Update app.py

app.py

@@ -109,22 +109,34 @@ def search_arxiv(query):
     #llm_model = st.sidebar.selectbox(key='llmmodel', label="LLM Model", ["mistralai/Mixtral-8x7B-Instruct-v0.1", "mistralai/Mistral-7B-Instruct-v0.2", "google/gemma-7b-it", "None"])
     llm_model = "mistralai/Mixtral-8x7B-Instruct-v0.1"
 
-    
     st.sidebar.markdown('### 🔎 ' + query)
-    result = client.predict(
-        search_query,
-        100,
-        search_source,
-        llm_model,
-        api_name="/update_with_rag_md"
+
+
+
+    # ArXiv searcher ~-<>-~ Paper Summary - Ask LLM
+    client = Client("awacke1/Arxiv-Paper-Search-And-QA-RAG-Pattern")
+    response2 = client.predict(
+            query,	# str  in 'parameter_13' Textbox component
+            "mistralai/Mixtral-8x7B-Instruct-v0.1",	# Literal['mistralai/Mixtral-8x7B-Instruct-v0.1', 'mistralai/Mistral-7B-Instruct-v0.2', 'google/gemma-7b-it', 'None']  in 'LLM Model' Dropdown component
+            True,	# bool  in 'Stream output' Checkbox component
+            api_name="/ask_llm"
     )
-    result = parse_to_markdown(result)
-    
-    #st.markdown(result)
-    #arxiv_results = st.text_area("ArXiv Results: ", value=result, height=700)
-    
-    result = str(result) # cast as string for these - check content length and format if encoding changes..
-    result=result.replace('\\n', ' ')
+    st.write('🔍Run of Multi-Agent System Paper Summary Spec is Complete')
+    st.markdown(response2)
+
+    # ArXiv searcher ~-<>-~ Paper References - Update with RAG
+    client = Client("awacke1/Arxiv-Paper-Search-And-QA-RAG-Pattern")
+    response1 = client.predict(
+    		query,	
+    		10,	
+    		"Semantic Search - up to 10 Mar 2024",	# Literal['Semantic Search - up to 10 Mar 2024', 'Arxiv Search - Latest - (EXPERIMENTAL)']  in 'Search Source' Dropdown component
+    		"mistralai/Mixtral-8x7B-Instruct-v0.1",	# Literal['mistralai/Mixtral-8x7B-Instruct-v0.1', 'mistralai/Mistral-7B-Instruct-v0.2', 'google/gemma-7b-it', 'None']  in 'LLM Model' Dropdown component
+    		api_name="/update_with_rag_md"
+    )
+    st.write('🔍Run of Multi-Agent System Paper References is Complete')
+    responseall = response1[0] + response1[1]
+    st.markdown(responseall)
+    result = response2 + responseall
 
     SpeechSynthesis(result)  # Search History Reader / Writer IO Memory - Audio at Same time as Reading.
     
