gmakstutis/cognee
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

refactor: Rename LLMAdapter to LLMGateway

Browse source
This commit is contained in:
Igor Ilic 2025-08-05 21:12:09 +02:00
parent a7f51c8ce9
commit a9ec51691e
31 changed files with 89 additions and 89 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

8
cognee-mcp/src/codingagents/coding_rule_associations.py
View file

@ -4,7 +4,7 @@ from cognee.infrastructure.databases.graph import get_graph_engine
from cognee.infrastructure.databases.vector import get_vector_engine
from cognee.low_level import DataPoint
from cognee.infrastructure.llm import LLMAdapter
from cognee.infrastructure.llm import LLMGateway
from cognee.shared.logging_utils import get_logger
from cognee.modules.engine.models import NodeSet
from cognee.tasks.storage import add_data_points, index_graph_edges
@ -96,12 +96,12 @@ async def add_rule_associations(data: str, rules_nodeset_name: str):
user_context = {"chat": data, "rules": existing_rules}
user_prompt = LLMAdapter.render_prompt(
user_prompt = LLMGateway.render_prompt(
"coding_rule_association_agent_user.txt", context=user_context
)
system_prompt = LLMAdapter.render_prompt("coding_rule_association_agent_system.txt", context={})
system_prompt = LLMGateway.render_prompt("coding_rule_association_agent_system.txt", context={})
rule_list = await LLMAdapter.acreate_structured_output(
rule_list = await LLMGateway.acreate_structured_output(
text_input=user_prompt, system_prompt=system_prompt, response_model=RuleSet
)

8
cognee/eval_framework/evaluation/direct_llm_eval_adapter.py
View file

@ -3,7 +3,7 @@ from pydantic import BaseModel
from cognee.eval_framework.evaluation.base_eval_adapter import BaseEvalAdapter
from cognee.eval_framework.eval_config import EvalConfig
from cognee.infrastructure.llm import LLMAdapter
from cognee.infrastructure.llm import LLMGateway
class CorrectnessEvaluation(BaseModel):
@ -25,10 +25,10 @@ class DirectLLMEvalAdapter(BaseEvalAdapter):
) -> Dict[str, Any]:
args = {"question": question, "answer": answer, "golden_answer": golden_answer}
user_prompt = LLMAdapter.render_prompt(self.eval_prompt_path, args)
system_prompt = LLMAdapter.read_query_prompt(self.system_prompt_path)
user_prompt = LLMGateway.render_prompt(self.eval_prompt_path, args)
system_prompt = LLMGateway.read_query_prompt(self.system_prompt_path)
evaluation = await LLMAdapter.acreate_structured_output(
evaluation = await LLMGateway.acreate_structured_output(
text_input=user_prompt,
system_prompt=system_prompt,
response_model=CorrectnessEvaluation,

2
cognee/infrastructure/llm/LLMAdapter.py → cognee/infrastructure/llm/LLMGateway.py
View file

@ -4,7 +4,7 @@ from typing import Coroutine
from cognee.infrastructure.llm import get_llm_config
class LLMAdapter:
class LLMGateway:
"""
Class handles selection of structured output frameworks and LLM functions.
Class used as a namespace for LLM related functions, should not be instantiated, all methods are static.

2
cognee/infrastructure/llm/__init__.py
View file

@ -11,4 +11,4 @@ from cognee.infrastructure.llm.utils import (
test_embedding_connection,
)
from cognee.infrastructure.llm.LLMAdapter import LLMAdapter
from cognee.infrastructure.llm.LLMGateway import LLMGateway

6
cognee/infrastructure/llm/structured_output_framework/litellm_instructor/extraction/extract_categories.py
View file

