embedding-flow 0.1.0__py3-none-any.whl → 0.1.1__py3-none-any.whl

embedding_flow/__init__.py

@@ -0,0 +1,4 @@
+from embedding_flow.main import embedding_flow
+
+__all__ = ['embedding_flow']
+

{contracts → embedding_flow/contracts}/contracts.py

@@ -11,4 +11,5 @@ class load_data(ABC):
     @abstractmethod
     def load_data(self, url: str) -> bool:
         """Carga datos y retorna True si fue exitoso, False si falló"""
-        pass
+        pass
+

{load → embedding_flow/load}/load.py

@@ -1,4 +1,4 @@
-from contracts.contracts import load_data
+from embedding_flow.contracts.contracts import load_data
 from qdrant_client import QdrantClient
 from qdrant_client.models import Distance, VectorParams, PointStruct
 import pandas as pd
@@ -98,4 +98,4 @@ class load_embedding(load_data):
             
         except Exception as e:
             logger.error(f"❌ Error al cargar embeddings a Qdrant desde {parquet_path}: {e}", exc_info=True)
-            return False
+            return False

embedding_flow/main.py

@@ -0,0 +1,22 @@
+from embedding_flow.transform.transform import transform_embedding
+from embedding_flow.load.load import load_embedding
+import logging
+
+logging.basicConfig(
+    level=logging.INFO,              # Nivel mínimo de logs a mostrar
+    format='%(asctime)s - %(levelname)s - %(message)s',
+    filename='appMain.log',             # Opcional: guarda los logs en un archivo
+    filemode='a'                    # 'a' append, 'w' overwrite
+)
+
+
+def embedding_flow(parquet_path: str)-> str | None  :
+    
+    transformer = transform_embedding(parquet_path)
+    of = load_embedding(transformer)
+    if of is None:
+        logging.error("❌ Pipeline failed")
+        return None
+    else:
+        logging.info("✅ Pipeline completed successfully")
+        return of

{transform → embedding_flow/transform}/transform.py

@@ -1,4 +1,4 @@
-from contracts.contracts import transform_data
+from embedding_flow.contracts.contracts import transform_data
 from pathlib import Path
 import pandas as pd
 from sentence_transformers import SentenceTransformer
@@ -39,4 +39,4 @@ class transform_embedding(transform_data):
 
         except Exception as e:
             logger.error(f"❌ Error al transformar en embeddings {parquet_path}: {e}", exc_info=True)
-            return None
+            return None

{embedding_flow-0.1.0.dist-info → embedding_flow-0.1.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: embedding-flow
-Version: 0.1.0
+Version: 0.1.1
 Summary: Pipeline to transform text chunks into embeddings and load to Qdrant
 Author: facuvega
 Classifier: Programming Language :: Python :: 3
@@ -10,6 +10,7 @@ Classifier: Programming Language :: Python :: 3.12
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Operating System :: OS Independent
 Requires-Python: >=3.10
+Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: pandas>=2.0.0
 Requires-Dist: pyarrow>=12.0.0
@@ -20,3 +21,41 @@ Provides-Extra: dev
 Requires-Dist: pytest>=7.0.0; extra == "dev"
 Requires-Dist: pytest-cov>=4.0.0; extra == "dev"
 Dynamic: license-file
+
+# embedding-flow
+
+Biblioteca para transformar chunks de texto en embeddings de 768 dimensiones y cargarlos en Qdrant.
+
+## Instalación
+
+```bash
+pip install embedding-flow
+```
+
+## Uso
+
+```python
+from embedding_flow import embedding_flow
+
+# Recibe el path del parquet con chunks y carga embeddings a Qdrant
+embedding_flow("/path/to/chunks.parquet")
+```
+
+## Variables de entorno
+
+```bash
+QDRANT_URL=http://localhost:6333
+QDRANT_COLLECTION=embeddings_collection
+VECTOR_SIZE=768
+```
+
+## Flujo
+
+1. Lee chunks desde parquet
+2. Genera embeddings (768 dim) con `all-mpnet-base-v2`
+3. Carga embeddings a Qdrant (Docker local)
+
+## Licencia
+
+MIT
+

embedding_flow-0.1.1.dist-info/RECORD

@@ -0,0 +1,13 @@
+embedding_flow/__init__.py,sha256=2M-FOuekraoC7yxnhc86gX1iwEhfWuejbqnf_AZSsag,78
+embedding_flow/main.py,sha256=e0VxDPrnAqxvcygWg5qTeUoQzm_Yt9QWBO5NbFDAjxg,752
+embedding_flow/contracts/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+embedding_flow/contracts/contracts.py,sha256=Sg1rsuFxMPx4ROHsLqIxsvhYhr371-QL5v1LiZrijXI,443
+embedding_flow/load/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+embedding_flow/load/load.py,sha256=mNkl5o6EOiTEq3qzAipGv-IPopgRnKnk1CoRTaQnIys,3722
+embedding_flow/transform/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+embedding_flow/transform/transform.py,sha256=BPLZnMaf9txbJwkw6oG-FeGI3wfuaxsxxVxoiV3dOPQ,1601
+embedding_flow-0.1.1.dist-info/licenses/LICENSE,sha256=Vi3cItkblr6fZwGbNlp_HnBaMFwXSWYPkrVQLXX3LCs,1057
+embedding_flow-0.1.1.dist-info/METADATA,sha256=-79fyZKjE1N68N5QRSm8s_G_rKpQQwaAvOVzM2rNy5w,1478
+embedding_flow-0.1.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+embedding_flow-0.1.1.dist-info/top_level.txt,sha256=ryROgL4aUmHN8Ez_pskO2-kRHYNg-wBDMTp48633S7s,15
+embedding_flow-0.1.1.dist-info/RECORD,,

embedding_flow-0.1.1.dist-info/top_level.txt

@@ -0,0 +1 @@
+embedding_flow

embedding_flow-0.1.0.dist-info/RECORD

@@ -1,11 +0,0 @@
-contracts/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-contracts/contracts.py,sha256=im3wzTHMxZFVIVyjVVN1u4eZ5J_HxYGrcu3oQ8BXoOk,441
-embedding_flow-0.1.0.dist-info/licenses/LICENSE,sha256=Vi3cItkblr6fZwGbNlp_HnBaMFwXSWYPkrVQLXX3LCs,1057
-load/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-load/load.py,sha256=Y0JbC1x7SfG_EzsSDacDK8fuIcv7K1guQ8AD0birheE,3706
-transform/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-transform/transform.py,sha256=GPeea6D2EbdNwmxdCDtDGgTGIPVLs_Z4VePYQJfzROc,1585
-embedding_flow-0.1.0.dist-info/METADATA,sha256=uFM06vDN-pagU7V_GoZ1wNU6ZPsX8MzdlxNMjV2JoaA,802
-embedding_flow-0.1.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-embedding_flow-0.1.0.dist-info/top_level.txt,sha256=VfSCJdxLtTjvyUSe1z1kQgIf0j2zFt3--FivJqWMxxA,25
-embedding_flow-0.1.0.dist-info/RECORD,,

embedding_flow-0.1.0.dist-info/top_level.txt

@@ -1,3 +0,0 @@
-contracts
-load
-transform