
|
||||
|
||||
if 'supporting_facts' in example:
|
||||
example['gold_titles'] = set(example['supporting_facts']['title'])
|
||||
del example['supporting_facts']
|
||||
|
||||
official_train.append(example)
|
||||
|
||||
rng = random.Random(0)
|
||||
rng.shuffle(official_train)
|
||||
|
||||
self._train = official_train[:len(official_train)*75//100]
|
||||
|
||||
if unofficial_dev:
|
||||
self._dev = official_train[len(official_train)*75//100:]
|
||||
else:
|
||||
self._dev = None
|
||||
|
||||
for example in self._train:
|
||||
if keep_details == 'dev_titles':
|
||||
del example['gold_titles']
|
||||
|
||||
test = []
|
||||
for raw_example in hf_official_dev:
|
||||
assert raw_example['level'] == 'hard'
|
||||
example = {k: raw_example[k] for k in ['id', 'question', 'answer', 'type', 'supporting_facts']}
|
||||
if 'supporting_facts' in example:
|
||||
example['gold_titles'] = set(example['supporting_facts']['title'])
|
||||
del example['supporting_facts']
|
||||
test.append(example)
|
||||
|
||||
self._test = test
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
from dsp.utils import dotdict
|
||||
|
||||
data_args = dotdict(train_seed=1, train_size=16, eval_seed=2023, dev_size=200*5, test_size=0)
|
||||
dataset = HotPotQA(**data_args)
|
||||
|
||||
print(dataset)
|
||||
print(dataset.train[0].question)
|
||||
print(dataset.train[15].question)
|
||||
|
||||
print(len(dataset.train), len(dataset.dev), len(dataset.test))
|
||||
|
||||
print(dataset.dev[0].question)
|
||||
print(dataset.dev[340].question)
|
||||
print(dataset.dev[937].question)
|
||||
|
||||
"""
|
||||
What was the population of the city where Woodward Avenue ends in 2010?
|
||||
Where did the star , who is also an executive producer, of the Mick begin her carrer?
|
||||
16 1000 0
|
||||
Both London and German have seen attacks during war, there was one specific type of attack that Germany called the blitz, what did London call a similar attack?
|
||||
Pre-Madonna was a collection of demos by the singer who was a leading presence during the emergence of what network?
|
||||
Alan Mills composed the classic folk song that tells the story of what?
|
||||
"""
|
||||
|
|
@ -1,65 +0,0 @@
|
|||
import dspy
|
||||
from dspy.evaluate.evaluate import Evaluate
|
||||
from dspy.primitives.example import Example
|
||||
from cognee.modules.data.extraction.knowledge_graph.extract_knowledge_graph_module import ExtractKnowledgeGraph
|
||||
from cognee.root_dir import get_absolute_path
|
||||
from cognee.shared.data_models import Answer
|
||||
from cognee.infrastructure.llm import get_llm_config
|
||||
from cognee.infrastructure.llm.get_llm_client import get_llm_client
|
||||
from cognee.modules.cognify.dataset import HotPotQA
|
||||
|
||||
def evaluate():
|
||||
dataset = HotPotQA(
|
||||
train_seed = 1,
|
||||
train_size = 16,
|
||||
eval_seed = 2023,
|
||||
dev_size = 8,
|
||||
test_size = 0,
|
||||
keep_details = True,
|
||||
)
|
||||
|
||||
#Evaluate
|
||||
evaluate_examples = [
|
||||
Example(
|
||||
base = None,
|
||||
question = None,
|
||||
context = "\r\n".join("".join(sentences) for sentences in example.context["sentences"]),
|
||||
answer = example.answer,
|
||||
) for example in dataset.dev
|
||||
]
|
||||
|
||||
devset = [example.with_inputs("context", "question") for example in evaluate_examples]
|
||||
|
||||
evaluate_on_hotpotqa = Evaluate(devset = devset, num_threads = 1, display_progress = True, display_table = 5, max_tokens = 4096)
|
||||
|
||||
llm_config = get_llm_config()
|
||||
gpt4 = dspy.OpenAI(model = llm_config.llm_model, api_key = llm_config.llm_api_key, model_type = "chat", max_tokens = 4096)
|
||||
compiled_extract_knowledge_graph = ExtractKnowledgeGraph(lm = gpt4)
|
||||
compiled_extract_knowledge_graph.load(get_absolute_path("./programs/extract_knowledge_graph/extract_knowledge_graph.json"))
|
||||
|
||||
def evaluate_answer(example, graph_prediction, trace = None):
|
||||
llm_client = get_llm_client()
|
||||
|
||||
try:
|
||||
answer_prediction = llm_client.create_structured_output(
|
||||
text_input = example.question,
|
||||
system_prompt = f"""Answer the question by looking at the provided knowledge graph.
|
||||
Use only the graph to answer the question and be very brief.
|
||||
This is the knowledge graph:
|
||||
{graph_prediction.graph.model_dump(mode = "json")}""",
|
||||
response_model = Answer,
|
||||
)
|
||||
except:
|
||||
return False
|
||||
|
||||
return dsp.answer_match(example.answer, [answer_prediction.answer], frac = 0.8) or \
|
||||
dsp.passage_match([example.answer], [answer_prediction.answer])
|
||||
|
||||
gpt4 = dspy.OpenAI(model = llm_config.llm_model, api_key = llm_config.llm_api_key, model_type = "chat", max_tokens = 4096)
|
||||
dspy.settings.configure(lm = gpt4)
|
||||
|
||||
evaluate_on_hotpotqa(compiled_extract_knowledge_graph, metric = evaluate_answer)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
evaluate()
|
||||
|
|
@ -1,89 +0,0 @@
|
|||
import dspy
|
||||
from cognee.modules.data.extraction.knowledge_graph.extract_knowledge_graph_module import ExtractKnowledgeGraph
|
||||
from cognee.root_dir import get_absolute_path
|
||||
from cognee.infrastructure.llm import get_llm_config
|
||||
|
||||
def run():
|
||||
llm_config = get_llm_config()
|
||||
gpt4 = dspy.OpenAI(model = llm_config.llm_model, api_key = llm_config.llm_api_key, model_type = "chat", max_tokens = 4096)
|
||||
compiled_extract_knowledge_graph = ExtractKnowledgeGraph(lm = gpt4)
|
||||
compiled_extract_knowledge_graph.load(get_absolute_path("./programs/extract_knowledge_graph/extract_knowledge_graph.json"))
|
||||
|
||||
text = """The 1985 FA Charity Shield (also known as the General Motors FA
|
||||
Charity Shield for sponsorship reasons) was the 63rd FA Charity Shield,
|
||||
an annual football match played between the winners of the previous
|
||||
season's First Division and FA Cup competitions. The match was played on
|
||||
10 August 1985 at Wembley Stadium and contested by Everton,
|
||||
who had won the 1984\u201385 First Division, and Manchester United,
|
||||
who had won the 1984\u201385 FA Cup. Everton won 2\u20130 with goals from
|
||||
Trevor Steven and Adrian Heath. Trevor Steven put Everton into the lead
|
||||
when he swept home from six yards after a cross from the left in the first half.
|
||||
The second goal came in the second half when Manchester United goalkeeper
|
||||
Gary Bailey dropped a cross from the left to allow Adrian Heath to tip the
|
||||
ball past him into the left corner of the net.\r\nThe 1995 FA Charity Shield
|
||||
(also known as the Littlewoods FA Charity Shield for sponsorship reasons) was the
|
||||
73rd FA Charity Shield, an annual football match played between the winners of
|
||||
the previous season's Premier League and FA Cup competitions. The match was
|
||||
played on 13 August 1995 at Wembley Stadium and contested by Blackburn Rovers,
|
||||
who had won the Premier League and FA Cup winners Everton. It was Blackburn's
|
||||
second successive Charity Shield appearance, while Everton were appearing in
|
||||
their eleventh and their first since 1987. Everton won the match 1\u20130
|
||||
with a goal from Vinny Samways when he caught Tim Flowers off his line and
|
||||
lifted the ball over him from the left of the penalty area and into the right
|
||||
corner of the net. Dave Watson lifted the trophy for Everton.\r\nThe 1972 FA
|
||||
Charity Shield was contested between Manchester City and Aston Villa.\r\nThe
|
||||
1997 FA Charity Shield (known as the Littlewoods FA Charity Shield for
|
||||
sponsorship reasons) was the 75th FA Charity Shield, an annual football match
|
||||
played between the winners of the previous season's Premier League and
|
||||
FA Cup competitions. The match was played on 3 August 1997 at Wembley Stadium
|
||||
and contested by Manchester United, who had won the 1996\u201397 FA Premier League,
|
||||
and Chelsea, who had won the 1996\u201397 FA Cup. Manchester United won the match
|
||||
4\u20132 on penalties after the match had finished at 1\u20131 after 90 minutes.
|
||||
\r\nThe 1956 FA Charity Shield was the 34th FA Charity Shield, an annual football
|
||||
match held between the winners of the previous season's Football League and
|
||||
FA Cup competitions. The match was contested by Manchester United, who had won
|
||||
the 1955\u201356 Football League, and Manchester City, who had won the
|
||||
1955\u201356 FA Cup, at Maine Road, Manchester, on 24 October 1956. Manchester
|
||||
United won the match 1\u20130, Dennis Viollet scoring the winning goal.
|
||||
Manchester United goalkeeper David Gaskell made his debut for the club during
|
||||
the game, taking the place of injured goalkeeper Ray Wood, and, at the age of
|
||||
16 years and 19 days, became the youngest player ever to play for the club.
|
||||
\r\nThe 1937 FA Charity Shield was the 24th FA Charity Shield, a football match
|
||||
between the winners of the previous season's First Division and FA Cup competitions.
|
||||
The match was contested by league champions Manchester City and FA Cup winners
|
||||
Sunderland, and was played at Maine Road, the home ground of Manchester City.
