Merge pull request #103 from boswelja/embeder-to-embedder

Embeder -> Embedder

README.md

@@ -107,7 +107,7 @@ model = EmbeddingModel.from_pretrained_hf(
     WhichModel.Bert, model_id="model link from huggingface"
 )
 config = TextEmbedConfig(chunk_size=200, batch_size=32)
-data = embed_anything.embed_file("file_address", embeder=model, config=config)
+data = embed_anything.embed_file("file_address", embedder=model, config=config)
 ```
 
 
@@ -190,7 +190,7 @@ pip install embed-anything-gpu
 model = EmbeddingModel.from_pretrained_local(
     WhichModel.Bert, model_id="Hugging_face_link"
 )
-data = embed_anything.embed_file("test_files/test.pdf", embeder=model)
+data = embed_anything.embed_file("test_files/test.pdf", embedder=model)
 ```
 
 
@@ -206,11 +206,11 @@ model = embed_anything.EmbeddingModel.from_pretrained_local(
     model_id="openai/clip-vit-base-patch16",
     # revision="refs/pr/15",
 )
-data: list[EmbedData] = embed_anything.embed_directory("test_files", embeder=model)
+data: list[EmbedData] = embed_anything.embed_directory("test_files", embedder=model)
 embeddings = np.array([data.embedding for data in data])
 query = ["Photo of a monkey?"]
 query_embedding = np.array(
-    embed_anything.embed_query(query, embeder=model)[0].embedding
+    embed_anything.embed_query(query, embedder=model)[0].embedding
 )
 similarities = np.dot(embeddings, query_embedding)
 max_index = np.argmax(similarities)
@@ -233,7 +233,7 @@ from embed_anything import (
 audio_decoder = AudioDecoderModel.from_pretrained_hf(
     "openai/whisper-tiny.en", revision="main", model_type="tiny-en", quantized=False
 )
-embeder = EmbeddingModel.from_pretrained_hf(
+embedder = EmbeddingModel.from_pretrained_hf(
     embed_anything.WhichModel.Bert,
     model_id="sentence-transformers/all-MiniLM-L6-v2",
     revision="main",
@@ -242,7 +242,7 @@ config = TextEmbedConfig(chunk_size=200, batch_size=32)
 data = embed_anything.embed_audio_file(
     "test_files/audio/samples_hp0.wav",
     audio_decoder=audio_decoder,
-    embeder=embeder,
+    embedder=embedder,
     text_embed_config=config,
 )
 print(data[0].metadata)

docs/blog/posts/embed-anything.md

@@ -115,7 +115,7 @@ model = EmbeddingModel.from_pretrained_hf(
     WhichModel.Bert, model_id="model link from huggingface"
 )
 config = TextEmbedConfig(chunk_size=200, batch_size=32)
-data = embed_anything.embed_file("file_address", embeder=model, config=config)
+data = embed_anything.embed_file("file_address", embedder=model, config=config)
 ```
 You can check out the documentation at  https://starlight-search.com/references/ 
 

docs/blog/posts/vector-streaming.md

@@ -114,7 +114,7 @@ model = embed_anything.EmbeddingModel.from_pretrained_cloud(
 
 data = embed_anything.embed_image_directory(
     "\image_directory",
-    embeder=model,
+    embedder=model,
     adapter=weaviate_adapter,
     config=embed_anything.ImageEmbedConfig(buffer_size=100),
 )
@@ -124,7 +124,7 @@ data = embed_anything.embed_image_directory(
 #### Step 4: Query the Vector Database
 
 ```python
-query_vector = embed_anything.embed_query(["image of a cat"], embeder=model)[0].embedding
+query_vector = embed_anything.embed_query(["image of a cat"], embedder=model)[0].embedding
 ```
 
 #### Step 5: Query the Vector Database

docs/index.md

@@ -119,7 +119,7 @@ pip install embed-anything-gpu
 model = EmbeddingModel.from_pretrained_local(
     WhichModel.Bert, model_id="sentence-transformers/all-MiniLM-L6-v2"
 )
-data = embed_anything.embed_file("test_files/test.pdf", embeder=model)
+data = embed_anything.embed_file("test_files/test.pdf", embedder=model)
 ```
 
 
@@ -162,11 +162,11 @@ model = embed_anything.EmbeddingModel.from_pretrained_local(
     model_id="openai/clip-vit-base-patch16",
     # revision="refs/pr/15",
 )
-data: list[EmbedData] = embed_anything.embed_directory("test_files", embeder=model)
+data: list[EmbedData] = embed_anything.embed_directory("test_files", embedder=model)
 embeddings = np.array([data.embedding for data in data])
 query = ["Photo of a monkey?"]
 query_embedding = np.array(
-    embed_anything.embed_query(query, embeder=model)[0].embedding
+    embed_anything.embed_query(query, embedder=model)[0].embedding
 )
 similarities = np.dot(embeddings, query_embedding)
 max_index = np.argmax(similarities)
@@ -199,7 +199,7 @@ jina_config = JinaConfig(
 
 config = EmbedConfig(jina=jina_config, audio_decoder=audio_decoder_config)
 data = embed_anything.embed_file(
-    "test_files/audio/samples_hp0.wav", embeder="Audio", config=config
+    "test_files/audio/samples_hp0.wav", embedder="Audio", config=config
 )
 print(data[0].metadata)
 end_time = time.time()

examples/adapters/elastic.py

@@ -77,7 +77,7 @@ def upsert(self, data: List[Dict]):
 
 data = embed_anything.embed_file(
     "/path/to/my-file.pdf",
-    embeder="Bert",
+    embedder="Bert",
     adapter=elasticsearch_adapter,
     config=embed_config,
 )

examples/adapters/pinecone_db.py

@@ -123,7 +123,7 @@ def upsert(self, data: List[Dict]):
 
 data = embed_anything.embed_image_directory(
     "test_files",
-    embeder=clip_model,
+    embedder=clip_model,
     adapter=pinecone_adapter,
     config=embed_config,
 )

examples/adapters/weaviate_db.py

@@ -65,10 +65,10 @@ def delete_index(self, index_name: str):
 
 
 data = embed_anything.embed_directory(
-    "test_files", embeder=model, adapter=weaviate_adapter
+    "test_files", embedder=model, adapter=weaviate_adapter
 )
 
-query_vector = embed_anything.embed_query(["What is attention"], embeder=model)[
+query_vector = embed_anything.embed_query(["What is attention"], embedder=model)[
     0
 ].embedding
 

examples/audio.py

@@ -14,7 +14,7 @@
     "openai/whisper-tiny.en", revision="main", model_type="tiny-en", quantized=False
 )
 
-embeder = EmbeddingModel.from_pretrained_hf(
+embedder = EmbeddingModel.from_pretrained_hf(
     embed_anything.WhichModel.Bert,
     model_id="sentence-transformers/all-MiniLM-L6-v2",
     revision="main",
@@ -24,7 +24,7 @@
 data = embed_anything.embed_audio_file(
     "test_files/audio/samples_hp0.wav",
     audio_decoder=audio_decoder,
-    embeder=embeder,
+    embedder=embedder,
     text_embed_config=config,
 )
 print(data[0].metadata)

examples/clip.py

@@ -11,7 +11,7 @@
     model_id="openai/clip-vit-base-patch16",
 )
 data: list[EmbedData] = embed_anything.embed_image_directory(
-    "test_files", embeder=model
+    "test_files", embedder=model
 )
 
 # Convert the embeddings to a numpy array
@@ -22,7 +22,7 @@
 # Embed a query
 query = ["Photo of a monkey?"]
 query_embedding = np.array(
-    embed_anything.embed_query(query, embeder=model)[0].embedding
+    embed_anything.embed_query(query, embedder=model)[0].embedding
 )
 
 # Calculate the similarities between the query embedding and all the embeddings

examples/hybridsearch.py

@@ -50,16 +50,16 @@
     WhichModel.Jina, model_id="jinaai/jina-embeddings-v2-small-en"
 )
 
-jina_embedddings = embed_anything.embed_query(sentences, embeder=jina_model)
-jina_query = embed_anything.embed_query(query_text, embeder=jina_model)[0]
+jina_embedddings = embed_anything.embed_query(sentences, embedder=jina_model)
+jina_query = embed_anything.embed_query(query_text, embedder=jina_model)[0]
 
 
 splade_model = EmbeddingModel.from_pretrained_hf(
     WhichModel.SparseBert, "prithivida/Splade_PP_en_v1"
 )
-jina_embedddings = embed_anything.embed_query(sentences, embeder=jina_model)
+jina_embedddings = embed_anything.embed_query(sentences, embedder=jina_model)
 
-splade_query = embed_anything.embed_query(query_text, embeder=splade_model)
+splade_query = embed_anything.embed_query(query_text, embedder=splade_model)
 
 client.query_points(
     collection_name="my-hybrid-collection",

examples/onnx_models.py

@@ -25,7 +25,7 @@
     "The dog is sitting in the park",
 ]
 
-embedddings = embed_query(sentences, embeder=model)
+embedddings = embed_query(sentences, embedder=model)
 
 embed_vector = np.array([e.embedding for e in embedddings])
 

examples/semantic_chunking.py

@@ -16,7 +16,7 @@
     semantic_encoder=semantic_encoder,
 )
 
-data = embed_anything.embed_file("test_files/bank.txt", embeder=model, config=config)
+data = embed_anything.embed_file("test_files/bank.txt", embedder=model, config=config)
 
 for d in data:
     print(d.text)

examples/splade.py

@@ -22,7 +22,7 @@
     "Do you like pizza?",
 ]
 
-embedddings = embed_query(sentences, embeder=model)
+embedddings = embed_query(sentences, embedder=model)
 
 embed_vector = np.array([e.embedding for e in embedddings])
 

examples/text.py

@@ -21,7 +21,7 @@ def embed_directory_example():
 
     # Embed all files in a directory
     data: list[EmbedData] = embed_anything.embed_directory(
-        "bench", embeder=model, config=config
+        "bench", embedder=model, config=config
     )
 
     # End timing
@@ -39,7 +39,7 @@ def embed_query_example():
 
     # Embed a query
     embeddings: EmbedData = embed_anything.embed_query(
-        ["Hello world my"], embeder=model, config=config
+        ["Hello world my"], embedder=model, config=config
     )[0]
 
     # Print the shape of the embedding
@@ -48,7 +48,7 @@ def embed_query_example():
     # Embed another query and print the result
     print(
         embed_anything.embed_query(
-            ["What is the capital of India?"], embeder=model, config=config
+            ["What is the capital of India?"], embedder=model, config=config
         )
     )
 
@@ -62,7 +62,7 @@ def embed_file_example():
 
     # Embed a single file
     data: list[EmbedData] = embed_anything.embed_file(
-        "test_files/bank.txt", embeder=model, config=config
+        "test_files/bank.txt", embedder=model, config=config
     )
 
     # Print the embedded data

examples/text_ocr.py

@@ -22,7 +22,7 @@
 
 data: list[EmbedData] = embed_anything.embed_file(
     "/home/akshay/projects/starlaw/src-server/test_files/court.pdf",  # Replace with your file path
-    embeder=model,
+    embedder=model,
     config=config,
 )
 end = time()

examples/web.py

@@ -1,3 +1,3 @@
 import embed_anything
 
-data = embed_anything.embed_webpage("https://www.akshaymakes.com/", embeder="Bert")
+data = embed_anything.embed_webpage("https://www.akshaymakes.com/", embedder="Bert")

python/python/embed_anything/__init__.py

@@ -21,7 +21,7 @@
 model = EmbeddingModel.from_pretrained_local(
     WhichModel.Bert, model_id="Hugging_face_link"
 )
-data = embed_anything.embed_file("test_files/test.pdf", embeder=model)
+data = embed_anything.embed_file("test_files/test.pdf", embedder=model)
 
 
 #For images
@@ -30,11 +30,11 @@
     model_id="openai/clip-vit-base-patch16",
     # revision="refs/pr/15",
 )
-data: list[EmbedData] = embed_anything.embed_directory("test_files", embeder=model)
+data: list[EmbedData] = embed_anything.embed_directory("test_files", embedder=model)
 embeddings = np.array([data.embedding for data in data])
 query = ["Photo of a monkey?"]
 query_embedding = np.array(
-    embed_anything.embed_query(query, embeder=model)[0].embedding
+    embed_anything.embed_query(query, embedder=model)[0].embedding
 )
 # For audio files
 from embed_anything import (
@@ -47,7 +47,7 @@
 audio_decoder = AudioDecoderModel.from_pretrained_hf(
     "openai/whisper-tiny.en", revision="main", model_type="tiny-en", quantized=False
 )
-embeder = EmbeddingModel.from_pretrained_hf(
+embedder = EmbeddingModel.from_pretrained_hf(
     embed_anything.WhichModel.Bert,
     model_id="sentence-transformers/all-MiniLM-L6-v2",
     revision="main",
@@ -56,7 +56,7 @@
 data = embed_anything.embed_audio_file(
     "test_files/audio/samples_hp0.wav",
     audio_decoder=audio_decoder,
-    embeder=embeder,
+    embedder=embedder,
     text_embed_config=config,
 )
 
@@ -98,7 +98,7 @@
 
 data = embed_anything.embed_image_directory(
     "test_files",
-    embeder=clip_model,
+    embedder=clip_model,
     adapter=pinecone_adapter,
     # config=embed_config,
 ```