Remove fastembed dependency

cognee/infrastructure/databases/vector/embeddings/FastembedEmbeddingEngine.py

@@ -1,25 +0,0 @@
-from typing import List, Optional
-from fastembed import TextEmbedding
-from cognee.root_dir import get_absolute_path
-from cognee.infrastructure.databases.vector.embeddings.EmbeddingEngine import EmbeddingEngine
-
-class FastembedEmbeddingEngine(EmbeddingEngine):
-    embedding_model: str
-    embedding_dimensions: int
-
-    def __init__(
-        self,
-        embedding_model: Optional[str] = "BAAI/bge-large-en-v1.5",
-        embedding_dimensions: Optional[int] = 1024,
-    ):
-        self.embedding_model = embedding_model
-        self.embedding_dimensions = embedding_dimensions
-
-    async def embed_text(self, text: List[str]) -> List[float]:
-        embedding_model = TextEmbedding(model_name = self.embedding_model, cache_dir = get_absolute_path("cache/embeddings"))
-        embeddings_list = list(map(lambda embedding: embedding.tolist(), embedding_model.embed(text)))
-
-        return embeddings_list
-
-    def get_vector_size(self) -> int:
-        return self.embedding_dimensions

cognee/modules/cognify/evaluate.py

@@ -1,4 +1,3 @@
-import dsp
 import dspy
 from dspy.evaluate.evaluate import Evaluate
 from dspy.primitives.example import Example

cognee/modules/cognify/train.py

@@ -1,4 +1,3 @@
-import dsp
 import dspy
 from dspy.teleprompt import BootstrapFewShot
 from dspy.primitives.example import Example

pyproject.toml

@@ -24,48 +24,46 @@ pydantic = "2.8.2"
 python-dotenv = "1.0.1"
 fastapi = "^0.109.2"
 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"
+falkordb = "1.0.9"
 boto3 = "^1.26.125"
+botocore="^1.35.54"
 gunicorn = "^20.1.0"
 sqlalchemy = "2.0.35"
-instructor = "1.3.5"
+instructor = "1.6.3"
 networkx = "^3.2.1"
-debugpy = "1.8.2"
-pyarrow = "15.0.0"
-pylint = "^3.0.3"
 aiosqlite = "^0.20.0"
 pandas = "2.0.3"
-greenlet = "^3.0.3"
-ruff = "^0.2.2"
 filetype = "^1.2.0"
 nltk = "^3.8.1"
 dlt = {extras = ["sqlalchemy"], version = "^1.2.0"}
-overrides = "^7.7.0"
 aiofiles = "^23.2.1"
 qdrant-client = "^1.9.0"
 graphistry = "^0.33.5"
-tenacity = "^8.2.3"
+tenacity = "^9.0.0"
 weaviate-client = "4.6.7"
 scikit-learn = "^1.5.0"
-fastembed = "0.2.7"
 pypdf = "^4.1.0"
 neo4j = "^5.20.0"
 jinja2 = "^3.1.3"
 matplotlib = "^3.8.3"
-structlog = "^24.1.0"
 tiktoken = "0.7.0"
+langchain_text_splitters = "0.3.2" 
+langsmith = "0.1.139"
+langdetect = "1.0.9"
 posthog = "^3.5.0"
 lancedb = "0.8.0"
-litellm = "1.51.3"
+litellm = "1.49.1"
 groq = "0.8.0"
-tantivy = "^0.22.0"
-tokenizers ="0.15.2"
-transformers ="4.39.0"
-python-multipart = "^0.0.9"
 langfuse = "^2.32.0"
-protobuf = "<5.0.0"
 pydantic-settings = "^2.2.1"
 anthropic = "^0.26.1"
-pdfplumber = "^0.11.1"
 sentry-sdk = {extras = ["fastapi"], version = "^2.9.0"}
 fastapi-users = { version = "*", extras = ["sqlalchemy"] }
 asyncpg = "^0.29.0"
@@ -88,6 +86,11 @@ pytest-asyncio = "^0.21.1"
 coverage = "^7.3.2"
 mypy = "^1.7.1"
 notebook = "^7.1.1"
+deptry = "^0.20.0"
+debugpy = "1.8.2"
+pylint = "^3.0.3"
+ruff = "^0.2.2"
+tweepy = "4.14.0"
 
 [tool.poetry.group.docs.dependencies]
 mkdocs-material = "^9.5.42"