@@ -262,85 +274,63 @@ roleplaying_glossary = {
 "Supports various AI algorithms and models"
 ]
 },
-"🚀 World Ship Design": {
-"ShipHullGAN 🌊": [
-"Generic parametric modeller for ship hull design",
-"Uses deep convolutional generative adversarial networks (GANs)",
-"Trained on diverse ship hull designs",
-"Generates geometrically valid and feasible ship hull shapes",
-"Enables exploration of traditional and novel designs",
-"From the paper 'ShipHullGAN: A generic parametric modeller for ship hull design using deep convolutional generative model'"
-],
-"B\'ezierGAN 📐": [
-"Automatic generation of smooth curves",
-"Maps low-dimensional parameters to B\'ezier curve points",
-"Generates diverse and realistic curves",
-"Preserves shape variation in latent space",
-"Useful for design optimization and exploration",
-"From the paper 'B\'ezierGAN: Automatic Generation of Smooth Curves from Interpretable Low-Dimensional Parameters'"
-],
-"PlotMap 🗺️": [
-"Automated game world layout design",
-"Uses reinforcement learning to place plot elements",
-"Considers spatial constraints from story",
-"Enables procedural content generation for games",
-"Handles multi-modal inputs (images, locations, text)",
-"From the paper 'PlotMap: Automated Layout Design for Building Game Worlds'"
+"🔬 Science Topics": {
+"Physics 🔭": [
+"Astrophysics: galaxies, cosmology, planets, high energy phenomena, instrumentation, solar/stellar",
+
+"Condensed Matter: disordered systems, materials science, nano/mesoscale, quantum gases, soft matter, statistical mechanics, superconductivity",
+"General Relativity and Quantum Cosmology",
+"High Energy Physics: experiment, lattice, phenomenology, theory",
+"Mathematical Physics",
+"Nonlinear Sciences: adaptation, cellular automata, chaos, solvable systems, pattern formation",
+"Nuclear: experiment, theory",
+"Physics: accelerators, atmospherics, atomic/molecular, biophysics, chemical, computational, education, fluids, geophysics, optics, plasma, popular, space"
 ],
-"ShipGen ⚓": [
-"Diffusion model for parametric ship hull generation",
-"Considers multiple objectives and constraints",
-"Generates tabular parametric design vectors",
-"Uses classifier guidance to improve hull quality",
-"Reduces design time and generates high-performing hulls",
-"From the paper 'ShipGen: A Diffusion Model for Parametric Ship Hull Generation with Multiple Objectives and Constraints'"
-],
-"Ship-D 📊": [
-"Large dataset of ship hulls for machine learning",
-"30,000 hulls with design and performance data",
-"Includes parameterization, mesh, point cloud, images",
-"Measures hydrodynamic drag under different conditions",
-"Enables data-driven ship design optimization",
-"From the paper 'Ship-D: Ship Hull Dataset for Design Optimization using Machine Learning'"
-]
-},
-"🌌 Exploring the Universe":{
-"Cosmos 🪐": [
-"Object-centric world modeling framework",
-"Designed for compositional generalization",
-"Uses neurosymbolic grounding",
-"Neurosymbolic scene encodings and attention mechanism",
-"Computes symbolic attributes using vision-language models",
-"From the paper 'Neurosymbolic Grounding for Compositional World Models'"
+"Mathematics ➗": [
+"Algebra: geometry, topology, number theory, combinatorics, representation theory",
+"Analysis: PDEs, functional, numerical, spectral theory, ODEs, complex variables",
+"Geometry: algebraic, differential, metric, symplectic, topological",
+"Probability and Statistics",
+"Applied Math: information theory, optimization and control"
 ],
-"Active World Model Learning 🔭": [
-"Curiosity-driven exploration for world model learning",
-"Constructs agent to visually explore 3D environment",
-"Uses progress-based curiosity signal ($\gamma$-Progress)",
-"Overcomes 'white noise problem' in exploration",
-"Outperforms baseline exploration strategies",
-"From the paper 'Active World Model Learning with Progress Curiosity'"
+"Computer Science 💻": [
+"Artificial Intelligence and Machine Learning",
+
+"Computation and Language, Complexity, Engineering, Finance, Science",
+"Computer Vision, Graphics, Robotics",
+"Cryptography, Security, Blockchain",
+"Data Structures, Algorithms, Databases",
+"Distributed and Parallel Computing",
+"Formal Languages, Automata, Logic",
+"Information Theory, Signal Processing",
+"Networks, Internet Architecture, Social Networks",
+"Programming Languages, Software Engineering"
 ],
-"Probabilistic Worldbuilding 🎲": [
-"Symbolic Bayesian model for semantic parsing and reasoning",
-"Aims for general natural language understanding",
-"Expresses meaning in human-readable formal language",
-"Designed to generalize to new domains and tasks",
-"Outperforms baselines on out-of-domain question answering",
-"From the paper 'Towards General Natural Language Understanding with Probabilistic Worldbuilding'"
+"Quantitative Biology 🧬": [
+"Biomolecules, Cell Behavior, Genomics",
+"Molecular Networks, Neurons and Cognition",
+"Populations, Evolution, Ecology",
+"Quantitative Methods, Subcellular Processes",
+"Tissues, Organs, Organisms"
 ],
-"Language-Guided World Models 💬": [
-"Capture environment dynamics from language descriptions",
-"Allow efficient communication and control",
-"Enable self-learning from human instruction texts",
-"Tested on challenging benchmark requiring generalization",
-"Improves interpretability and safety via generated plans",
-"From the paper 'Language-Guided World Models: A Model-Based Approach to AI Control'"
 
+"Quantitative Finance 📈": [
+"Computational and Mathematical Finance",
+"Econometrics and Statistical Finance",
+
+"Economics, Portfolio Management, Trading",
+"Pricing, Risk Management"
+],
+"Electrical Engineering 🔌": [
+"Audio, Speech, Image and Video Processing",
+"Communications and Information Theory",
+"Signal Processing, Controls, Robotics",
+"Electronic Circuits, Embedded Systems"
 ]
 }
 }
 
+
 @st.cache_resource
 def get_table_download_link(file_path):
 
@@ -571,13 +561,12 @@ image_urls = [
     "https://cdn-uploads.huggingface.co/production/uploads/620630b603825909dcbeba35/cmCZ5RTdSx3usMm7MwwWK.png",
 ]
 
-try:
-    selected_image_url = random.choice(image_urls)
-    selected_image_base64 = get_image_as_base64(selected_image_url)
-    if selected_image_base64 is not None:
-        with st.sidebar:
-            st.markdown(f"![image](data:image/png;base64,{selected_image_base64})")
-except:
+selected_image_url = random.choice(image_urls)
+selected_image_base64 = get_image_as_base64(selected_image_url)
+if selected_image_base64 is not None:
+    with st.sidebar:
+        st.markdown(f"![image](data:image/png;base64,{selected_image_base64})")
+else:
     st.sidebar.write("Failed to load the image.")
 