@ -1,12 +1,12 @@
from typing import Type
from pydantic import BaseModel
from cognee.infrastructure.llm.LLMAdapter import LLMAdapter
from cognee.infrastructure.llm.LLMGateway import LLMGateway
async def extract_categories(content: str, response_model: Type[BaseModel]):
system_prompt = LLMAdapter.read_query_prompt("classify_content.txt")
system_prompt = LLMGateway.read_query_prompt("classify_content.txt")
llm_output = await LLMAdapter.acreate_structured_output(content, system_prompt, response_model)
llm_output = await LLMGateway.acreate_structured_output(content, system_prompt, response_model)
return llm_output

6
cognee/infrastructure/llm/structured_output_framework/litellm_instructor/extraction/extract_summary.py
View file

@ -5,7 +5,7 @@ from typing import Type
from instructor.exceptions import InstructorRetryException
from pydantic import BaseModel
from cognee.infrastructure.llm.LLMAdapter import LLMAdapter
from cognee.infrastructure.llm.LLMGateway import LLMGateway
from cognee.shared.data_models import SummarizedCode
logger = get_logger("extract_summary")
@ -25,9 +25,9 @@ def get_mock_summarized_code():
async def extract_summary(content: str, response_model: Type[BaseModel]):
system_prompt = LLMAdapter.read_query_prompt("summarize_content.txt")
system_prompt = LLMGateway.read_query_prompt("summarize_content.txt")
llm_output = await LLMAdapter.acreate_structured_output(content, system_prompt, response_model)
llm_output = await LLMGateway.acreate_structured_output(content, system_prompt, response_model)
return llm_output

6
cognee/infrastructure/llm/structured_output_framework/litellm_instructor/extraction/knowledge_graph/extract_content_graph.py
View file

@ -2,7 +2,7 @@ import os
from typing import Type
from pydantic import BaseModel
from cognee.infrastructure.llm.LLMAdapter import LLMAdapter
from cognee.infrastructure.llm.LLMGateway import LLMGateway
from cognee.infrastructure.llm.config import (
get_llm_config,
)
@ -22,9 +22,9 @@ async def extract_content_graph(content: str, response_model: Type[BaseModel]):
else:
base_directory = None
system_prompt = LLMAdapter.render_prompt(prompt_path, {}, base_directory=base_directory)
system_prompt = LLMGateway.render_prompt(prompt_path, {}, base_directory=base_directory)
content_graph = await LLMAdapter.acreate_structured_output(
content_graph = await LLMGateway.acreate_structured_output(
content, system_prompt, response_model
)

4
cognee/infrastructure/llm/structured_output_framework/litellm_instructor/llm/anthropic/adapter.py
View file

@ -11,7 +11,7 @@ from cognee.infrastructure.llm.structured_output_framework.litellm_instructor.ll
sleep_and_retry_async,
)
from cognee.infrastructure.llm.LLMAdapter import LLMAdapter
from cognee.infrastructure.llm.LLMGateway import LLMGateway
class AnthropicAdapter(LLMInterface):
@ -91,7 +91,7 @@ class AnthropicAdapter(LLMInterface):
if not system_prompt:
raise InvalidValueError(message="No system prompt path provided.")
system_prompt = LLMAdapter.read_query_prompt(system_prompt)
system_prompt = LLMGateway.read_query_prompt(system_prompt)
formatted_prompt = (
f"""System Prompt:\n{system_prompt}\n\nUser Input:\n{text_input}\n"""

4
cognee/infrastructure/llm/structured_output_framework/litellm_instructor/llm/gemini/adapter.py
View file

@ -9,7 +9,7 @@ from cognee.exceptions import InvalidValueError
from cognee.infrastructure.llm.structured_output_framework.litellm_instructor.llm.llm_interface import (
LLMInterface,
)
from cognee.infrastructure.llm.LLMAdapter import LLMAdapter
from cognee.infrastructure.llm.LLMGateway import LLMGateway
from cognee.infrastructure.llm.structured_output_framework.litellm_instructor.llm.rate_limiter import (
rate_limit_async,
sleep_and_retry_async,
@ -136,7 +136,7 @@ class GeminiAdapter(LLMInterface):
text_input = "No user input provided."
if not system_prompt:
raise InvalidValueError(message="No system prompt path provided.")
system_prompt = LLMAdapter.read_query_prompt(system_prompt)
system_prompt = LLMGateway.read_query_prompt(system_prompt)
formatted_prompt = (
f"""System Prompt:\n{system_prompt}\n\nUser Input:\n{text_input}\n"""

4
cognee/infrastructure/llm/structured_output_framework/litellm_instructor/llm/llm_interface.py
View file

@ -3,7 +3,7 @@
from typing import Type, Protocol
from abc import abstractmethod
from pydantic import BaseModel
from cognee.infrastructure.llm.LLMAdapter import LLMAdapter
from cognee.infrastructure.llm.LLMGateway import LLMGateway
class LLMInterface(Protocol):
@ -57,7 +57,7 @@ class LLMInterface(Protocol):
text_input = "No user input provided."
if not system_prompt:
raise ValueError("No system prompt path provided.")
system_prompt = LLMAdapter.read_query_prompt(system_prompt)
system_prompt = LLMGateway.read_query_prompt(system_prompt)
formatted_prompt = f"""System Prompt:\n{system_prompt}\n\nUser Input:\n{text_input}\n"""

4
cognee/infrastructure/llm/structured_output_framework/litellm_instructor/llm/openai/adapter.py
View file

@ -8,7 +8,7 @@ from litellm.exceptions import ContentPolicyViolationError
from instructor.exceptions import InstructorRetryException
from cognee.exceptions import InvalidValueError
from cognee.infrastructure.llm.LLMAdapter import LLMAdapter
from cognee.infrastructure.llm.LLMGateway import LLMGateway
from cognee.infrastructure.llm.structured_output_framework.litellm_instructor.llm.llm_interface import (
LLMInterface,
)
@ -326,7 +326,7 @@ class OpenAIAdapter(LLMInterface):
text_input = "No user input provided."
if not system_prompt:
raise InvalidValueError(message="No system prompt path provided.")
system_prompt = LLMAdapter.read_query_prompt(system_prompt)
system_prompt = LLMGateway.read_query_prompt(system_prompt)
formatted_prompt = (
f"""System Prompt:\n{system_prompt}\n\nUser Input:\n{text_input}\n"""

4
cognee/modules/data/processing/document_types/AudioDocument.py
View file

@ -1,5 +1,5 @@
from cognee.modules.chunking.Chunker import Chunker
from cognee.infrastructure.llm.LLMAdapter import LLMAdapter
from cognee.infrastructure.llm.LLMGateway import LLMGateway
from .Document import Document
@ -8,7 +8,7 @@ class AudioDocument(Document):
type: str = "audio"
async def create_transcript(self):
result = await LLMAdapter.create_transcript(self.raw_data_location)
result = await LLMGateway.create_transcript(self.raw_data_location)
return result.text
async def read(self, chunker_cls: Chunker, max_chunk_size: int):

4
cognee/modules/data/processing/document_types/ImageDocument.py
View file

@ -1,4 +1,4 @@
from cognee.infrastructure.llm.LLMAdapter import LLMAdapter
from cognee.infrastructure.llm.LLMGateway import LLMGateway
from cognee.modules.chunking.Chunker import Chunker
from .Document import Document
@ -8,7 +8,7 @@ class ImageDocument(Document):
type: str = "image"
async def transcribe_image(self):
result = await LLMAdapter.transcribe_image(self.raw_data_location)
result = await LLMGateway.transcribe_image(self.raw_data_location)
return result.choices[0].message.content
async def read(self, chunker_cls: Chunker, max_chunk_size: int):

6
cognee/modules/retrieval/code_retriever.py
View file

@ -7,7 +7,7 @@ from cognee.shared.logging_utils import get_logger
from cognee.modules.retrieval.base_retriever import BaseRetriever
from cognee.infrastructure.databases.graph import get_graph_engine
from cognee.infrastructure.databases.vector import get_vector_engine
from cognee.infrastructure.llm.LLMAdapter import LLMAdapter
from cognee.infrastructure.llm.LLMGateway import LLMGateway
logger = get_logger("CodeRetriever")
@ -41,10 +41,10 @@ class CodeRetriever(BaseRetriever):
f"Processing query with LLM: '{query[:100]}{'...' if len(query) > 100 else ''}'"
)
system_prompt = LLMAdapter.read_query_prompt("codegraph_retriever_system.txt")
system_prompt = LLMGateway.read_query_prompt("codegraph_retriever_system.txt")
try:
result = await LLMAdapter.acreate_structured_output(
result = await LLMGateway.acreate_structured_output(
text_input=query,
system_prompt=system_prompt,
response_model=self.CodeQueryInfo,

14
cognee/modules/retrieval/graph_completion_cot_retriever.py
View file

@ -3,7 +3,7 @@ from cognee.shared.logging_utils import get_logger
from cognee.modules.retrieval.graph_completion_retriever import GraphCompletionRetriever
from cognee.modules.retrieval.utils.completion import generate_completion
from cognee.infrastructure.llm.LLMAdapter import LLMAdapter
from cognee.infrastructure.llm.LLMGateway import LLMGateway
logger = get_logger()
@ -94,27 +94,27 @@ class GraphCompletionCotRetriever(GraphCompletionRetriever):
logger.info(f"Chain-of-thought: round {round_idx} - answer: {answer}")
if round_idx < max_iter:
valid_args = {"query": query, "answer": answer, "context": context}
valid_user_prompt = LLMAdapter.render_prompt(
valid_user_prompt = LLMGateway.render_prompt(
filename=self.validation_user_prompt_path, context=valid_args
)
valid_system_prompt = LLMAdapter.read_query_prompt(
valid_system_prompt = LLMGateway.read_query_prompt(
prompt_file_name=self.validation_system_prompt_path
)
reasoning = await LLMAdapter.acreate_structured_output(
reasoning = await LLMGateway.acreate_structured_output(
text_input=valid_user_prompt,
system_prompt=valid_system_prompt,
response_model=str,
)
followup_args = {"query": query, "answer": answer, "reasoning": reasoning}
followup_prompt = LLMAdapter.render_prompt(
followup_prompt = LLMGateway.render_prompt(
filename=self.followup_user_prompt_path, context=followup_args
)
followup_system = LLMAdapter.read_query_prompt(
followup_system = LLMGateway.read_query_prompt(
prompt_file_name=self.followup_system_prompt_path
)
followup_question = await LLMAdapter.acreate_structured_output(
followup_question = await LLMGateway.acreate_structured_output(
text_input=followup_prompt, system_prompt=followup_system, response_model=str
)
logger.info(

6
cognee/modules/retrieval/natural_language_retriever.py
View file

@ -2,7 +2,7 @@ from typing import Any, Optional
from cognee.shared.logging_utils import get_logger
from cognee.infrastructure.databases.graph import get_graph_engine
from cognee.infrastructure.databases.graph.networkx.adapter import NetworkXAdapter
from cognee.infrastructure.llm.LLMAdapter import LLMAdapter
from cognee.infrastructure.llm.LLMGateway import LLMGateway
from cognee.modules.retrieval.base_retriever import BaseRetriever
from cognee.modules.retrieval.exceptions import SearchTypeNotSupported
from cognee.infrastructure.databases.graph.graph_db_interface import GraphDBInterface
@ -50,7 +50,7 @@ class NaturalLanguageRetriever(BaseRetriever):
async def _generate_cypher_query(self, query: str, edge_schemas, previous_attempts=None) -> str:
"""Generate a Cypher query using LLM based on natural language query and schema information."""
system_prompt = LLMAdapter.render_prompt(
system_prompt = LLMGateway.render_prompt(
self.system_prompt_path,
context={
"edge_schemas": edge_schemas,
@ -58,7 +58,7 @@ class NaturalLanguageRetriever(BaseRetriever):
},
)
return await LLMAdapter.acreate_structured_output(
return await LLMGateway.acreate_structured_output(
text_input=query,
system_prompt=system_prompt,
response_model=str,

12
cognee/modules/retrieval/utils/completion.py
View file

@ -1,4 +1,4 @@
from cognee.infrastructure.llm.LLMAdapter import LLMAdapter
from cognee.infrastructure.llm.LLMGateway import LLMGateway
async def generate_completion(
@ -9,10 +9,10 @@ async def generate_completion(
) -> str:
"""Generates a completion using LLM with given context and prompts."""
args = {"question": query, "context": context}
user_prompt = LLMAdapter.render_prompt(user_prompt_path, args)
system_prompt = LLMAdapter.read_query_prompt(system_prompt_path)
user_prompt = LLMGateway.render_prompt(user_prompt_path, args)
system_prompt = LLMGateway.read_query_prompt(system_prompt_path)
return await LLMAdapter.acreate_structured_output(
return await LLMGateway.acreate_structured_output(
text_input=user_prompt,
system_prompt=system_prompt,
response_model=str,
@ -24,9 +24,9 @@ async def summarize_text(
prompt_path: str = "summarize_search_results.txt",
) -> str:
"""Summarizes text using LLM with the specified prompt."""
system_prompt = LLMAdapter.read_query_prompt(prompt_path)
system_prompt = LLMGateway.read_query_prompt(prompt_path)
return await LLMAdapter.acreate_structured_output(
return await LLMGateway.acreate_structured_output(
text_input=text,
system_prompt=system_prompt,
response_model=str,

4
cognee/modules/retrieval/utils/description_to_codepart_search.py
View file

@ -9,7 +9,7 @@ from cognee.modules.users.methods import get_default_user
from cognee.modules.users.models import User
from cognee.shared.utils import send_telemetry
from cognee.modules.search.methods import search
from cognee.infrastructure.llm.LLMAdapter import LLMAdapter
from cognee.infrastructure.llm.LLMGateway import LLMGateway
logger = get_logger(level=ERROR)
@ -71,7 +71,7 @@ async def code_description_to_code_part(
if isinstance(obj, dict) and "description" in obj
)
context_from_documents = await LLMAdapter.acreate_structured_output(
context_from_documents = await LLMGateway.acreate_structured_output(
text_input=f"The retrieved context from documents is {concatenated_descriptions}.",
system_prompt="You are a Senior Software Engineer, summarize the context from documents"
f" in a way that it is gonna be provided next to codeparts as context"

4
cognee/modules/search/operations/select_search_type.py
View file

@ -1,7 +1,7 @@
from cognee.infrastructure.llm.prompts import read_query_prompt
from cognee.modules.search.types import SearchType
from cognee.shared.logging_utils import get_logger
from cognee.infrastructure.llm.LLMAdapter import LLMAdapter
from cognee.infrastructure.llm.LLMGateway import LLMGateway
logger = get_logger("SearchTypeSelector")
@ -24,7 +24,7 @@ async def select_search_type(
system_prompt = read_query_prompt(system_prompt_path)
try:
response = await LLMAdapter.acreate_structured_output(
response = await LLMGateway.acreate_structured_output(
text_input=query,
system_prompt=system_prompt,
response_model=str,

4
cognee/tasks/chunk_naive_llm_classifier/chunk_naive_llm_classifier.py
View file

@ -7,7 +7,7 @@ from pydantic import BaseModel
from cognee.infrastructure.databases.graph import get_graph_engine
from cognee.infrastructure.databases.vector import get_vector_engine
from cognee.infrastructure.engine.models import DataPoint
from cognee.infrastructure.llm.LLMAdapter import LLMAdapter
from cognee.infrastructure.llm.LLMGateway import LLMGateway
from cognee.modules.chunking.models.DocumentChunk import DocumentChunk
@ -40,7 +40,7 @@ async def chunk_naive_llm_classifier(
return data_chunks
chunk_classifications = await asyncio.gather(
*[LLMAdapter.extract_categories(chunk.text, classification_model) for chunk in data_chunks],
*[LLMGateway.extract_categories(chunk.text, classification_model) for chunk in data_chunks],
)
classification_data_points = []

8
cognee/tasks/entity_completion/entity_extractors/llm_entity_extractor.py
View file

@ -6,7 +6,7 @@ from pydantic import BaseModel
from cognee.infrastructure.entities.BaseEntityExtractor import BaseEntityExtractor
from cognee.modules.engine.models import Entity
from cognee.modules.engine.models.EntityType import EntityType
from cognee.infrastructure.llm.LLMAdapter import LLMAdapter
from cognee.infrastructure.llm.LLMGateway import LLMGateway
logger = get_logger("llm_entity_extractor")
@ -50,10 +50,10 @@ class LLMEntityExtractor(BaseEntityExtractor):
try:
logger.info(f"Extracting entities from text: {text[:100]}...")
user_prompt = LLMAdapter.render_prompt(self.user_prompt_template, {"text": text})
system_prompt = LLMAdapter.read_query_prompt(self.system_prompt_template)
user_prompt = LLMGateway.render_prompt(self.user_prompt_template, {"text": text})
system_prompt = LLMGateway.read_query_prompt(self.system_prompt_template)
response = await LLMAdapter.acreate_structured_output(
response = await LLMGateway.acreate_structured_output(
text_input=user_prompt,
system_prompt=system_prompt,
response_model=EntityList,

8
cognee/tasks/graph/cascade_extract/utils/extract_content_nodes_and_relationship_names.py
View file

@ -1,7 +1,7 @@
from typing import List, Tuple
from pydantic import BaseModel
from cognee.infrastructure.llm.LLMAdapter import LLMAdapter
from cognee.infrastructure.llm.LLMGateway import LLMGateway
from cognee.root_dir import get_absolute_path
@ -32,15 +32,15 @@ async def extract_content_nodes_and_relationship_names(
}
base_directory = get_absolute_path("./tasks/graph/cascade_extract/prompts")
text_input = LLMAdapter.render_prompt(
text_input = LLMGateway.render_prompt(
"extract_graph_relationship_names_prompt_input.txt",
context,
base_directory=base_directory,
)
system_prompt = LLMAdapter.read_query_prompt(
system_prompt = LLMGateway.read_query_prompt(
"extract_graph_relationship_names_prompt_system.txt", base_directory=base_directory
)
response = await LLMAdapter.acreate_structured_output(
response = await LLMGateway.acreate_structured_output(
text_input=text_input,
system_prompt=system_prompt,
response_model=PotentialNodesAndRelationshipNames,

8
cognee/tasks/graph/cascade_extract/utils/extract_edge_triplets.py
View file

@ -1,6 +1,6 @@
from typing import List
from cognee.infrastructure.llm.LLMAdapter import LLMAdapter
from cognee.infrastructure.llm.LLMGateway import LLMGateway
from cognee.shared.data_models import KnowledgeGraph
from cognee.root_dir import get_absolute_path
@ -26,13 +26,13 @@ async def extract_edge_triplets(
}
base_directory = get_absolute_path("./tasks/graph/cascade_extract/prompts")
text_input = LLMAdapter.render_prompt(
text_input = LLMGateway.render_prompt(
"extract_graph_edge_triplets_prompt_input.txt", context, base_directory=base_directory
)
system_prompt = LLMAdapter.read_query_prompt(
system_prompt = LLMGateway.read_query_prompt(
"extract_graph_edge_triplets_prompt_system.txt", base_directory=base_directory
)
extracted_graph = await LLMAdapter.acreate_structured_output(
extracted_graph = await LLMGateway.acreate_structured_output(
text_input=text_input, system_prompt=system_prompt, response_model=KnowledgeGraph
)

8
cognee/tasks/graph/cascade_extract/utils/extract_nodes.py
View file

@ -1,7 +1,7 @@
from typing import List
from pydantic import BaseModel
from cognee.infrastructure.llm.LLMAdapter import LLMAdapter
from cognee.infrastructure.llm.LLMGateway import LLMGateway
from cognee.root_dir import get_absolute_path
@ -24,13 +24,13 @@ async def extract_nodes(text: str, n_rounds: int = 2) -> List[str]:
"text": text,
}
base_directory = get_absolute_path("./tasks/graph/cascade_extract/prompts")
text_input = LLMAdapter.render_prompt(
text_input = LLMGateway.render_prompt(
"extract_graph_nodes_prompt_input.txt", context, base_directory=base_directory
)
system_prompt = LLMAdapter.read_query_prompt(
system_prompt = LLMGateway.read_query_prompt(
"extract_graph_nodes_prompt_system.txt", base_directory=base_directory
)
response = await LLMAdapter.acreate_structured_output(
response = await LLMGateway.acreate_structured_output(
text_input=text_input, system_prompt=system_prompt, response_model=PotentialNodes
)

4
cognee/tasks/graph/extract_graph_from_code.py
View file

@ -2,7 +2,7 @@ import asyncio
from typing import Type, List
from pydantic import BaseModel
from cognee.infrastructure.llm.LLMAdapter import LLMAdapter
from cognee.infrastructure.llm.LLMGateway import LLMGateway
from cognee.modules.chunking.models.DocumentChunk import DocumentChunk
from cognee.tasks.storage import add_data_points
@ -18,7 +18,7 @@ async def extract_graph_from_code(
- Graph nodes are stored using the `add_data_points` function for later retrieval or analysis.
"""
chunk_graphs = await asyncio.gather(
*[LLMAdapter.extract_content_graph(chunk.text, graph_model) for chunk in data_chunks]
*[LLMGateway.extract_content_graph(chunk.text, graph_model) for chunk in data_chunks]
)
for chunk_index, chunk in enumerate(data_chunks):

4
cognee/tasks/graph/extract_graph_from_data.py
View file

@ -11,7 +11,7 @@ from cognee.modules.graph.utils import (
retrieve_existing_edges,
)
from cognee.shared.data_models import KnowledgeGraph
from cognee.infrastructure.llm.LLMAdapter import LLMAdapter
from cognee.infrastructure.llm.LLMGateway import LLMGateway
async def integrate_chunk_graphs(
@ -56,7 +56,7 @@ async def extract_graph_from_data(
Extracts and integrates a knowledge graph from the text content of document chunks using a specified graph model.
"""
chunk_graphs = await asyncio.gather(
*[LLMAdapter.extract_content_graph(chunk.text, graph_model) for chunk in data_chunks]
*[LLMGateway.extract_content_graph(chunk.text, graph_model) for chunk in data_chunks]
)
# Note: Filter edges with missing source or target nodes

6
cognee/tasks/graph/infer_data_ontology.py
View file

@ -27,7 +27,7 @@ from cognee.modules.data.methods.add_model_class_to_graph import (
from cognee.tasks.graph.models import NodeModel, GraphOntology
from cognee.shared.data_models import KnowledgeGraph
from cognee.modules.engine.utils import generate_node_id, generate_node_name
from cognee.infrastructure.llm.LLMAdapter import LLMAdapter
from cognee.infrastructure.llm.LLMGateway import LLMGateway
logger = get_logger("task:infer_data_ontology")
@ -53,9 +53,9 @@ async def extract_ontology(content: str, response_model: Type[BaseModel]):
The structured ontology extracted from the content.
"""
system_prompt = LLMAdapter.read_query_prompt("extract_ontology.txt")
system_prompt = LLMGateway.read_query_prompt("extract_ontology.txt")
ontology = await LLMAdapter.acreate_structured_output(content, system_prompt, response_model)
ontology = await LLMGateway.acreate_structured_output(content, system_prompt, response_model)
return ontology

4
cognee/tasks/summarization/summarize_code.py
View file

@ -3,7 +3,7 @@ from typing import AsyncGenerator, Union
from uuid import uuid5
from cognee.infrastructure.engine import DataPoint
from cognee.infrastructure.llm.LLMAdapter import LLMAdapter
from cognee.infrastructure.llm.LLMGateway import LLMGateway
from .models import CodeSummary
@ -16,7 +16,7 @@ async def summarize_code(
code_data_points = [file for file in code_graph_nodes if hasattr(file, "source_code")]
file_summaries = await asyncio.gather(
*[LLMAdapter.extract_code_summary(file.source_code) for file in code_data_points]
*[LLMGateway.extract_code_summary(file.source_code) for file in code_data_points]
)
file_summaries_map = {

4
cognee/tasks/summarization/summarize_text.py
View file

@ -4,7 +4,7 @@ from uuid import uuid5
from pydantic import BaseModel
from cognee.modules.chunking.models.DocumentChunk import DocumentChunk
from cognee.infrastructure.llm.LLMAdapter import LLMAdapter
from cognee.infrastructure.llm.LLMGateway import LLMGateway
from cognee.modules.cognify.config import get_cognify_config
from .models import TextSummary
@ -43,7 +43,7 @@ async def summarize_text(
summarization_model = cognee_config.summarization_model
chunk_summaries = await asyncio.gather(
*[LLMAdapter.extract_summary(chunk.text, summarization_model) for chunk in data_chunks]
*[LLMGateway.extract_summary(chunk.text, summarization_model) for chunk in data_chunks]
)
summaries = [

4
examples/python/agentic_reasoning_procurement_example.py
View file

@ -3,7 +3,7 @@ import logging
import cognee
import asyncio
from cognee.infrastructure.llm.LLMAdapter import LLMAdapter
from cognee.infrastructure.llm.LLMGateway import LLMGateway
from dotenv import load_dotenv
from cognee.api.v1.search import SearchType
from cognee.modules.engine.models import NodeSet
@ -185,7 +185,7 @@ async def run_procurement_example():
print(research_information)
print("\nPassing research to LLM for final procurement recommendation...\n")
final_decision = await LLMAdapter.acreate_structured_output(
final_decision = await LLMGateway.acreate_structured_output(
text_input=research_information,
system_prompt="""You are a procurement decision assistant. Use the provided QA pairs that were collected through a research phase. Recommend the best vendor,
based on pricing, delivery, warranty, policy fit, and past performance. Be concise and justify your choice with evidence.

8
examples/python/graphiti_example.py
View file

@ -12,7 +12,7 @@ from cognee.tasks.temporal_awareness.index_graphiti_objects import (
)
from cognee.modules.retrieval.utils.brute_force_triplet_search import brute_force_triplet_search
from cognee.modules.retrieval.graph_completion_retriever import GraphCompletionRetriever
from cognee.infrastructure.llm.LLMAdapter import LLMAdapter
from cognee.infrastructure.llm.LLMGateway import LLMGateway
from cognee.modules.users.methods import get_default_user
text_list = [
@ -59,10 +59,10 @@ async def main():
"context": context,
}
user_prompt = LLMAdapter.render_prompt("graph_context_for_question.txt", args)
system_prompt = LLMAdapter.read_query_prompt("answer_simple_question_restricted.txt")
user_prompt = LLMGateway.render_prompt("graph_context_for_question.txt", args)
system_prompt = LLMGateway.read_query_prompt("answer_simple_question_restricted.txt")
computed_answer = await LLMAdapter.acreate_structured_output(
computed_answer = await LLMGateway.acreate_structured_output(
text_input=user_prompt,
system_prompt=system_prompt,
response_model=str,