|
||||
Manchester City won the game, 2\u20130.\r\nThe 2000 FA Charity Shield (also known
|
||||
as the One 2 One FA Charity Shield for sponsorship reasons) was the
|
||||
78th FA Charity Shield, an annual football match played between the winners
|
||||
of the previous season's Premier League and FA Cup competitions. The match
|
||||
was played between Manchester United, who won the 1999\u20132000 Premier League,
|
||||
and Chelsea, who won the 1999\u20132000 FA Cup, and resulted in a 2\u20130 Chelsea win.
|
||||
The goals were scored by Jimmy Floyd Hasselbaink and Mario Melchiot. Roy Keane
|
||||
was sent off for a challenge on Gustavo Poyet and was the last person to be
|
||||
sent off at the old Wembley Stadium.\r\nThe 2001 FA Charity Shield (also known
|
||||
as the One 2 One FA Charity Shield for sponsorship reasons) was the 79th FA Charity Shield,
|
||||
an annual football match played between the winners of the previous season's
|
||||
Premier League and FA Cup. The match was contested between Liverpool, winners of
|
||||
the 2000\u201301 FA Cup and Manchester United, who won the 2000\u201301 Premier
|
||||
League on 12 August 2001. It was the first Shield match to be held at the
|
||||
Millennium Stadium following the closure of Wembley Stadium for reconstruction.
|
||||
\r\nAston Villa Football Club ( ; nicknamed Villa, The Villa, The Villans
|
||||
and The Lions) is a professional football club in Aston, Birmingham, that plays
|
||||
in the Championship, the second level of English football. Founded in 1874,
|
||||
they have played at their current home ground, Villa Park, since 1897. Aston Villa
|
||||
were one of the founder members of the Football League in 1888 and of the
|
||||
Premier League in 1992.\r\nThe 1996 FA Charity Shield (also known as the
|
||||
Littlewoods FA Charity Shield for sponsorship reasons) was the 74th FA Charity Shield,
|
||||
an annual football match played between the winners of the previous season's Premier
|
||||
League and FA Cup competitions. The match was played on 11 August 1996 at Wembley
|
||||
Stadium and contested by Manchester United, who had won the Double of Premier League
|
||||
and FA Cup in 1995\u201396, and Newcastle United, who had finished as runners-up
|
||||
in the Premier League. Manchester United won the match 4\u20130 with goals from
|
||||
Eric Cantona, Nicky Butt, David Beckham and Roy Keane."""
|
||||
|
||||
prediction = compiled_extract_knowledge_graph(context = text, question = "")
|
||||
|
||||
print(prediction.graph)
|
||||
|
||||
if __name__ == "__main__":
|
||||
run()
|
||||
|
|
@ -1,68 +0,0 @@
|
|||
import dspy
|
||||
from dspy.teleprompt import BootstrapFewShot
|
||||
from dspy.primitives.example import Example
|
||||
from cognee.modules.data.extraction.knowledge_graph.extract_knowledge_graph import ExtractKnowledgeGraph
|
||||
from cognee.root_dir import get_absolute_path
|
||||
from cognee.infrastructure.files.storage import LocalStorage
|
||||
from cognee.shared.data_models import Answer
|
||||
from cognee.infrastructure.llm.get_llm_client import get_llm_client
|
||||
from cognee.modules.cognify.dataset import HotPotQA
|
||||
from cognee.infrastructure.llm import get_llm_config
|
||||
|
||||
def train():
|
||||
colbertv2_wiki17_abstracts = dspy.ColBERTv2(url = "http://20.102.90.50:2017/wiki17_abstracts")
|
||||
|
||||
dspy.configure(rm = colbertv2_wiki17_abstracts)
|
||||
|
||||
def evaluate_answer(example, graph_prediction, trace = None):
|
||||
llm_client = get_llm_client()
|
||||
|
||||
try:
|
||||
answer_prediction = llm_client.create_structured_output(
|
||||
text_input = example.question,
|
||||
system_prompt = f"""Answer the question by looking at the provided knowledge graph.
|
||||
Use only the graph to answer the question and be very brief.
|
||||
This is the knowledge graph:
|
||||
{graph_prediction.graph.model_dump(mode = "json")}""",
|
||||
response_model = Answer,
|
||||
)
|
||||
except:
|
||||
return False
|
||||
|
||||
return dsp.answer_match(example.answer, [answer_prediction.answer], frac = 0.8) or \
|
||||
dsp.passage_match([example.answer], [answer_prediction.answer])
|
||||
|
||||
optimizer = BootstrapFewShot(metric = evaluate_answer)
|
||||
|
||||
dataset = HotPotQA(
|
||||
train_seed = 1,
|
||||
train_size = 16,
|
||||
eval_seed = 2023,
|
||||
dev_size = 8,
|
||||
test_size = 0,
|
||||
keep_details = True,
|
||||
)
|
||||
|
||||
# Train
|
||||
train_examples = [
|
||||
Example(
|
||||
base = None,
|
||||
question = example.question,
|
||||
context = "\r\n".join("".join(sentences) for sentences in example.context["sentences"]),
|
||||
answer = example.answer,
|
||||
) for example in dataset.train
|
||||
]
|
||||
|
||||
trainset = [example.with_inputs("context", "question") for example in train_examples]
|
||||
|
||||
llm_config = get_llm_config()
|
||||
gpt4 = dspy.OpenAI(model = llm_config.llm_model, api_key = llm_config.llm_api_key, model_type = "chat", max_tokens = 4096)
|
||||
|
||||
compiled_extract_knowledge_graph = optimizer.compile(ExtractKnowledgeGraph(lm = gpt4), trainset = trainset)
|
||||
|
||||
# Save program
|
||||
LocalStorage.ensure_directory_exists(get_absolute_path("./programs/extract_knowledge_graph"))
|
||||
compiled_extract_knowledge_graph.save(get_absolute_path("./programs/extract_knowledge_graph/extract_knowledge_graph.json"))
|
||||
|
||||
if __name__ == "__main__":
|
||||
train()
|
||||
35
cognee/modules/graph/cognee_graph/CogneeAbstractGraph.py
Normal file
35
cognee/modules/graph/cognee_graph/CogneeAbstractGraph.py
Normal file
|
|
@ -0,0 +1,35 @@
|
|||
from abc import ABC, abstractmethod
|
||||
from typing import List, Dict, Union
|
||||
from cognee.modules.graph.cognee_graph.CogneeGraphElements import Node, Edge
|
||||
from cognee.infrastructure.databases.graph.graph_db_interface import GraphDBInterface
|
||||
|
||||
class CogneeAbstractGraph(ABC):
|
||||
"""
|
||||
Abstract base class for representing a graph structure.
|
||||
|
||||
"""
|
||||
|
||||
@abstractmethod
|
||||
def add_node(self, node: Node) -> None:
|
||||
"""Add a node to the graph."""
|
||||
pass
|
||||
|
||||
@abstractmethod
|
||||
def add_edge(self, edge: Edge) -> None:
|
||||
"""Add an edge to the graph."""
|
||||
pass
|
||||
|
||||
@abstractmethod
|
||||
def get_node(self, node_id: str) -> Node:
|
||||
"""Retrieve a node by its ID."""
|
||||
pass
|
||||
|
||||
@abstractmethod
|
||||
def get_edges(self, node_id: str) -> List[Edge]:
|
||||
"""Retrieve edges connected to a specific node."""
|
||||
pass
|
||||
|
||||
@abstractmethod
|
||||
async def project_graph_from_db(self, adapter: GraphDBInterface, directed: bool, dimension: int) -> None:
|
||||
"""Project the graph structure from a database using the provided adapter."""
|
||||
pass
|
||||
91
cognee/modules/graph/cognee_graph/CogneeGraph.py
Normal file
91
cognee/modules/graph/cognee_graph/CogneeGraph.py
Normal file
|
|
@ -0,0 +1,91 @@
|
|||
from typing import List, Dict, Union
|
||||
|
||||
from cognee.infrastructure.databases.graph.graph_db_interface import GraphDBInterface
|
||||
from cognee.modules.graph.cognee_graph.CogneeGraphElements import Node, Edge
|
||||
from cognee.modules.graph.cognee_graph.CogneeAbstractGraph import CogneeAbstractGraph
|
||||
from cognee.infrastructure.databases.graph import get_graph_engine
|
||||
|
||||
class CogneeGraph(CogneeAbstractGraph):
|
||||
"""
|
||||
Concrete implementation of the AbstractGraph class for Cognee.
|
||||
|
||||
This class provides the functionality to manage nodes and edges,
|
||||
and project a graph from a database using adapters.
|
||||
"""
|
||||
|
||||
nodes: Dict[str, Node]
|
||||
edges: List[Edge]
|
||||
directed: bool
|
||||
|
||||
def __init__(self, directed: bool = True):
|
||||
self.nodes = {}
|
||||
self.edges = []
|
||||
self.directed = directed
|
||||
|
||||
def add_node(self, node: Node) -> None:
|
||||
if node.id not in self.nodes:
|
||||
self.nodes[node.id] = node
|
||||
else:
|
||||
raise ValueError(f"Node with id {node.id} already exists.")
|
||||
|
||||
def add_edge(self, edge: Edge) -> None:
|
||||
if edge not in self.edges:
|
||||
self.edges.append(edge)
|
||||
edge.node1.add_skeleton_edge(edge)
|
||||
edge.node2.add_skeleton_edge(edge)
|
||||
else:
|
||||
raise ValueError(f"Edge {edge} already exists in the graph.")
|
||||
|
||||
def get_node(self, node_id: str) -> Node:
|
||||
return self.nodes.get(node_id, None)
|
||||
|
||||
def get_edges(self, node_id: str) -> List[Edge]:
|
||||
node = self.get_node(node_id)
|
||||
if node:
|
||||
return node.skeleton_edges
|
||||
else:
|
||||
raise ValueError(f"Node with id {node_id} does not exist.")
