Update short.py

short.py

@@ -1,144 +1,144 @@
-from pydantic import BaseModel,Field
-from typing import TypedDict, Annotated
-from langgraph.graph import MessagesState,StateGraph, START, END
-from langchain_community.tools import TavilySearchResults
-from langchain_core.messages import SystemMessage, HumanMessage, AIMessage
-from langchain_community.document_loaders import WebBaseLoader
-from langgraph.checkpoint.memory import MemorySaver
-
-
-import operator
-from setup import *
-
-class GeneratorState(MessagesState):
-  context : Annotated[list, operator.add] # retrived docs
-  max_usecase : int # no of usecase to generate
-  topic : str # input query
-
-
-class SearchQuery(BaseModel):
-  search_query : str = Field(description = 'Search query for web-search')
-
-
-keyword_search = TavilySearchResults(
-  max_results=1,
-  search_depth="advanced",
-  include_answer=True,
-  include_raw_content=True,
-  include_images=True)
-
-
-
-def search_web(state: GeneratorState):
-  
-  topic = state['topic']
-  structured_llm = llm2.with_structured_output(SearchQuery)
-  
-  search_instructions = """You are an AI assistant specialized in generating effective internet search queries. Your goal is to create **precise, keyword-rich search queries** that retrieve the best results for **AI use cases in specific industries** using Tavily Search.  
-
-    ## **Instructions:**
-    - Extract the **industry name** from the user’s query.
-    - Generate a **focused search query** that retrieves **practical AI use cases** in that industry.
-    - Include keywords like **"applications," "use cases," "impact," or "case studies"** to refine the search.
-    - Prioritize sources like **research papers, industry reports, and authoritative tech sites**.
-    - Use **Google-style operators (e.g., `site:`) to focus on trusted sources** if applicable.
-
-    ---
-    ## **Example:**
-    User Input: `"GenAI in healthcare"`  
-    Generated Query:  
-    "Generative AI use cases in healthcare applications and impact"
-
-    Generate search query for the below:
-    {topic}
-    """
-
-  search_prompt = search_instructions.format(topic=topic)
-  search_query = structured_llm.invoke(search_prompt)
-  exclude_domains = ["vktr.com"]
-  search_docs = tavily_search.invoke(search_query.search_query, exclude_domains=exclude_domains)
-  page_url = [doc['url'] for doc in search_docs]
-  loader = WebBaseLoader(
-    web_paths= page_url,
-    bs_get_text_kwargs={"separator": "|", "strip": True},
-    raise_for_status=True,
-  )
-  docs = loader.load()
-  formatted_search_docs = "\n\n---\n\n".join(
-    [
-      f'<Document href="{doc.metadata['source']}"/>\n{doc.page_content}\n</Document>'
-      for doc in docs
-    ])
-  
-  summarization_prompt = '''You are an advanced summarization assistant. Your task is to generate a 500-word summary based on the provided context. 
-    Maintain key information while removing redundancy, preserving critical details, and ensuring readability. Follow these guidelines:
-    Focus on Key Points: Extract essential facts, insights, and takeaways.
-    Maintain Clarity & Coherence: Ensure logical flow and readability.
-    Preserve Critical Data: Retain names, dates, figures, and important references.
-    Adjust Length as Needed: Summarize concisely while covering all vital aspects.
-    Format the summary professionally, adapting tone and detail to match the context.
-    context : {formatted_search_docs}
-  '''
-  summarized_docs = llm2.invoke([SystemMessage(content=summarization_prompt)])
-
-  return {'context': [summarized_docs]}
-
-
-
-def generate_usecases(state: GeneratorState):
-  topic = state['topic']
-  context = state['context']
-  generation_prompt = '''
-    You are a highly skilled technical writer. Your task is to consolidate insights from analyst memos into a structured report based on the given context and topic. Ensure the report includes a **brief introduction**, at least five AI use cases, and a **short conclusion**. Follow this format:  
-    topic : {topic}
-    context:
-    {context}
-
-    # Focus Title: [Provided Title]  
-
-    ## Introduction:
-      Provide a concise overview of the report's purpose and relevance.  
-
-    ## Use Case 1: [Descriptive Title]  
-    **Objective/Use Case:** Summarize the goal in one or two sentences.  
-    **AI Application:** Describe the AI technologies used.  
-    **Cross-Functional Benefit:**  
-    - **[Department]:** [Benefit]  
-    - **[Department]:** [Benefit]  
-
-    ## Use Case 2: [Descriptive Title]  
-    (Repeat format)  
-
-    ## Conclusion:
-      Summarize key takeaways and potential future implications.  
-
-    Ensure clarity, relevance, and no duplicate citations in the **Sources** section. Extract insights accurately from the **context** provided.'''
-
-  system_message = generation_prompt.format(topic=topic, context=context)
-  answer = llm1.invoke([SystemMessage(content=system_message)])
-
-  return {'messages': answer}
-
-
-
-def graph(topic,max_analysts):
-  graph_builder = StateGraph(GeneratorState)
-
-  graph_builder.add_node('search_web', search_web)
-  graph_builder.add_node('usecase_generation', generate_usecases)
-
-  graph_builder.add_edge(START, 'search_web')
-  graph_builder.add_edge('search_web', 'usecase_generation')
-  graph_builder.add_edge('usecase_generation', END)
-
-  memory = MemorySaver()
-  graph = graph_builder.compile(checkpointer=memory)
-  config = {"configurable": {"thread_id": "1"}}
-  graph.invoke({"topic":topic,
-                "max_analysts":max_analysts}, 
-                config)
-  
-  final_state = graph.get_state(config)
-  report = final_state.values['messages'][0].content
-  
+from pydantic import BaseModel,Field
+from typing import TypedDict, Annotated
+from langgraph.graph import MessagesState,StateGraph, START, END
+from langchain_community.tools import TavilySearchResults
+from langchain_core.messages import SystemMessage, HumanMessage, AIMessage
+from langchain_community.document_loaders import WebBaseLoader
+from langgraph.checkpoint.memory import MemorySaver
+
+
+import operator
+from setup import *
+
+class GeneratorState(MessagesState):
+  context : Annotated[list, operator.add] # retrived docs
+  max_usecase : int # no of usecase to generate
+  topic : str # input query
+
+
+class SearchQuery(BaseModel):
+  search_query : str = Field(description = 'Search query for web-search')
+
+
+keyword_search = TavilySearchResults(
+  max_results=1,
+  search_depth="advanced",
+  include_answer=True,
+  include_raw_content=True,
+  include_images=True)
+
+
+
+def search_web(state: GeneratorState):
+  
+  topic = state['topic']
+  structured_llm = llm2.with_structured_output(SearchQuery)
+  
+  search_instructions = """You are an AI assistant specialized in generating effective internet search queries. Your goal is to create **precise, keyword-rich search queries** that retrieve the best results for **AI use cases in specific industries** using Tavily Search.  
+
+    ## **Instructions:**
+    - Extract the **industry name** from the user’s query.
+    - Generate a **focused search query** that retrieves **practical AI use cases** in that industry.
+    - Include keywords like **"applications," "use cases," "impact," or "case studies"** to refine the search.
+    - Prioritize sources like **research papers, industry reports, and authoritative tech sites**.
+    - Use **Google-style operators (e.g., `site:`) to focus on trusted sources** if applicable.
+
+    ---
+    ## **Example:**
+    User Input: `"GenAI in healthcare"`  
+    Generated Query:  
+    "Generative AI use cases in healthcare applications and impact"
+
+    Generate search query for the below:
+    {topic}
+    """
+
+  search_prompt = search_instructions.format(topic=topic)
+  search_query = structured_llm.invoke(search_prompt)
+  exclude_domains = ["vktr.com"]
+  search_docs = tavily_search.invoke(search_query.search_query, exclude_domains=exclude_domains)
+  page_url = [doc['url'] for doc in search_docs]
+  loader = WebBaseLoader(
+    web_paths= page_url,
+    bs_get_text_kwargs={"separator": "|", "strip": True},
+    raise_for_status=True,
+  )
+  docs = loader.load()
+  formatted_search_docs = "\n\n---\n\n".join(
+    [
+      f'<Document href="{doc.metadata["source"]}"/>\n{doc.page_content}\n</Document>'
+      for doc in docs
+    ])
+  
+  summarization_prompt = '''You are an advanced summarization assistant. Your task is to generate a 500-word summary based on the provided context. 
+    Maintain key information while removing redundancy, preserving critical details, and ensuring readability. Follow these guidelines:
+    Focus on Key Points: Extract essential facts, insights, and takeaways.
+    Maintain Clarity & Coherence: Ensure logical flow and readability.
+    Preserve Critical Data: Retain names, dates, figures, and important references.
+    Adjust Length as Needed: Summarize concisely while covering all vital aspects.
+    Format the summary professionally, adapting tone and detail to match the context.
+    context : {formatted_search_docs}
+  '''
+  summarized_docs = llm2.invoke([SystemMessage(content=summarization_prompt)])
+
+  return {'context': [summarized_docs]}
+
+
+
+def generate_usecases(state: GeneratorState):
+  topic = state['topic']
+  context = state['context']
+  generation_prompt = '''
+    You are a highly skilled technical writer. Your task is to consolidate insights from analyst memos into a structured report based on the given context and topic. Ensure the report includes a **brief introduction**, at least five AI use cases, and a **short conclusion**. Follow this format:  
+    topic : {topic}
+    context:
+    {context}
+
+    # Focus Title: [Provided Title]  
+
+    ## Introduction:
+      Provide a concise overview of the report's purpose and relevance.  
+
+    ## Use Case 1: [Descriptive Title]  
+    **Objective/Use Case:** Summarize the goal in one or two sentences.  
+    **AI Application:** Describe the AI technologies used.  
+    **Cross-Functional Benefit:**  
+    - **[Department]:** [Benefit]  
+    - **[Department]:** [Benefit]  
+
+    ## Use Case 2: [Descriptive Title]  
+    (Repeat format)  
+
+    ## Conclusion:
+      Summarize key takeaways and potential future implications.  
+
+    Ensure clarity, relevance, and no duplicate citations in the **Sources** section. Extract insights accurately from the **context** provided.'''
+
+  system_message = generation_prompt.format(topic=topic, context=context)
+  answer = llm1.invoke([SystemMessage(content=system_message)])
+
+  return {'messages': answer}
+
+
+
+def graph(topic,max_analysts):
+  graph_builder = StateGraph(GeneratorState)
+
+  graph_builder.add_node('search_web', search_web)
+  graph_builder.add_node('usecase_generation', generate_usecases)
+
+  graph_builder.add_edge(START, 'search_web')
+  graph_builder.add_edge('search_web', 'usecase_generation')
+  graph_builder.add_edge('usecase_generation', END)
+
+  memory = MemorySaver()
+  graph = graph_builder.compile(checkpointer=memory)
+  config = {"configurable": {"thread_id": "1"}}
+  graph.invoke({"topic":topic,
+                "max_analysts":max_analysts}, 
+                config)
+  
+  final_state = graph.get_state(config)
+  report = final_state.values['messages'][0].content
+  
   return report