Update app.py

app.py

@@ -1,151 +1,42 @@
-from beyondllm import source,retrieve,embeddings,llms,generator
-import os
-from getpass import getpass
-from beyondllm.vectordb import ChromaVectorDb
-import json
-from graphviz import Digraph
-import graphviz
 import streamlit as st
-from beyondllm.llms import AzureOpenAIModel
-from beyondllm.embeddings import AzureAIEmbeddings
-from Json_2_tree import json_to_dot
-
-# os.environ["PATH"] += os.pathsep + 'Graphiviz/Graphviz-11.0.0-win64/bin/bin/'
-# os.environ["PATH"] += os.pathsep + "Graphviz2.38/bin/dot.exe"
-
-st.title("Chat with document")
-
-st.text("Enter API Key")
-
-# api_key = st.text_input("API Key:", type="password")
-# os.environ['OPENAI_API_KEY'] = api_key
-st.success("API Key entered successfully!")
-
-st.caption("Upload a PDF document to get information from the document.")
-uploaded_file = st.file_uploader("Choose a PDF file", type='pdf')
-submit=st.button("Get the data")
-if submit:
-
-    question = "Give Decision taken in the document"
-    system_prompt = '''You are a business analyst with extensive knowledge of legal documents and regulatory documentation.
-    Your expertise is in helping people understand and extract key information from such documents. 
-    Your task is to extract the rules and exceptions in a way that enables the creation of a decision tree, facilitating integration into the proper flow.
-    Legal Document Context: {context}
-    
-    Create a decision tree in JSON format based on the following structure:
-
-    Write a question and question should be two response like yes or no. if yes it has fallowing answers or other question 
-        - If Yes, the result should be: "Not restricted" additional -Council regulations: provide dates and articles if possible.
-        - If No, proceed to the next question2.( by giving some link to the next question not direct to next question)
-
-    2. Next question based on the previous question outcome.
-        - If Yes, the result should be: "Not restricted" additional -Council regulations: provide dates and articles if possible.
-        - If No, proceed to the next question.
-    In simple terms - flow chat if conditons.
-    [Continue this structure for as many questions as needed, ensuring each question branches into Yes/No answers and provides appropriate results based on the Council regulations.]
-    Please continue this format for as many questions as needed, ensuring each question follows the same structure.
-    Output is the JSON response follow this pattern: Do not change everytime Json output
-    This is JSON output Example, add more questions in this formate only. 
-        {
-        "Question1": ,
-        "Yes": {
-            "Result": ,
-            "Council regulations": 
-        },
-        "No": {
-            "Question2": ,
-            "Yes": {
-                "Result":,
-                "Council regulations": 
-            },
-            "No": {
-                "Question3": ,
-                "Yes": {
-                    "Result": ,
-                    "Council regulations":
-                },
-                "No": {
-                    "Result": ,
-                    "Council regulations": 
-                }
-            }
-        }
-    }
-    Additional Instructions:
-    
-    Analyze the entire document to identify all relevant rules and exceptions.
-    Ensure that the descriptions of rules and exceptions are clear and concise.
-    Include relevant dates, jurisdictions, and specific regulations where applicable.
-    Structure the questions and answers to facilitate the creation of a logical decision tree or workflow.
-    If the regulation mentions specific products, territories, or operations, include them in the appropriate sections.
-    Aim to simplify legal language while maintaining accuracy and intent.