|
||||
|
||||
async def project_graph_from_db(self,
|
||||
adapter: Union[GraphDBInterface],
|
||||
node_properties_to_project: List[str],
|
||||
edge_properties_to_project: List[str],
|
||||
directed = True,
|
||||
node_dimension = 1,
|
||||
edge_dimension = 1) -> None:
|
||||
|
||||
if node_dimension < 1 or edge_dimension < 1:
|
||||
raise ValueError("Dimensions must be positive integers")
|
||||
|
||||
try:
|
||||
nodes_data, edges_data = await adapter.get_graph_data()
|
||||
|
||||
if not nodes_data:
|
||||
raise ValueError("No node data retrieved from the database.")
|
||||
if not edges_data:
|
||||
raise ValueError("No edge data retrieved from the database.")
|
||||
|
||||
for node_id, properties in nodes_data:
|
||||
node_attributes = {key: properties.get(key) for key in node_properties_to_project}
|
||||
self.add_node(Node(str(node_id), node_attributes, dimension=node_dimension))
|
||||
|
||||
for source_id, target_id, relationship_type, properties in edges_data:
|
||||
source_node = self.get_node(str(source_id))
|
||||
target_node = self.get_node(str(target_id))
|
||||
if source_node and target_node:
|
||||
edge_attributes = {key: properties.get(key) for key in edge_properties_to_project}
|
||||
edge_attributes['relationship_type'] = relationship_type
|
||||
|
||||
edge = Edge(source_node, target_node, attributes=edge_attributes, directed=directed, dimension=edge_dimension)
|
||||
self.add_edge(edge)
|
||||
|
||||
source_node.add_skeleton_edge(edge)
|
||||
target_node.add_skeleton_edge(edge)
|
||||
|
||||
else:
|
||||
raise ValueError(f"Edge references nonexistent nodes: {source_id} -> {target_id}")
|
||||
|
||||
except (ValueError, TypeError) as e:
|
||||
print(f"Error projecting graph: {e}")
|
||||
except Exception as ex:
|
||||
print(f"Unexpected error: {ex}")
|
||||
114
cognee/modules/graph/cognee_graph/CogneeGraphElements.py
Normal file
114
cognee/modules/graph/cognee_graph/CogneeGraphElements.py
Normal file
|
|
@ -0,0 +1,114 @@
|
|||
import numpy as np
|
||||
from typing import List, Dict, Optional, Any
|
||||
|
||||
class Node:
|
||||
"""
|
||||
Represents a node in a graph.
|
||||
Attributes:
|
||||
id (str): A unique identifier for the node.
|
||||
attributes (Dict[str, Any]): A dictionary of attributes associated with the node.
|
||||
neighbors (List[Node]): Represents the original nodes
|
||||
skeleton_edges (List[Edge]): Represents the original edges
|
||||
"""
|
||||
id: str
|
||||
attributes: Dict[str, Any]
|
||||
skeleton_neighbours: List["Node"]
|
||||
skeleton_edges: List["Edge"]
|
||||
status: np.ndarray
|
||||
|
||||
def __init__(self, node_id: str, attributes: Optional[Dict[str, Any]] = None, dimension: int = 1):
|
||||
if dimension <= 0:
|
||||
raise ValueError("Dimension must be a positive integer")
|
||||
self.id = node_id
|
||||
self.attributes = attributes if attributes is not None else {}
|
||||
self.skeleton_neighbours = []
|
||||
self.skeleton_edges = []
|
||||
self.status = np.ones(dimension, dtype=int)
|
||||
|
||||
def add_skeleton_neighbor(self, neighbor: "Node") -> None:
|
||||
if neighbor not in self.skeleton_neighbours:
|
||||
self.skeleton_neighbours.append(neighbor)
|
||||
|
||||
def remove_skeleton_neighbor(self, neighbor: "Node") -> None:
|
||||
if neighbor in self.skeleton_neighbours:
|
||||
self.skeleton_neighbours.remove(neighbor)
|
||||
|
||||
def add_skeleton_edge(self, edge: "Edge") -> None:
|
||||
if edge not in self.skeleton_edges:
|
||||
self.skeleton_edges.append(edge)
|
||||
# Add neighbor
|
||||
if edge.node1 == self:
|
||||
self.add_skeleton_neighbor(edge.node2)
|
||||
elif edge.node2 == self:
|
||||
self.add_skeleton_neighbor(edge.node1)
|
||||
|
||||
def remove_skeleton_edge(self, edge: "Edge") -> None:
|
||||
if edge in self.skeleton_edges:
|
||||
self.skeleton_edges.remove(edge)
|
||||
# Remove neighbor if no other edge connects them
|
||||
neighbor = edge.node2 if edge.node1 == self else edge.node1
|
||||
if all(e.node1 != neighbor and e.node2 != neighbor for e in self.skeleton_edges):
|
||||
self.remove_skeleton_neighbor(neighbor)
|
||||
|
||||
def is_node_alive_in_dimension(self, dimension: int) -> bool:
|
||||
if dimension < 0 or dimension >= len(self.status):
|
||||
raise ValueError(f"Dimension {dimension} is out of range. Valid range is 0 to {len(self.status) - 1}.")
|
||||
return self.status[dimension] == 1
|
||||
|
||||
def __repr__(self) -> str:
|
||||
return f"Node({self.id}, attributes={self.attributes})"
|
||||
|
||||
def __hash__(self) -> int:
|
||||
return hash(self.id)
|
||||
|
||||
def __eq__(self, other: "Node") -> bool:
|
||||
return isinstance(other, Node) and self.id == other.id
|
||||
|
||||
|
||||
class Edge:
|
||||
"""
|
||||
Represents an edge in a graph, connecting two nodes.
|
||||
Attributes:
|
||||
node1 (Node): The starting node of the edge.
|
||||
node2 (Node): The ending node of the edge.
|
||||
attributes (Dict[str, Any]): A dictionary of attributes associated with the edge.
|
||||
directed (bool): A flag indicating whether the edge is directed or undirected.
|
||||
"""
|
||||
|
||||
node1: "Node"
|
||||
node2: "Node"
|
||||
attributes: Dict[str, Any]
|
||||
directed: bool
|
||||
status: np.ndarray
|
||||
|
||||
def __init__(self, node1: "Node", node2: "Node", attributes: Optional[Dict[str, Any]] = None, directed: bool = True, dimension: int = 1):
|
||||
if dimension <= 0:
|
||||
raise ValueError("Dimensions must be a positive integer.")
|
||||
self.node1 = node1
|
||||
self.node2 = node2
|
||||
self.attributes = attributes if attributes is not None else {}
|
||||
self.directed = directed
|
||||
self.status = np.ones(dimension, dtype=int)
|
||||
|
||||
def is_edge_alive_in_dimension(self, dimension: int) -> bool:
|
||||
if dimension < 0 or dimension >= len(self.status):
|
||||
raise ValueError(f"Dimension {dimension} is out of range. Valid range is 0 to {len(self.status) - 1}.")
|
||||
return self.status[dimension] == 1
|
||||
|
||||
def __repr__(self) -> str:
|
||||
direction = "->" if self.directed else "--"
|
||||
return f"Edge({self.node1.id} {direction} {self.node2.id}, attributes={self.attributes})"
|
||||
|
||||
def __hash__(self) -> int:
|
||||
if self.directed:
|
||||
return hash((self.node1, self.node2))
|
||||
else:
|
||||
return hash(frozenset({self.node1, self.node2}))
|
||||
|
||||
def __eq__(self, other: "Edge") -> bool:
|
||||
if not isinstance(other, Edge):
|
||||
return False
|
||||
if self.directed:
|
||||
return self.node1 == other.node1 and self.node2 == other.node2
|
||||
else:
|
||||
return {self.node1, self.node2} == {other.node1, other.node2}
|
||||
0
cognee/modules/graph/cognee_graph/__init__.py
Normal file
0
cognee/modules/graph/cognee_graph/__init__.py
Normal file
|
|
@ -28,7 +28,7 @@ class Class(DataPoint):
|
|||
description: str
|
||||
constructor_parameters: List[Variable]
|
||||
extended_from_class: Optional["Class"] = None
|
||||
has_methods: list["Function"]
|
||||
has_methods: List["Function"]
|
||||
|
||||
_metadata = {
|
||||
"index_fields": ["name"]
|
||||
|
|
@ -89,7 +89,8 @@ class SourceCodeGraph(DataPoint):
|
|||
Operator,
|
||||
Expression,
|
||||
]]
|
||||
|
||||
Class.model_rebuild()
|
||||
ClassInstance.model_rebuild()
|
||||
Expression.model_rebuild()
|
||||
FunctionCall.model_rebuild()
|
||||
SourceCodeGraph.model_rebuild()
|
||||
|
|
|
|||
144
cognee/tests/unit/modules/graph/cognee_graph_elements_test.py
Normal file
144
cognee/tests/unit/modules/graph/cognee_graph_elements_test.py
Normal file
|
|
@ -0,0 +1,144 @@
|
|||
import pytest
|
||||
import numpy as np
|
||||
|
||||
from cognee.modules.graph.cognee_graph.CogneeGraphElements import Node, Edge
|
||||
|
||||
|
||||
def test_node_initialization():
|
||||
"""Test that a Node is initialized correctly."""
|
||||
node = Node("node1", {"attr1": "value1"}, dimension=2)
|
||||
assert node.id == "node1"
|
||||
assert node.attributes == {"attr1": "value1"}
|
||||
assert len(node.status) == 2
|
||||
assert np.all(node.status == 1)
|
||||
|
||||
def test_node_invalid_dimension():
|
||||
"""Test that initializing a Node with a non-positive dimension raises an error."""
|
||||
with pytest.raises(ValueError, match="Dimension must be a positive integer"):
|
||||
Node("node1", dimension=0)
|
||||
|
||||
def test_add_skeleton_neighbor():
|
||||
"""Test adding a neighbor to a node."""
