Now loads in embedding model locally in Dockerfile

Dockerfile

@@ -1,11 +1,24 @@
 # First stage: build dependencies
 FROM public.ecr.aws/docker/library/python:3.10.13-slim AS build
 
+# Install wget
+RUN apt-get update && apt-get install -y wget
+
+# Create a directory for the model
+RUN mkdir /model
+
 WORKDIR /src
 
 COPY requirements.txt .
 
-RUN pip install --no-cache-dir -r requirements.txt
+RUN pip install -r requirements.txt
+
+# Download the model during the build process
+RUN curl -s https://packagecloud.io/install/repositories/github/git-lfs/script.deb.sh | bash
+RUN apt-get install git-lfs -y
+RUN git lfs install
+RUN git clone https://huggingface.co/BAAI/bge-small-en-v1.5 /model/bge
+RUN rm -rf /model/bge/.git
 
 # Second stage: final image
 FROM build AS final

app.py

@@ -190,7 +190,10 @@ depends on factors such as the type of documents or queries. Information taken f
     semantic_query.submit(bge_simple_retrieval, inputs=[semantic_query, vectorstore_state, ingest_docs, in_semantic_column, k_val, out_passages, semantic_min_distance, vec_weight, join_data_state, in_join_column, search_df_join_column], outputs=[semantic_output_single_text, semantic_output_file])
 
 # Simple run for HF spaces or local on your computer
-block.queue().launch(debug=True) 
+#block.queue().launch(debug=True) 
+
+# Running on local server without specifying port
+block.queue().launch(server_name="0.0.0.0") 
 
 # Running on local server without https
 #block.queue().launch(server_name="0.0.0.0", server_port=7861, ssl_verify=False)

search_funcs/semantic_functions.py

@@ -43,10 +43,27 @@ PandasDataFrame = Type[pd.DataFrame]
 
 # Load embeddings
 embeddings_name = "BAAI/bge-small-en-v1.5"
-local_embeddings_location = "model/bge/"
 
-# Not using SentenceTransformer here
-embeddings_model = SentenceTransformer(embeddings_name)
+# Define a list of possible local locations to search for the model
+local_embeddings_locations = [
+    "model/bge/", # Potential local location
+    "/model/bge/", # Potential location in Docker container
+    "/home/user/app/model/bge/" # This is inside a Docker container
+]
+
+# Attempt to load the model from each local location
+for location in local_embeddings_locations:
+    try:
+        embeddings_model = SentenceTransformer(location)
+        print(f"Found local model installation at: {location}")
+        break  # Exit the loop if the model is found
+    except Exception as e:
+        print(f"Failed to load model from {location}: {e}")
+        continue
+else:
+    # If the loop completes without finding the model in any local location
+    embeddings_model = SentenceTransformer(embeddings_name)
+    print("Could not find local model installation. Downloading from Huggingface")
     
 def docs_to_bge_embed_np_array(docs_out, in_file, embeddings_state, output_file_state, clean, return_intermediate_files = "No", embeddings_super_compress = "No", embeddings_model = embeddings_model, progress=gr.Progress(track_tqdm=True)):
     '''