-    [Provide your answer in JSON form. Reply with only the answer in JSON form and include no other commentary]:
-    Provide your answer in JSON form. Reply with only the answer in JSON form and include no other commentary
-
-    Return Valid Json to create Tree 
-    '''
-
-    
-
-    if uploaded_file is not None and question:
-
-        save_path = "./uploaded_files"
-        if not os.path.exists(save_path):
-            os.makedirs(save_path)
-        file_path = os.path.join(save_path, uploaded_file.name)
-        with open(file_path, "wb") as f:
-            f.write(uploaded_file.getbuffer())
-
-        data = source.fit(file_path, dtype="pdf", chunk_size=1024, chunk_overlap=0)
-        embed_model = AzureAIEmbeddings(
-                endpoint_url="https://marketplace.openai.azure.com/",
-                azure_key="d6d9522a01c74836907af2f3fd72ff85",
-                api_version="2024-02-01",
-                deployment_name="text-embed-marketplace")
-
-        retriever = retrieve.auto_retriever(data, embed_model, type="normal", top_k=4)
-        # vectordb = ChromaVectorDb(collection_name="my_persistent_collection", persist_directory="./db/chroma/")
-
-        # llm = llms.ChatOpenAIModel()
-        BASE_URL = "https://gpt-res.openai.azure.com/"
-        DEPLOYMENT_NAME= "gpt-4-32k" 
-        API_KEY = "a20bc67dbd7c47ed8c978bbcfdacf930"
-        llm = AzureOpenAIModel(model="gpt4",azure_key = API_KEY,deployment_name=DEPLOYMENT_NAME ,endpoint_url=BASE_URL,model_kwargs={"max_tokens":512,"temperature":0.1})
-        pipeline = generator.Generate(question=question, system_prompt=system_prompt, retriever=retriever, llm=llm)
-        decision_tree_json = pipeline.call()
-        response = json.loads(decision_tree_json)
-        # Function to recursively create DOT format from JSON
-        def json_to_dot(graph, node_id, parent_node, parent_label):
-            if isinstance(parent_node, dict):
-                for key, value in parent_node.items():
-                    if key.startswith("Question"):
-                        question_id = f"{node_id}_{key}"
-                        label_text = "\n".join(value[i:i+30] for i in range(0, len(value), 30))
-                        shape = 'diamond' if len(value) > 50 else 'box'
-                        graph.node(question_id, label_text, shape=shape, style='filled', fillcolor='lightblue')
-                        graph.edge(parent_label, question_id, color='black')
-                        json_to_dot(graph, question_id, value, question_id)
-                    elif key in ["Yes", "No"]:
-                        option_label = f"{node_id}_{key}"
-                        graph.node(option_label, key, shape='box', style='filled', fillcolor='lightgreen' if key == "Yes" else 'lightcoral')
-                        graph.edge(parent_label, option_label, label=key, color='black')
-                        json_to_dot(graph, option_label, value, option_label)
-                    elif key == "Result":
-                        result_label = f"{node_id}_{key}"
-                        result_str = f"{key}: {value}\nCouncil regulations: {parent_node['Council regulations']}"
-                        graph.node(result_label, result_str, shape='box', style='filled', fillcolor='lightgrey')
-                        graph.edge(parent_label, result_label, color='black')
-
-        # Create a new graph
-        dot = graphviz.Digraph(comment='Decision Tree')
-        # Add the root node
-        dot.node('Root', 'Start', shape='ellipse', style='filled', fillcolor='lightyellow')
-        # Build the DOT format
-        json_to_dot(dot, "Root", response, "Root")
-        # Render and display the graph using Graphviz engine
-        dot.format = 'png'
-        dot.render('decision_tree', view=True)
-        import streamlit as st
-        with st.chat_message(""):
-            st.write("")
-            st.image('decision_tree.png', caption='tree from json')
+import pandas as pd
+import numpy as np
+
+st.title('Uber pickups in NYC')
+
+DATE_COLUMN = 'date/time'
+DATA_URL = ('https://s3-us-west-2.amazonaws.com/'
+            'streamlit-demo-data/uber-raw-data-sep14.csv.gz')
+
+@st.cache_data
+def load_data(nrows):
+    data = pd.read_csv(DATA_URL, nrows=nrows)
+    lowercase = lambda x: str(x).lower()
+    data.rename(lowercase, axis='columns', inplace=True)
+    data[DATE_COLUMN] = pd.to_datetime(data[DATE_COLUMN])
+    return data
+
+data_load_state = st.text('Loading data...')
+data = load_data(10000)
+data_load_state.text("Done! (using st.cache)")
+
+if st.checkbox('Show raw data'):
+    st.subheader('Raw data')
+    st.write(data)
+
+st.subheader('Number of pickups by hour')
+hist_values = np.histogram(data[DATE_COLUMN].dt.hour, bins=24, range=(0,24))[0]
+st.bar_chart(hist_values)
+
+# Some number in the range 0-23
+hour_to_filter = st.slider('hour', 0, 23, 17)
+filtered_data = data[data[DATE_COLUMN].dt.hour == hour_to_filter]
+
+st.subheader('Map of all pickups at %s:00' % hour_to_filter)
+st.map(filtered_data)
+
+uploaded_file = st.file_uploader("Choose a file")
+if uploaded_file is not None:
+    st.write(uploaded_file.name)
+    bytes_data = uploaded_file.getvalue()
+    st.write(len(bytes_data), "bytes")