|
||||
node1 = Node("node1")
|
||||
node2 = Node("node2")
|
||||
node1.add_skeleton_neighbor(node2)
|
||||
assert node2 in node1.skeleton_neighbours
|
||||
|
||||
def test_remove_skeleton_neighbor():
|
||||
"""Test removing a neighbor from a node."""
|
||||
node1 = Node("node1")
|
||||
node2 = Node("node2")
|
||||
node1.add_skeleton_neighbor(node2)
|
||||
node1.remove_skeleton_neighbor(node2)
|
||||
assert node2 not in node1.skeleton_neighbours
|
||||
|
||||
def test_add_skeleton_edge():
|
||||
"""Test adding an edge updates both skeleton_edges and skeleton_neighbours."""
|
||||
node1 = Node("node1")
|
||||
node2 = Node("node2")
|
||||
edge = Edge(node1, node2)
|
||||
node1.add_skeleton_edge(edge)
|
||||
assert edge in node1.skeleton_edges
|
||||
assert node2 in node1.skeleton_neighbours
|
||||
|
||||
def test_remove_skeleton_edge():
|
||||
"""Test removing an edge updates both skeleton_edges and skeleton_neighbours."""
|
||||
node1 = Node("node1")
|
||||
node2 = Node("node2")
|
||||
edge = Edge(node1, node2)
|
||||
node1.add_skeleton_edge(edge)
|
||||
node1.remove_skeleton_edge(edge)
|
||||
assert edge not in node1.skeleton_edges
|
||||
assert node2 not in node1.skeleton_neighbours
|
||||
|
||||
def test_is_node_alive_in_dimension():
|
||||
"""Test checking node's alive status in a specific dimension."""
|
||||
node = Node("node1", dimension=2)
|
||||
assert node.is_node_alive_in_dimension(1)
|
||||
node.status[1] = 0
|
||||
assert not node.is_node_alive_in_dimension(1)
|
||||
|
||||
def test_node_alive_invalid_dimension():
|
||||
"""Test that checking alive status with an invalid dimension raises an error."""
|
||||
node = Node("node1", dimension=1)
|
||||
with pytest.raises(ValueError, match="Dimension 1 is out of range"):
|
||||
node.is_node_alive_in_dimension(1)
|
||||
|
||||
def test_node_equality():
|
||||
"""Test equality between nodes."""
|
||||
node1 = Node("node1")
|
||||
node2 = Node("node1")
|
||||
assert node1 == node2
|
||||
|
||||
def test_node_hash():
|
||||
"""Test hashing for Node."""
|
||||
node = Node("node1")
|
||||
assert hash(node) == hash("node1")
|
||||
|
||||
### Tests for Edge ###
|
||||
|
||||
def test_edge_initialization():
|
||||
"""Test that an Edge is initialized correctly."""
|
||||
node1 = Node("node1")
|
||||
node2 = Node("node2")
|
||||
edge = Edge(node1, node2, {"weight": 10}, directed=False, dimension=2)
|
||||
assert edge.node1 == node1
|
||||
assert edge.node2 == node2
|
||||
assert edge.attributes == {"weight": 10}
|
||||
assert edge.directed is False
|
||||
assert len(edge.status) == 2
|
||||
assert np.all(edge.status == 1)
|
||||
|
||||
def test_edge_invalid_dimension():
|
||||
"""Test that initializing an Edge with a non-positive dimension raises an error."""
|
||||
node1 = Node("node1")
|
||||
node2 = Node("node2")
|
||||
with pytest.raises(ValueError, match="Dimensions must be a positive integer."):
|
||||
Edge(node1, node2, dimension=0)
|
||||
|
||||
def test_is_edge_alive_in_dimension():
|
||||
"""Test checking edge's alive status in a specific dimension."""
|
||||
node1 = Node("node1")
|
||||
node2 = Node("node2")
|
||||
edge = Edge(node1, node2, dimension=2)
|
||||
assert edge.is_edge_alive_in_dimension(1)
|
||||
edge.status[1] = 0
|
||||
assert not edge.is_edge_alive_in_dimension(1)
|
||||
|
||||
def test_edge_alive_invalid_dimension():
|
||||
"""Test that checking alive status with an invalid dimension raises an error."""
|
||||
node1 = Node("node1")
|
||||
node2 = Node("node2")
|
||||
edge = Edge(node1, node2, dimension=1)
|
||||
with pytest.raises(ValueError, match="Dimension 1 is out of range"):
|
||||
edge.is_edge_alive_in_dimension(1)
|
||||
|
||||
def test_edge_equality_directed():
|
||||
"""Test equality between directed edges."""
|
||||
node1 = Node("node1")
|
||||
node2 = Node("node2")
|
||||
edge1 = Edge(node1, node2, directed=True)
|
||||
edge2 = Edge(node1, node2, directed=True)
|
||||
assert edge1 == edge2
|
||||
|
||||
def test_edge_equality_undirected():
|
||||
"""Test equality between undirected edges."""
|
||||
node1 = Node("node1")
|
||||
node2 = Node("node2")
|
||||
edge1 = Edge(node1, node2, directed=False)
|
||||
edge2 = Edge(node2, node1, directed=False)
|
||||
assert edge1 == edge2
|
||||
|
||||
def test_edge_hash_directed():
|
||||
"""Test hashing for directed edges."""
|
||||
node1 = Node("node1")
|
||||
node2 = Node("node2")
|
||||
edge = Edge(node1, node2, directed=True)
|
||||
assert hash(edge) == hash((node1, node2))
|
||||
|
||||
def test_edge_hash_undirected():
|
||||
"""Test hashing for undirected edges."""
|
||||
node1 = Node("node1")
|
||||
node2 = Node("node2")
|
||||
edge = Edge(node1, node2, directed=False)
|
||||
assert hash(edge) == hash(frozenset({node1, node2}))
|
||||
79
cognee/tests/unit/modules/graph/cognee_graph_test.py
Normal file
79
cognee/tests/unit/modules/graph/cognee_graph_test.py
Normal file
|
|
@ -0,0 +1,79 @@
|
|||
import pytest
|
||||
|
||||
from cognee.modules.graph.cognee_graph.CogneeGraphElements import Node, Edge
|
||||
from cognee.modules.graph.cognee_graph.CogneeGraph import CogneeGraph
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def setup_graph():
|
||||
"""Fixture to initialize a CogneeGraph instance."""
|
||||
return CogneeGraph()
|
||||
|
||||
def test_add_node_success(setup_graph):
|
||||
"""Test successful addition of a node."""
|
||||
graph = setup_graph
|
||||
node = Node("node1")
|
||||
graph.add_node(node)
|
||||
assert graph.get_node("node1") == node
|
||||
|
||||
def test_add_duplicate_node(setup_graph):
|
||||
"""Test adding a duplicate node raises an exception."""
|
||||
graph = setup_graph
|
||||
node = Node("node1")
|
||||
graph.add_node(node)
|
||||
with pytest.raises(ValueError, match="Node with id node1 already exists."):
|
||||
graph.add_node(node)
|
||||
|
||||
def test_add_edge_success(setup_graph):
|
||||
"""Test successful addition of an edge."""
|
||||
graph = setup_graph
|
||||
node1 = Node("node1")
|
||||
node2 = Node("node2")
|
||||
graph.add_node(node1)
|
||||
graph.add_node(node2)
|
||||
edge = Edge(node1, node2)
|
||||
graph.add_edge(edge)
|
||||
assert edge in graph.edges
|
||||
assert edge in node1.skeleton_edges
|
||||
assert edge in node2.skeleton_edges
|
||||
|
||||
def test_add_duplicate_edge(setup_graph):
|
||||
"""Test adding a duplicate edge raises an exception."""
|
||||
graph = setup_graph
|
||||
node1 = Node("node1")
|
||||
node2 = Node("node2")
|
||||
graph.add_node(node1)
|
||||
graph.add_node(node2)
|
||||
edge = Edge(node1, node2)
|
||||
graph.add_edge(edge)
|
||||
with pytest.raises(ValueError, match="Edge .* already exists in the graph."):
|
||||
graph.add_edge(edge)
|
||||
|
||||
def test_get_node_success(setup_graph):
|
||||
"""Test retrieving an existing node."""
|
||||
graph = setup_graph
|
||||
node = Node("node1")
|
||||
graph.add_node(node)
|
||||
assert graph.get_node("node1") == node
|
||||
|
||||
def test_get_node_nonexistent(setup_graph):
|
||||
"""Test retrieving a nonexistent node returns None."""
|
||||
graph = setup_graph
|
||||
assert graph.get_node("nonexistent") is None
|
||||
|
||||
def test_get_edges_success(setup_graph):
|
||||
"""Test retrieving edges of a node."""
|
||||
graph = setup_graph
|
||||
node1 = Node("node1")
|
||||
node2 = Node("node2")
|
||||
graph.add_node(node1)
|
||||
graph.add_node(node2)
|
||||
edge = Edge(node1, node2)
|
||||
graph.add_edge(edge)
|
||||
assert edge in graph.get_edges("node1")
|
||||
|
||||
def test_get_edges_nonexistent_node(setup_graph):
|
||||
"""Test retrieving edges for a nonexistent node raises an exception."""
|
||||
graph = setup_graph
|
||||
with pytest.raises(ValueError, match="Node with id nonexistent does not exist."):
|
||||
graph.get_edges("nonexistent")
|
||||
229
examples/python/dynamic_steps_example.py
Normal file
229
examples/python/dynamic_steps_example.py
Normal file
|
|
@ -0,0 +1,229 @@
|
|||
import cognee
|
||||
import asyncio
|
||||
from cognee.api.v1.search import SearchType
|
||||
|
||||
job_position = """0:Senior Data Scientist (Machine Learning)
|
||||
|
||||
Company: TechNova Solutions
|
||||
Location: San Francisco, CA
|
||||
|
||||
Job Description:
|
||||
|
||||
TechNova Solutions is seeking a Senior Data Scientist specializing in Machine Learning to join our dynamic analytics team. The ideal candidate will have a strong background in developing and deploying machine learning models, working with large datasets, and translating complex data into actionable insights.
|
||||
|
||||
Responsibilities:
|
||||
|
||||
Develop and implement advanced machine learning algorithms and models.
|
||||
Analyze large, complex datasets to extract meaningful patterns and insights.
|
||||
Collaborate with cross-functional teams to integrate predictive models into products.
|
||||
Stay updated with the latest advancements in machine learning and data science.
|
||||
Mentor junior data scientists and provide technical guidance.
|
||||
Qualifications:
|
||||
|
||||
Master’s or Ph.D. in Data Science, Computer Science, Statistics, or a related field.
|
||||
5+ years of experience in data science and machine learning.
|
||||
Proficient in Python, R, and SQL.
|
||||
Experience with deep learning frameworks (e.g., TensorFlow, PyTorch).
|
||||
Strong problem-solving skills and attention to detail.
|
||||
Candidate CVs
|
||||
"""
|
||||
|
||||
job_1 = """
|
||||
CV 1: Relevant
|
||||
Name: Dr. Emily Carter
|
||||
Contact Information:
|
||||
|
||||
Email: emily.carter@example.com
|
||||
Phone: (555) 123-4567
|
||||
Summary:
|
||||
|
||||
Senior Data Scientist with over 8 years of experience in machine learning and predictive analytics. Expertise in developing advanced algorithms and deploying scalable models in production environments.
|
||||
|
||||
Education:
|
||||
|
||||
Ph.D. in Computer Science, Stanford University (2014)
|
||||
B.S. in Mathematics, University of California, Berkeley (2010)
|
||||
Experience:
|
||||
|
||||
Senior Data Scientist, InnovateAI Labs (2016 – Present)
|
||||
Led a team in developing machine learning models for natural language processing applications.
|
||||
Implemented deep learning algorithms that improved prediction accuracy by 25%.
|
||||
Collaborated with cross-functional teams to integrate models into cloud-based platforms.
|
||||
Data Scientist, DataWave Analytics (2014 – 2016)
|
||||
Developed predictive models for customer segmentation and churn analysis.
|
||||
Analyzed large datasets using Hadoop and Spark frameworks.
|
||||
Skills:
|
||||
|
||||
Programming Languages: Python, R, SQL
|
||||
Machine Learning: TensorFlow, Keras, Scikit-Learn
|
||||
Big Data Technologies: Hadoop, Spark
|
||||
Data Visualization: Tableau, Matplotlib
|
||||
"""
|
||||
|
||||
job_2 = """
|
||||
CV 2: Relevant
|
||||
Name: Michael Rodriguez
|
||||
Contact Information:
|
||||
|
||||
Email: michael.rodriguez@example.com
|
||||
Phone: (555) 234-5678
|
||||
Summary:
|
||||
|
||||
Data Scientist with a strong background in machine learning and statistical modeling. Skilled in handling large datasets and translating data into actionable business insights.
|
||||
|
||||
Education:
|
||||
|
||||
M.S. in Data Science, Carnegie Mellon University (2013)
|
||||
B.S. in Computer Science, University of Michigan (2011)
|
||||
Experience:
|
||||
|
||||
Senior Data Scientist, Alpha Analytics (2017 – Present)
|
||||
Developed machine learning models to optimize marketing strategies.
|
||||
Reduced customer acquisition cost by 15% through predictive modeling.
|
||||
Data Scientist, TechInsights (2013 – 2017)
|
||||
Analyzed user behavior data to improve product features.
|
||||
Implemented A/B testing frameworks to evaluate product changes.
|
||||
Skills:
|
||||
|
||||
Programming Languages: Python, Java, SQL
|
||||
Machine Learning: Scikit-Learn, XGBoost
|
||||
Data Visualization: Seaborn, Plotly
|
||||
Databases: MySQL, MongoDB
|
||||
"""
|
||||
|
||||
|
||||
job_3 = """
|
||||
CV 3: Relevant
|
||||
Name: Sarah Nguyen
|
||||
Contact Information:
|
||||
|
||||
Email: sarah.nguyen@example.com
|
||||
Phone: (555) 345-6789
|
||||
Summary:
|
||||
|
||||
Data Scientist specializing in machine learning with 6 years of experience. Passionate about leveraging data to drive business solutions and improve product performance.
|
||||
|
||||
Education:
|
||||
|
||||
M.S. in Statistics, University of Washington (2014)
|
||||
B.S. in Applied Mathematics, University of Texas at Austin (2012)
|
||||
Experience:
|
||||
|
||||
Data Scientist, QuantumTech (2016 – Present)
|
||||
Designed and implemented machine learning algorithms for financial forecasting.
|
||||
Improved model efficiency by 20% through algorithm optimization.
|
||||
Junior Data Scientist, DataCore Solutions (2014 – 2016)
|
||||
Assisted in developing predictive models for supply chain optimization.
|
||||
Conducted data cleaning and preprocessing on large datasets.
|
||||
Skills:
|
||||
|
||||
Programming Languages: Python, R
|
||||
Machine Learning Frameworks: PyTorch, Scikit-Learn
|
||||
Statistical Analysis: SAS, SPSS
|
||||
Cloud Platforms: AWS, Azure
|
||||
"""
|
||||
|
||||
|
||||
job_4 = """
|
||||
CV 4: Not Relevant
|
||||
Name: David Thompson
|
||||
Contact Information:
|
||||
|
||||
Email: david.thompson@example.com
|
||||
Phone: (555) 456-7890
|
||||
Summary:
|
||||
|
||||
Creative Graphic Designer with over 8 years of experience in visual design and branding. Proficient in Adobe Creative Suite and passionate about creating compelling visuals.
|
||||
|
||||
Education:
|
||||
|
||||
B.F.A. in Graphic Design, Rhode Island School of Design (2012)
|
||||
Experience:
|
||||
|
||||
Senior Graphic Designer, CreativeWorks Agency (2015 – Present)
|
||||
Led design projects for clients in various industries.
|
||||
Created branding materials that increased client engagement by 30%.
|
||||
Graphic Designer, Visual Innovations (2012 – 2015)
|
||||
Designed marketing collateral, including brochures, logos, and websites.
|
||||
Collaborated with the marketing team to develop cohesive brand strategies.
|
||||
Skills:
|
||||
|
||||
Design Software: Adobe Photoshop, Illustrator, InDesign
|
||||
Web Design: HTML, CSS
|
||||
Specialties: Branding and Identity, Typography
|
||||
"""
|
||||
|
||||
|
||||
job_5 = """
|
||||
CV 5: Not Relevant
|
||||
Name: Jessica Miller
|
||||
Contact Information:
|
||||
|
||||
Email: jessica.miller@example.com
|
||||
Phone: (555) 567-8901
|
||||
Summary:
|
||||
|
||||
Experienced Sales Manager with a strong track record in driving sales growth and building high-performing teams. Excellent communication and leadership skills.
|
||||
|
||||
Education:
|
||||
|
||||
B.A. in Business Administration, University of Southern California (2010)
|
||||
Experience:
|
||||
|
||||
Sales Manager, Global Enterprises (2015 – Present)
|
||||
Managed a sales team of 15 members, achieving a 20% increase in annual revenue.
|
||||
Developed sales strategies that expanded customer base by 25%.
|
||||
Sales Representative, Market Leaders Inc. (2010 – 2015)
|
||||
Consistently exceeded sales targets and received the 'Top Salesperson' award in 2013.
|
||||
Skills:
|
||||
|
||||
Sales Strategy and Planning
|
||||
Team Leadership and Development
|
||||
CRM Software: Salesforce, Zoho
|
||||
Negotiation and Relationship Building
|
||||
"""
|
||||
|
||||
async def main(enable_steps):
|
||||
# Step 1: Reset data and system state
|
||||
if enable_steps.get("prune_data"):
|
||||
await cognee.prune.prune_data()
|
||||
print("Data pruned.")
|
||||
|
||||
if enable_steps.get("prune_system"):
|
||||
await cognee.prune.prune_system(metadata=True)
|
||||
print("System pruned.")
|
||||
|
||||
# Step 2: Add text
|
||||
if enable_steps.get("add_text"):
|
||||
text_list = [job_position, job_1, job_2, job_3, job_4, job_5]
|
||||
for text in text_list:
|
||||
await cognee.add(text)
|
||||
print(f"Added text: {text[:35]}...")
|
||||
|
||||
# Step 3: Create knowledge graph
|
||||
if enable_steps.get("cognify"):
|
||||
await cognee.cognify()
|
||||
print("Knowledge graph created.")
|
||||
|
||||
# Step 4: Query insights
|
||||
if enable_steps.get("search_insights"):
|
||||
search_results = await cognee.search(
|
||||
SearchType.INSIGHTS,
|
||||
{'query': 'Which applicant has the most relevant experience in data science?'}
|
||||
)
|
||||
print("Search results:")
|
||||
for result_text in search_results:
|
||||
print(result_text)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
# Flags to enable/disable steps
|
||||
steps_to_enable = {
|
||||
"prune_data": True,
|
||||
"prune_system": True,
|
||||
"add_text": True,
|
||||
"cognify": True,
|
||||
"search_insights": True
|
||||
}
|
||||
|
||||
asyncio.run(main(steps_to_enable))
|
||||
236
poetry.lock
generated
236
poetry.lock
generated
|
|
@ -876,23 +876,6 @@ files = [
|
|||
{file = "colorama-0.4.6.tar.gz", hash = "sha256:08695f5cb7ed6e0531a20572697297273c47b8cae5a63ffc6d6ed5c201be6e44"},
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "colorlog"
|
||||
version = "6.9.0"
|
||||
description = "Add colours to the output of Python's logging module."