 # Ensure the directory for storing scores exists
@@ -611,8 +600,10 @@ def load_score(key):
         return score_data["score"]
     return 0
 
+
+ # 🔍Run--------------------------------------------------------
 @st.cache_resource
-def search_glossary(query):  # 🔍Run--------------------------------------------------------
+def search_glossary(query): 
     for category, terms in roleplaying_glossary.items():
         if query.lower() in (term.lower() for term in terms):
             st.markdown(f"#### {category}")
@@ -622,11 +613,21 @@ def search_glossary(query):  # 🔍Run------------------------------------------
     # 🔍Run 1 - plain query
     #response = chat_with_model(query)  
     #response1 = chat_with_model45(query) 
-    
     #all = query + '   ' + response1
     #st.write('🔍Run 1 is Complete.')
 
-    # ArXiv searcher ~-<>-~
+    # ArXiv searcher ~-<>-~ Paper Summary - Ask LLM
+    client = Client("awacke1/Arxiv-Paper-Search-And-QA-RAG-Pattern")
+    response2 = client.predict(
+            query,	# str  in 'parameter_13' Textbox component
+            "mistralai/Mixtral-8x7B-Instruct-v0.1",	# Literal['mistralai/Mixtral-8x7B-Instruct-v0.1', 'mistralai/Mistral-7B-Instruct-v0.2', 'google/gemma-7b-it', 'None']  in 'LLM Model' Dropdown component
+            True,	# bool  in 'Stream output' Checkbox component
+            api_name="/ask_llm"
+    )
+    st.write('🔍Run of Multi-Agent System Paper Summary Spec is Complete')
+    #st.markdown(response2)
+
+    # ArXiv searcher ~-<>-~ Paper References - Update with RAG
     client = Client("awacke1/Arxiv-Paper-Search-And-QA-RAG-Pattern")
     response1 = client.predict(
     		query,	
@@ -635,26 +636,23 @@ def search_glossary(query):  # 🔍Run------------------------------------------
     		"mistralai/Mixtral-8x7B-Instruct-v0.1",	# Literal['mistralai/Mixtral-8x7B-Instruct-v0.1', 'mistralai/Mistral-7B-Instruct-v0.2', 'google/gemma-7b-it', 'None']  in 'LLM Model' Dropdown component
     		api_name="/update_with_rag_md"
     )
-    st.write('🔍Run of Multi-Agent Systems is Complete')
-
-# experimental 45 - - - - - - - - - - - - -<><><><><>
+    st.write('🔍Run of Multi-Agent System Paper References is Complete')
+    #st.markdown(response1)
 
+    responseall = response2 + response1[0] + response1[1]
+    st.markdown(responseall)
+    return responseall
 
+# GPT 35 turbo and GPT 45 - - - - - - - - - - - - -<><><><><>:
     RunPostArxivLLM = False
-
     if RunPostArxivLLM:
-        
         # 🔍Run PaperSummarizer
         PaperSummarizer = '  Create a paper summary as a markdown table with paper links clustering the features writing short markdown emoji outlines to extract three main ideas from each of the ten summaries. For each one create three simple points led by an emoji of the main three steps needed as method step process for implementing the idea as a single app.py streamlit python app.  '
-        # = str(result).replace('\n', ' ').replace('|', '   ')
-    #    response2 = chat_with_model45(PaperSummarizer + str(response1))        
         response2 = chat_with_model(PaperSummarizer + str(response1))        
         st.write('🔍Run 3 - Paper Summarizer is Complete.')
     
         # 🔍Run AppSpecifier
-        AppSpecifier = '  Design and write a streamlit python code listing and specification that implements each scientific method steps as ten functions keeping specification in a markdown table in the function comments with original paper link to outline the AI pipeline ensemble implementing code as full plan to build.'
-        #result = str(result).replace('\n', ' ').replace('|', '   ')
-    #    response3 = chat_with_model45(AppSpecifier + str(response2))        
+        AppSpecifier = '  Design and write a streamlit python code listing and specification that implements each scientific method steps as ten functions keeping specification in a markdown table in the function comments with original paper link to outline the AI pipeline ensemble implementing code as full plan to build.'       
         response3 = chat_with_model(AppSpecifier + str(response2))        
         st.write('🔍Run 4 - AppSpecifier is Complete.')
         
@@ -1377,7 +1375,6 @@ What is SORA?
 '''
 
 
-# Search History to ArXiv
 session_state = {}
 if "search_queries" not in session_state:
     session_state["search_queries"] = []
@@ -1388,12 +1385,10 @@ if example_input:
     # Search AI
     query=example_input
     if query: 
-        try:
-            result = search_arxiv(query)
-            #search_glossary(query)
-            search_glossary(result)
-        except:
-            st.markdown(' ')
+        result = search_arxiv(query)
+        #search_glossary(query)
+        search_glossary(result)
+    st.markdown(' ')
                              
 st.write("Search history:")
 for example_input in session_state["search_queries"]: