adding more features to the app

app.py

@@ -1,4 +1,6 @@
 import gradio as gr
+from weaviate_utils import init_client
+
 from structured_apparatus_chain import (
     arxiv_chain as apparatus_arxiv_chain, 
     pub_med_chain as apparatus_pub_med_chain, 
@@ -10,7 +12,6 @@ from structured_experiment_chain import (
     wikipedia_chain as experiment_wikipedia_chain
 )
 
-from weaviate_utils import init_client
 
 apparatus_retriever_options = {
     "Arxiv": apparatus_arxiv_chain,
@@ -27,6 +28,19 @@ experiment_retriever_options = {
 def generate_apparatus(input_text, retriever_choice):
     selected_chain = apparatus_retriever_options[retriever_choice]
     output_text = selected_chain.invoke(input_text)
+    weaviate_client = init_client()
+    app_components =  output_text["Material"]
+    component_collection = weaviate_client.collections.get("Component")
+    
+    for i in app_components:
+
+        app_uuid = component_collection.data.insert({
+            "Tags": output_text['Fields_of_study'],
+            "FeildsOfStudy" : output_text['Fields_of_study'],
+            "ToolName" : i,
+            "UsedInComps" : [input_text]
+        })
+    
     return output_text
 
 def generate_experiment(input_text, retriever_choice):
@@ -51,15 +65,31 @@ def generate_experiment(input_text, retriever_choice):
     })
     return output_text
 
-def process_text(input_text, number):
+def search_experiments(input_text, number):
     # Example processing function
     weaviate_client = init_client()
     science_experiment_collection = weaviate_client.collections.get("ScienceEperiment")
     response = science_experiment_collection.query.bm25(
             query=input_text,
-            limit=3
+            limit=number
         )
-    return response.objects.__str__()
+    weaviate_client.close()
+    response_objects_string = "\n\n".join([str(obj) for obj in response.objects])
+    return response_objects_string
+
+def search_apparatus(input_text, number):
+    # Example processing function
+    weaviate_client = init_client()
+    component_collection = weaviate_client.collections.get("Component")
+    response = component_collection.query.bm25(
+            query=input_text,
+            limit=number
+        )
+    # print(response.objects.__str__())
+    response_objects_string = "\n\n".join([str(obj) for obj in response.objects])
+    weaviate_client.close()
+    
+    return response_objects_string
 
 generate_apparatus_interface = gr.Interface(
     fn=generate_apparatus,
@@ -77,19 +107,28 @@ generate_experiment_interface = gr.Interface(
     description="I am here to generate and store science experiments for our users",
 )
 
-process_text_interface = gr.Interface(
-    fn=process_text,
+search_experiments_interface = gr.Interface(
+    fn=search_experiments,
     inputs=["text", gr.Slider(minimum=2, maximum=6, step=1, value=2, label="Select a number")],
     outputs="text",
     title="Search Existing Experiments",
     description="If you would like an idea of the experiments in the vectorestore here is the place",
 )
 
+search_apparatus_interface = gr.Interface(
+    fn=search_apparatus,
+    inputs=["text", gr.Slider(minimum=2, maximum=6, step=1, value=2, label="Select a number")],
+    outputs="text",
+    title="Search Existing Apparatuses",
+    description="If you would like an idea of the apparatuses in the vectorestore here is the place",
+)
+
 demo = gr.TabbedInterface([
     generate_apparatus_interface, 
     generate_experiment_interface,
-    process_text_interface
-], ["Generate Apparatus", "Generate Experiment", "Search Existing Experiments"])
+    search_experiments_interface,
+    search_apparatus_interface,
+], ["Generate Apparatus", "Generate Experiment", "Search Existing Experiments","Search Existing Apparatuses"])
 
 if __name__ == "__main__":
     demo.launch()

chain_apparatarus_weaviate.py

@@ -0,0 +1,89 @@
+# goal: store results from app.py into vector store
+
+from structured_apparatus_chain import (
+    arxiv_chain as apparatus_arxiv_chain, 
+    pub_med_chain as apparatus_pub_med_chain, 
+    wikipedia_chain as apparatus_wikipedia_chain
+)
+from structured_experiment_chain import (
+    arxiv_chain as experiment_arxiv_chain, 
+    pub_med_chain as experiment_pub_med_chain, 
+    wikipedia_chain as experiment_wikipedia_chain
+)
+
+from weaviate_utils import init_client
+
+from datetime import datetime, timezone
+
+
+
+
+def main():
+    # exp_qury = "fabricating cellolouse based electronics"
+    # exp_qury = "fabrication of spider silk"
+    # app_query = "microscope"
+    # app_query = "A gas Condenser"
+    app_query = "Electron Microscope"
+    app_data = apparatus_arxiv_chain.invoke(app_query)
+    # exp_data = experiment_arxiv_chain.invoke(exp_qury)
+    
+    weaviate_client = init_client()
+    
+    component_collection = weaviate_client.collections.get("Component")
+    component_image_collection = weaviate_client.collections.get("ComponentImage")
+    science_experiment_collection = weaviate_client.collections.get("ScienceEperiment")
+    
+    app_components =  app_data["Material"]
+    
+    for i in app_components:
+    
+        app_uuid = component_collection.data.insert({
+            "Tags": app_data['Fields_of_study'],
+            "FeildsOfStudy" : app_data['Fields_of_study'],
+            "ToolName" : i,
+            "UsedInComps" : [app_query]
+        })
+    
+    response = component_collection.query.bm25(
+            query="something that goes in a microscope",
+            limit=5
+        )
+    
+    # exp_uuid = science_experiment_collection.data.insert({
+    #     # "DateCreated": datetime.now(timezone.utc),
+    #     "FieldsOfStudy": exp_data['Fields_of_study'],
+    #     "Tags": exp_data['Fields_of_study'],
+    #     "Experiment_Name": exp_data['Experiment_Name'],
+    #     "Material": exp_data['Material'],
+    #     "Sources": exp_data['Sources'],
+    #     "Protocal": exp_data['Protocal'],
+    #     "Purpose_of_Experiments": exp_data['Purpose_of_Experiments'],
+    #     "Safety_Precaution": exp_data['Safety_Precuation'],  # Corrected spelling mistake
+    #     "Level_of_Difficulty": exp_data['Level_of_Difficulty'],
+    # })
+    
+    response = science_experiment_collection.query.bm25(
+            query="silk",
+            limit=3
+        )
+    
+    jj = science_experiment_collection.query.near_text(
+        query="biology",
+        limit=2
+    )
+    
+    
+    
+    # uuid = component_collection.data.insert({
+    #     "DateCreated" : datetime.now(timezone.utc),
+    #     "UsedInComps" : [query],
+    #     "ToolName" : shap_e_sample,
+    #     "Tags" : shap_e_list,
+    #     "feildsOfStudy" : shap_e_list,
+    #     # "GlbBlob" : base_64_result,
+    # })
+    
+    x = 0
+
+if __name__ == '__main__':
+    main()

chain_weaviate.py → chain_experiments_weaviate.py

@@ -45,6 +45,11 @@ def main():
         "Level_of_Difficulty": exp_data['Level_of_Difficulty'],
     })
     
+    response = science_experiment_collection.query.bm25(
+            query="silk",
+            limit=3
+        )
+    
     jj = science_experiment_collection.query.near_text(
         query="biology",
         limit=2

mesh_utils.py

@@ -0,0 +1,48 @@
+from stl import mesh
+from mpl_toolkits import mplot3d
+from matplotlib import pyplot as plt
+from typing import List, Tuple
+
+def generate_mesh_images(file_path: str, viewing_angles: List[Tuple[int, int]], output_prefix: str = 'mesh_') -> None:
+    """
+    Generate images of an STL file from different viewing angles.
+
+    Args:
+        file_path (str): Path to the STL file.
+        viewing_angles (List[Tuple[int, int]]): List of tuples containing the elevation and azimuth angles for viewing.
+        output_prefix (str, optional): Prefix for the output image filenames. Defaults to 'mesh_'.
+    """
+    # Load the STL file
+    your_mesh = mesh.Mesh.from_file(file_path)
+
+    # Iterate over each viewing angle and generate an image
+    for i, (elev, azim) in enumerate(viewing_angles, start=1):
+        # Create a new plot with a larger figure size
+        fig = plt.figure(figsize=(10, 10))
+        ax = fig.add_subplot(111, projection='3d')
+
+        # Add the STL file to the plot
+        ax.add_collection3d(mplot3d.art3d.Poly3DCollection(your_mesh.vectors))
+
+        # Calculate the limits of the mesh
+        max_dim = max(your_mesh.points.flatten())
+        min_dim = min(your_mesh.points.flatten())
+
+        # Set the limits of the plot
+        ax.set_xlim([min_dim, max_dim])
+        ax.set_ylim([min_dim, max_dim])
+        ax.set_zlim([min_dim, max_dim])
+
+        # Set the viewing angle
+        ax.view_init(elev=elev, azim=azim)
+
+        # Save the plot as an image
+        plt.savefig(f'{output_prefix}{i}.png')
+
+        # Close the plot to avoid memory leaks
+        plt.close()
+
+# Example usage:
+file_path = 'sample_data.stl'
+viewing_angles = [(30, 45), (60, 90), (45, 135)]
+generate_mesh_images(file_path, viewing_angles)