|
||||
optional = false
|
||||
python-versions = ">=3.6"
|
||||
files = [
|
||||
{file = "colorlog-6.9.0-py3-none-any.whl", hash = "sha256:5906e71acd67cb07a71e779c47c4bcb45fb8c2993eebe9e5adcd6a6f1b283eff"},
|
||||
{file = "colorlog-6.9.0.tar.gz", hash = "sha256:bfba54a1b93b94f54e1f4fe48395725a3d92fd2a4af702f6bd70946bdc0c6ac2"},
|
||||
]
|
||||
|
||||
[package.dependencies]
|
||||
colorama = {version = "*", markers = "sys_platform == \"win32\""}
|
||||
|
||||
[package.extras]
|
||||
development = ["black", "flake8", "mypy", "pytest", "types-colorama"]
|
||||
|
||||
[[package]]
|
||||
name = "comm"
|
||||
version = "0.2.2"
|
||||
|
|
@ -1292,17 +1275,6 @@ files = [
|
|||
graph = ["objgraph (>=1.7.2)"]
|
||||
profile = ["gprof2dot (>=2022.7.29)"]
|
||||
|
||||
[[package]]
|
||||
name = "diskcache"
|
||||
version = "5.6.3"
|
||||
description = "Disk Cache -- Disk and file backed persistent cache."
|
||||
optional = false
|
||||
python-versions = ">=3"
|
||||
files = [
|
||||
{file = "diskcache-5.6.3-py3-none-any.whl", hash = "sha256:5e31b2d5fbad117cc363ebaf6b689474db18a1f6438bc82358b024abd4c2ca19"},
|
||||
{file = "diskcache-5.6.3.tar.gz", hash = "sha256:2c3a3fa2743d8535d832ec61c2054a1641f41775aa7c556758a109941e33e4fc"},
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "distro"
|
||||
version = "1.9.0"
|
||||
|
|
@ -1414,55 +1386,6 @@ files = [
|
|||
{file = "docstring_parser-0.16.tar.gz", hash = "sha256:538beabd0af1e2db0146b6bd3caa526c35a34d61af9fd2887f3a8a27a739aa6e"},
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "dspy"
|
||||
version = "2.5.25"
|
||||
description = "DSPy"
|
||||
optional = false
|
||||
python-versions = ">=3.9"
|
||||
files = [
|
||||
{file = "dspy-2.5.25-py3-none-any.whl", hash = "sha256:6c65dc49e1377f71fbe68dd90d851c7181898b46c36affd69de29cf0b125bb16"},
|
||||
{file = "dspy-2.5.25.tar.gz", hash = "sha256:e35f391cd57ab9a822a95b91fe067eb3721b7f61e263913d9ae7b1df54f7fdd9"},
|
||||
]
|
||||
|
||||
[package.dependencies]
|
||||
backoff = "*"
|
||||
datasets = "*"
|
||||
diskcache = "*"
|
||||
httpx = "*"
|
||||
joblib = ">=1.3,<2.0"
|
||||
json-repair = "*"
|
||||
litellm = "<=1.49.1"
|
||||
magicattr = ">=0.1.6,<0.2.0"
|
||||
openai = "*"
|
||||
optuna = "*"
|
||||
pandas = "*"
|
||||
pydantic = ">=2.0,<3.0"
|
||||
regex = "*"
|
||||
requests = "*"
|
||||
structlog = "*"
|
||||
tenacity = ">=8.2.3"
|
||||
tqdm = "*"
|
||||
ujson = "*"
|
||||
|
||||
[package.extras]
|
||||
chromadb = ["chromadb (>=0.4.14,<0.5.0)"]
|
||||
faiss-cpu = ["faiss-cpu", "sentence-transformers"]
|
||||
fastembed = ["fastembed"]
|
||||
google-vertex-ai = ["google-cloud-aiplatform (==1.43.0)"]
|
||||
groq = ["groq (>=0.8.0,<0.9.0)"]
|
||||
lancedb = ["lancedb (>=0.11.0,<0.12.0)"]
|
||||
langfuse = ["langfuse (>=2.36.1,<2.37.0)"]
|
||||
marqo = ["marqo (>=3.1.0,<3.2.0)"]
|
||||
milvus = ["pymilvus (>=2.3.7,<2.4.0)"]
|
||||
mongodb = ["pymongo (>=3.12.0,<3.13.0)"]
|
||||
myscale = ["clickhouse-connect"]
|
||||
pgvector = ["pgvector (>=0.2.5,<0.3.0)", "psycopg2 (>=2.9.9,<2.10.0)"]
|
||||
pinecone = ["pinecone-client (>=2.2.4,<2.3.0)"]
|
||||
qdrant = ["fastembed", "qdrant-client"]
|
||||
snowflake = ["snowflake-snowpark-python"]
|
||||
weaviate = ["weaviate-client (>=4.6.5,<4.7.0)"]
|
||||
|
||||
[[package]]
|
||||
name = "email-validator"
|
||||
version = "2.2.0"
|
||||
|
|
@ -2742,17 +2665,6 @@ files = [
|
|||
{file = "jsmin-3.0.1.tar.gz", hash = "sha256:c0959a121ef94542e807a674142606f7e90214a2b3d1eb17300244bbb5cc2bfc"},
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "json-repair"
|
||||
version = "0.30.1"
|
||||
description = "A package to repair broken json strings"
|
||||
optional = false
|
||||
python-versions = ">=3.9"
|
||||
files = [
|
||||
{file = "json_repair-0.30.1-py3-none-any.whl", hash = "sha256:6fa8a05d246e282df2f812fa542bd837d671d7774eaae11191aabaac97d41e33"},
|
||||
{file = "json_repair-0.30.1.tar.gz", hash = "sha256:5f075c4e3b098d78fb6cd60c34aec07a4517f14e9d423ad5364214b0e870e218"},
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "json5"
|
||||
version = "0.9.27"
|
||||
|
|
@ -3334,16 +3246,6 @@ tokenizers = "*"
|
|||
extra-proxy = ["azure-identity (>=1.15.0,<2.0.0)", "azure-keyvault-secrets (>=4.8.0,<5.0.0)", "google-cloud-kms (>=2.21.3,<3.0.0)", "prisma (==0.11.0)", "resend (>=0.8.0,<0.9.0)"]
|
||||
proxy = ["PyJWT (>=2.8.0,<3.0.0)", "apscheduler (>=3.10.4,<4.0.0)", "backoff", "cryptography (>=42.0.5,<43.0.0)", "fastapi (>=0.111.0,<0.112.0)", "fastapi-sso (>=0.10.0,<0.11.0)", "gunicorn (>=22.0.0,<23.0.0)", "orjson (>=3.9.7,<4.0.0)", "pynacl (>=1.5.0,<2.0.0)", "python-multipart (>=0.0.9,<0.0.10)", "pyyaml (>=6.0.1,<7.0.0)", "rq", "uvicorn (>=0.22.0,<0.23.0)"]
|
||||
|
||||
[[package]]
|
||||
name = "magicattr"
|
||||
version = "0.1.6"
|
||||
description = "A getattr and setattr that works on nested objects, lists, dicts, and any combination thereof without resorting to eval"
|
||||
optional = false
|
||||
python-versions = "*"
|
||||
files = [
|
||||
{file = "magicattr-0.1.6-py2.py3-none-any.whl", hash = "sha256:d96b18ee45b5ee83b09c17e15d3459a64de62d538808c2f71182777dd9dbbbdf"},
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "makefun"
|
||||
version = "1.15.6"
|
||||
|
|
@ -4256,33 +4158,6 @@ typing-extensions = ">=4.11,<5"
|
|||
[package.extras]
|
||||
datalib = ["numpy (>=1)", "pandas (>=1.2.3)", "pandas-stubs (>=1.1.0.11)"]
|
||||
|
||||
[[package]]
|
||||
name = "optuna"
|
||||
version = "4.0.0"
|
||||
description = "A hyperparameter optimization framework"
|
||||
optional = false
|
||||
python-versions = ">=3.7"
|
||||
files = [
|
||||
{file = "optuna-4.0.0-py3-none-any.whl", hash = "sha256:a825c32d13f6085bcb2229b2724a5078f2e0f61a7533e800e580ce41a8c6c10d"},
|
||||
{file = "optuna-4.0.0.tar.gz", hash = "sha256:844949f09e2a7353ab414e9cfd783cf0a647a65fc32a7236212ed6a37fe08973"},
|
||||
]
|
||||
|
||||
[package.dependencies]
|
||||
alembic = ">=1.5.0"
|
||||
colorlog = "*"
|
||||
numpy = "*"
|
||||
packaging = ">=20.0"
|
||||
PyYAML = "*"
|
||||
sqlalchemy = ">=1.3.0"
|
||||
tqdm = "*"
|
||||
|
||||
[package.extras]
|
||||
benchmark = ["asv (>=0.5.0)", "botorch", "cma", "virtualenv"]
|
||||
checking = ["black", "blackdoc", "flake8", "isort", "mypy", "mypy-boto3-s3", "types-PyYAML", "types-redis", "types-setuptools", "types-tqdm", "typing-extensions (>=3.10.0.0)"]
|
||||
document = ["ase", "cmaes (>=0.10.0)", "fvcore", "kaleido", "lightgbm", "matplotlib (!=3.6.0)", "pandas", "pillow", "plotly (>=4.9.0)", "scikit-learn", "sphinx", "sphinx-copybutton", "sphinx-gallery", "sphinx-rtd-theme (>=1.2.0)", "torch", "torchvision"]
|
||||
optional = ["boto3", "cmaes (>=0.10.0)", "google-cloud-storage", "matplotlib (!=3.6.0)", "pandas", "plotly (>=4.9.0)", "redis", "scikit-learn (>=0.24.2)", "scipy", "torch"]
|
||||
test = ["coverage", "fakeredis[lua]", "kaleido", "moto", "pytest", "scipy (>=1.9.2)", "torch"]
|
||||
|
||||
[[package]]
|
||||
name = "orjson"
|
||||
version = "3.10.11"
|
||||
|
|
@ -6193,6 +6068,11 @@ files = [
|
|||
{file = "scikit_learn-1.5.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f60021ec1574e56632be2a36b946f8143bf4e5e6af4a06d85281adc22938e0dd"},
|
||||
{file = "scikit_learn-1.5.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:394397841449853c2290a32050382edaec3da89e35b3e03d6cc966aebc6a8ae6"},
|
||||
{file = "scikit_learn-1.5.2-cp312-cp312-win_amd64.whl", hash = "sha256:57cc1786cfd6bd118220a92ede80270132aa353647684efa385a74244a41e3b1"},
|
||||
{file = "scikit_learn-1.5.2-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:e9a702e2de732bbb20d3bad29ebd77fc05a6b427dc49964300340e4c9328b3f5"},
|
||||
{file = "scikit_learn-1.5.2-cp313-cp313-macosx_12_0_arm64.whl", hash = "sha256:b0768ad641981f5d3a198430a1d31c3e044ed2e8a6f22166b4d546a5116d7908"},
|
||||
{file = "scikit_learn-1.5.2-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:178ddd0a5cb0044464fc1bfc4cca5b1833bfc7bb022d70b05db8530da4bb3dd3"},
|
||||
{file = "scikit_learn-1.5.2-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f7284ade780084d94505632241bf78c44ab3b6f1e8ccab3d2af58e0e950f9c12"},
|
||||
{file = "scikit_learn-1.5.2-cp313-cp313-win_amd64.whl", hash = "sha256:b7b0f9a0b1040830d38c39b91b3a44e1b643f4b36e36567b80b7c6bd2202a27f"},
|
||||
{file = "scikit_learn-1.5.2-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:757c7d514ddb00ae249832fe87100d9c73c6ea91423802872d9e74970a0e40b9"},
|
||||
{file = "scikit_learn-1.5.2-cp39-cp39-macosx_12_0_arm64.whl", hash = "sha256:52788f48b5d8bca5c0736c175fa6bdaab2ef00a8f536cda698db61bd89c551c1"},
|
||||
{file = "scikit_learn-1.5.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:643964678f4b5fbdc95cbf8aec638acc7aa70f5f79ee2cdad1eec3df4ba6ead8"},
|
||||
|
|
@ -6669,23 +6549,6 @@ typing-extensions = {version = ">=3.10.0", markers = "python_version < \"3.10\""
|
|||
[package.extras]
|
||||
full = ["httpx (>=0.22.0)", "itsdangerous", "jinja2", "python-multipart (>=0.0.7)", "pyyaml"]
|
||||
|
||||
[[package]]
|
||||
name = "structlog"
|
||||
version = "24.4.0"
|
||||
description = "Structured Logging for Python"
|
||||
optional = false
|
||||
python-versions = ">=3.8"
|
||||
files = [
|
||||
{file = "structlog-24.4.0-py3-none-any.whl", hash = "sha256:597f61e80a91cc0749a9fd2a098ed76715a1c8a01f73e336b746504d1aad7610"},
|
||||
{file = "structlog-24.4.0.tar.gz", hash = "sha256:b27bfecede327a6d2da5fbc96bd859f114ecc398a6389d664f62085ee7ae6fc4"},
|
||||
]
|
||||
|
||||
[package.extras]
|
||||
dev = ["freezegun (>=0.2.8)", "mypy (>=1.4)", "pretend", "pytest (>=6.0)", "pytest-asyncio (>=0.17)", "rich", "simplejson", "twisted"]
|
||||
docs = ["cogapp", "furo", "myst-parser", "sphinx", "sphinx-notfound-page", "sphinxcontrib-mermaid", "sphinxext-opengraph", "twisted"]
|
||||
tests = ["freezegun (>=0.2.8)", "pretend", "pytest (>=6.0)", "pytest-asyncio (>=0.17)", "simplejson"]
|
||||
typing = ["mypy (>=1.4)", "rich", "twisted"]
|
||||
|
||||
[[package]]
|
||||
name = "tenacity"
|
||||
version = "9.0.0"
|
||||
|
|
@ -7094,93 +6957,6 @@ files = [
|
|||
{file = "tzdata-2024.2.tar.gz", hash = "sha256:7d85cc416e9382e69095b7bdf4afd9e3880418a2413feec7069d533d6b4e31cc"},
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "ujson"
|
||||
version = "5.10.0"
|
||||
description = "Ultra fast JSON encoder and decoder for Python"
|
||||
optional = false
|
||||
python-versions = ">=3.8"
|
||||
files = [
|
||||
{file = "ujson-5.10.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:2601aa9ecdbee1118a1c2065323bda35e2c5a2cf0797ef4522d485f9d3ef65bd"},
|
||||
{file = "ujson-5.10.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:348898dd702fc1c4f1051bc3aacbf894caa0927fe2c53e68679c073375f732cf"},
|
||||
{file = "ujson-5.10.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:22cffecf73391e8abd65ef5f4e4dd523162a3399d5e84faa6aebbf9583df86d6"},
|
||||
{file = "ujson-5.10.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:26b0e2d2366543c1bb4fbd457446f00b0187a2bddf93148ac2da07a53fe51569"},
|
||||
{file = "ujson-5.10.0-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:caf270c6dba1be7a41125cd1e4fc7ba384bf564650beef0df2dd21a00b7f5770"},
|
||||
{file = "ujson-5.10.0-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:a245d59f2ffe750446292b0094244df163c3dc96b3ce152a2c837a44e7cda9d1"},
|
||||
{file = "ujson-5.10.0-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:94a87f6e151c5f483d7d54ceef83b45d3a9cca7a9cb453dbdbb3f5a6f64033f5"},
|
||||
{file = "ujson-5.10.0-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:29b443c4c0a113bcbb792c88bea67b675c7ca3ca80c3474784e08bba01c18d51"},
|
||||
{file = "ujson-5.10.0-cp310-cp310-win32.whl", hash = "sha256:c18610b9ccd2874950faf474692deee4223a994251bc0a083c114671b64e6518"},
|
||||
{file = "ujson-5.10.0-cp310-cp310-win_amd64.whl", hash = "sha256:924f7318c31874d6bb44d9ee1900167ca32aa9b69389b98ecbde34c1698a250f"},
|
||||
{file = "ujson-5.10.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:a5b366812c90e69d0f379a53648be10a5db38f9d4ad212b60af00bd4048d0f00"},
|
||||
{file = "ujson-5.10.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:502bf475781e8167f0f9d0e41cd32879d120a524b22358e7f205294224c71126"},
|
||||
{file = "ujson-5.10.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5b91b5d0d9d283e085e821651184a647699430705b15bf274c7896f23fe9c9d8"},
|
||||
{file = "ujson-5.10.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:129e39af3a6d85b9c26d5577169c21d53821d8cf68e079060602e861c6e5da1b"},
|
||||
{file = "ujson-5.10.0-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f77b74475c462cb8b88680471193064d3e715c7c6074b1c8c412cb526466efe9"},
|
||||
{file = "ujson-5.10.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:7ec0ca8c415e81aa4123501fee7f761abf4b7f386aad348501a26940beb1860f"},
|
||||
{file = "ujson-5.10.0-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:ab13a2a9e0b2865a6c6db9271f4b46af1c7476bfd51af1f64585e919b7c07fd4"},
|
||||
{file = "ujson-5.10.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:57aaf98b92d72fc70886b5a0e1a1ca52c2320377360341715dd3933a18e827b1"},
|
||||
{file = "ujson-5.10.0-cp311-cp311-win32.whl", hash = "sha256:2987713a490ceb27edff77fb184ed09acdc565db700ee852823c3dc3cffe455f"},
|
||||
{file = "ujson-5.10.0-cp311-cp311-win_amd64.whl", hash = "sha256:f00ea7e00447918ee0eff2422c4add4c5752b1b60e88fcb3c067d4a21049a720"},
|
||||
{file = "ujson-5.10.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:98ba15d8cbc481ce55695beee9f063189dce91a4b08bc1d03e7f0152cd4bbdd5"},
|
||||
{file = "ujson-5.10.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:a9d2edbf1556e4f56e50fab7d8ff993dbad7f54bac68eacdd27a8f55f433578e"},
|
||||
{file = "ujson-5.10.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6627029ae4f52d0e1a2451768c2c37c0c814ffc04f796eb36244cf16b8e57043"},
|
||||
{file = "ujson-5.10.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f8ccb77b3e40b151e20519c6ae6d89bfe3f4c14e8e210d910287f778368bb3d1"},
|
||||
{file = "ujson-5.10.0-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f3caf9cd64abfeb11a3b661329085c5e167abbe15256b3b68cb5d914ba7396f3"},
|
||||
{file = "ujson-5.10.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:6e32abdce572e3a8c3d02c886c704a38a1b015a1fb858004e03d20ca7cecbb21"},
|
||||
{file = "ujson-5.10.0-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:a65b6af4d903103ee7b6f4f5b85f1bfd0c90ba4eeac6421aae436c9988aa64a2"},
|
||||
{file = "ujson-5.10.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:604a046d966457b6cdcacc5aa2ec5314f0e8c42bae52842c1e6fa02ea4bda42e"},
|
||||
{file = "ujson-5.10.0-cp312-cp312-win32.whl", hash = "sha256:6dea1c8b4fc921bf78a8ff00bbd2bfe166345f5536c510671bccececb187c80e"},
|
||||
{file = "ujson-5.10.0-cp312-cp312-win_amd64.whl", hash = "sha256:38665e7d8290188b1e0d57d584eb8110951a9591363316dd41cf8686ab1d0abc"},
|
||||
{file = "ujson-5.10.0-cp313-cp313-macosx_10_9_x86_64.whl", hash = "sha256:618efd84dc1acbd6bff8eaa736bb6c074bfa8b8a98f55b61c38d4ca2c1f7f287"},
|
||||
{file = "ujson-5.10.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:38d5d36b4aedfe81dfe251f76c0467399d575d1395a1755de391e58985ab1c2e"},
|
||||
{file = "ujson-5.10.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:67079b1f9fb29ed9a2914acf4ef6c02844b3153913eb735d4bf287ee1db6e557"},
|
||||
{file = "ujson-5.10.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d7d0e0ceeb8fe2468c70ec0c37b439dd554e2aa539a8a56365fd761edb418988"},
|
||||
{file = "ujson-5.10.0-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:59e02cd37bc7c44d587a0ba45347cc815fb7a5fe48de16bf05caa5f7d0d2e816"},
|
||||
{file = "ujson-5.10.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:2a890b706b64e0065f02577bf6d8ca3b66c11a5e81fb75d757233a38c07a1f20"},
|
||||
{file = "ujson-5.10.0-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:621e34b4632c740ecb491efc7f1fcb4f74b48ddb55e65221995e74e2d00bbff0"},
|
||||
{file = "ujson-5.10.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:b9500e61fce0cfc86168b248104e954fead61f9be213087153d272e817ec7b4f"},
|
||||
{file = "ujson-5.10.0-cp313-cp313-win32.whl", hash = "sha256:4c4fc16f11ac1612f05b6f5781b384716719547e142cfd67b65d035bd85af165"},
|
||||
{file = "ujson-5.10.0-cp313-cp313-win_amd64.whl", hash = "sha256:4573fd1695932d4f619928fd09d5d03d917274381649ade4328091ceca175539"},
|
||||
{file = "ujson-5.10.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:a984a3131da7f07563057db1c3020b1350a3e27a8ec46ccbfbf21e5928a43050"},
|
||||
{file = "ujson-5.10.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:73814cd1b9db6fc3270e9d8fe3b19f9f89e78ee9d71e8bd6c9a626aeaeaf16bd"},
|
||||
{file = "ujson-5.10.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:61e1591ed9376e5eddda202ec229eddc56c612b61ac6ad07f96b91460bb6c2fb"},
|
||||
{file = "ujson-5.10.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d2c75269f8205b2690db4572a4a36fe47cd1338e4368bc73a7a0e48789e2e35a"},
|
||||
{file = "ujson-5.10.0-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7223f41e5bf1f919cd8d073e35b229295aa8e0f7b5de07ed1c8fddac63a6bc5d"},
|
||||
{file = "ujson-5.10.0-cp38-cp38-musllinux_1_2_aarch64.whl", hash = "sha256:d4dc2fd6b3067c0782e7002ac3b38cf48608ee6366ff176bbd02cf969c9c20fe"},
|
||||
{file = "ujson-5.10.0-cp38-cp38-musllinux_1_2_i686.whl", hash = "sha256:232cc85f8ee3c454c115455195a205074a56ff42608fd6b942aa4c378ac14dd7"},
|
||||
{file = "ujson-5.10.0-cp38-cp38-musllinux_1_2_x86_64.whl", hash = "sha256:cc6139531f13148055d691e442e4bc6601f6dba1e6d521b1585d4788ab0bfad4"},
|
||||
{file = "ujson-5.10.0-cp38-cp38-win32.whl", hash = "sha256:e7ce306a42b6b93ca47ac4a3b96683ca554f6d35dd8adc5acfcd55096c8dfcb8"},
|
||||
{file = "ujson-5.10.0-cp38-cp38-win_amd64.whl", hash = "sha256:e82d4bb2138ab05e18f089a83b6564fee28048771eb63cdecf4b9b549de8a2cc"},
|
||||
{file = "ujson-5.10.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:dfef2814c6b3291c3c5f10065f745a1307d86019dbd7ea50e83504950136ed5b"},
|
||||
{file = "ujson-5.10.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:4734ee0745d5928d0ba3a213647f1c4a74a2a28edc6d27b2d6d5bd9fa4319e27"},
|
||||
{file = "ujson-5.10.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d47ebb01bd865fdea43da56254a3930a413f0c5590372a1241514abae8aa7c76"},
|
||||
{file = "ujson-5.10.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:dee5e97c2496874acbf1d3e37b521dd1f307349ed955e62d1d2f05382bc36dd5"},
|
||||
{file = "ujson-5.10.0-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7490655a2272a2d0b072ef16b0b58ee462f4973a8f6bbe64917ce5e0a256f9c0"},
|
||||
{file = "ujson-5.10.0-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:ba17799fcddaddf5c1f75a4ba3fd6441f6a4f1e9173f8a786b42450851bd74f1"},
|
||||
{file = "ujson-5.10.0-cp39-cp39-musllinux_1_2_i686.whl", hash = "sha256:2aff2985cef314f21d0fecc56027505804bc78802c0121343874741650a4d3d1"},
|
||||
{file = "ujson-5.10.0-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:ad88ac75c432674d05b61184178635d44901eb749786c8eb08c102330e6e8996"},
|
||||
{file = "ujson-5.10.0-cp39-cp39-win32.whl", hash = "sha256:2544912a71da4ff8c4f7ab5606f947d7299971bdd25a45e008e467ca638d13c9"},
|
||||
{file = "ujson-5.10.0-cp39-cp39-win_amd64.whl", hash = "sha256:3ff201d62b1b177a46f113bb43ad300b424b7847f9c5d38b1b4ad8f75d4a282a"},
|
||||
{file = "ujson-5.10.0-pp310-pypy310_pp73-macosx_10_9_x86_64.whl", hash = "sha256:5b6fee72fa77dc172a28f21693f64d93166534c263adb3f96c413ccc85ef6e64"},
|
||||
{file = "ujson-5.10.0-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:61d0af13a9af01d9f26d2331ce49bb5ac1fb9c814964018ac8df605b5422dcb3"},
|
||||
{file = "ujson-5.10.0-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ecb24f0bdd899d368b715c9e6664166cf694d1e57be73f17759573a6986dd95a"},
|
||||
{file = "ujson-5.10.0-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fbd8fd427f57a03cff3ad6574b5e299131585d9727c8c366da4624a9069ed746"},
|
||||
{file = "ujson-5.10.0-pp310-pypy310_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:beeaf1c48e32f07d8820c705ff8e645f8afa690cca1544adba4ebfa067efdc88"},
|
||||
{file = "ujson-5.10.0-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:baed37ea46d756aca2955e99525cc02d9181de67f25515c468856c38d52b5f3b"},
|
||||
{file = "ujson-5.10.0-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:7663960f08cd5a2bb152f5ee3992e1af7690a64c0e26d31ba7b3ff5b2ee66337"},
|
||||
{file = "ujson-5.10.0-pp38-pypy38_pp73-macosx_11_0_arm64.whl", hash = "sha256:d8640fb4072d36b08e95a3a380ba65779d356b2fee8696afeb7794cf0902d0a1"},
|
||||
{file = "ujson-5.10.0-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:78778a3aa7aafb11e7ddca4e29f46bc5139131037ad628cc10936764282d6753"},
|
||||
{file = "ujson-5.10.0-pp38-pypy38_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b0111b27f2d5c820e7f2dbad7d48e3338c824e7ac4d2a12da3dc6061cc39c8e6"},
|
||||
{file = "ujson-5.10.0-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:c66962ca7565605b355a9ed478292da628b8f18c0f2793021ca4425abf8b01e5"},
|
||||
{file = "ujson-5.10.0-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:ba43cc34cce49cf2d4bc76401a754a81202d8aa926d0e2b79f0ee258cb15d3a4"},
|
||||
{file = "ujson-5.10.0-pp39-pypy39_pp73-macosx_11_0_arm64.whl", hash = "sha256:ac56eb983edce27e7f51d05bc8dd820586c6e6be1c5216a6809b0c668bb312b8"},
|
||||
{file = "ujson-5.10.0-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f44bd4b23a0e723bf8b10628288c2c7c335161d6840013d4d5de20e48551773b"},
|
||||
{file = "ujson-5.10.0-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7c10f4654e5326ec14a46bcdeb2b685d4ada6911050aa8baaf3501e57024b804"},
|
||||
{file = "ujson-5.10.0-pp39-pypy39_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:0de4971a89a762398006e844ae394bd46991f7c385d7a6a3b93ba229e6dac17e"},
|
||||
{file = "ujson-5.10.0-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:e1402f0564a97d2a52310ae10a64d25bcef94f8dd643fcf5d310219d915484f7"},
|
||||
{file = "ujson-5.10.0.tar.gz", hash = "sha256:b3cd8f3c5d8c7738257f1018880444f7b7d9b66232c64649f562d7ba86ad4bc1"},
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "uri-template"
|
||||
version = "1.3.0"
|
||||
|
|
@ -7746,4 +7522,4 @@ weaviate = ["weaviate-client"]
|
|||
[metadata]
|
||||
lock-version = "2.0"
|
||||
python-versions = ">=3.9.0,<3.12"
|
||||
content-hash = "fb09733ff7a70fb91c5f72ff0c8a8137b857557930a7aa025aad3154de4d8ceb"
|
||||
content-hash = "57a154a7bbdd990e0fbe2313fa24c412dad98e47b9cd05e41bf378a3f597713f"
|
||||
|
|
|
|||
|
|
@ -27,7 +27,6 @@ uvicorn = "0.22.0"
|
|||
requests = "2.32.3"
|
||||
aiohttp = "3.10.10"
|
||||
typing_extensions = "4.12.2"
|
||||
dspy = "2.5.25"
|
||||
nest_asyncio = "1.6.0"
|
||||
numpy = "1.26.4"
|
||||
datasets = "3.1.0"
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue