Added all agents

agents/eda_agent.py

@@ -0,0 +1,22 @@
+# from langchain.agents.agent_types import AgentType
+import pandas as pd
+
+import sys
+
+sys.path.append('..')
+
+from langchain_experimental.agents.agent_toolkits import create_pandas_dataframe_agent
+from langchain_openai import OpenAI, ChatOpenAI
+from langchain.agents.agent_types import AgentType
+
+def init_config(df):
+
+    llm = ChatOpenAI(model_name="gpt-4")
+
+    agent = create_pandas_dataframe_agent(llm=llm, df=df, verbose=True)
+
+    return agent
+
+def answer_question(agent, question):
+    return agent.invoke(question)['output']
+

agents/master_agent.py

@@ -0,0 +1,42 @@
+from langchain import hub
+from langchain.agents import AgentExecutor, create_openai_tools_agent
+from langchain.agents import load_tools
+from langchain_openai import ChatOpenAI
+
+def init_config():
+
+    search_tool = load_tools(['serpapi'])
+    
+    tools = [search_tool[0]]
+
+    prompt = hub.pull("hwchase17/openai-tools-agent")
+
+    llm = ChatOpenAI(model="gpt-4", temperature=0)
+
+# Construct the OpenAI Tools agent
+    agent = create_openai_tools_agent(llm, tools, prompt)
+
+    agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)
+
+    return agent_executor
+
+def answer_question(agent, question):
+
+    full_prompt = f"""
+                You are a master AI that can control other AI agents. You are specifically designed to automate plant maintenance.
+                You will recieve a prompt from a user, and will have to classify the prompt's purpose as one of the following categories:
+                [1] Plant Maintenance
+                [2] AI modeling & EDA
+                [3] Questions about the plant
+
+                Some samples of the prompts are:
+                [1] "Release the fertilizer", "Turn lights on", "Turn lights off", "Water the plant"
+                [2] "What is the accuracy of the model?", "What is the distribution of the data?", "What is the correlation between the features?", "Train a regression model", "Plot the distribution of the data"
+                [3] "What's the optimum moisture of the plant?", "Where does it generally grow?", "What is the plant's life cycle?", "What is the plant's scientific name?.
+
+                Return the category number and name of the prompt in a JSON format.
+
+                User: {question}
+    """
+
+    return agent.invoke({"input": full_prompt})['output']

agents/plant_agent.py

@@ -0,0 +1,38 @@
+from langchain import hub
+from langchain.agents import AgentExecutor, create_openai_tools_agent
+from langchain.agents import load_tools
+from langchain_openai import ChatOpenAI
+
+def init_config():
+
+    search_tool = load_tools(['serpapi'])
+    
+    tools = [search_tool[0]]
+
+    prompt = hub.pull("hwchase17/openai-tools-agent")
+
+    llm = ChatOpenAI(model="gpt-4", temperature=0)
+
+# Construct the OpenAI Tools agent
+    agent = create_openai_tools_agent(llm, tools, prompt)
+
+    agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)
+
+    return agent_executor
+
+def answer_question(agent, question):
+
+    full_prompt = f"""
+                You are a master AI that can control other AI agents. You are specifically designed to automate plant maintenance.
+                You will recieve a prompt from a user regarding plant maintenance, and will have to classify the prompt's purpose as one of the following categories:
+                [0] Fertilizing the plant
+                [1] Turning plant lights on
+                [2] Turning plant lights off
+                [3] Watering the plant
+
+                Return the category number and name of the prompt in a JSON format.
+
+                User: {question}
+    """
+
+    return agent.invoke({"input": full_prompt})['output']

agents/rag_agent.py

@@ -0,0 +1,70 @@
+import os
+
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.embeddings import OpenAIEmbeddings
+from langchain.vectorstores.chroma import Chroma
+import os
+import shutil
+
+from langchain.vectorstores.chroma import Chroma
+from langchain.embeddings import OpenAIEmbeddings
+
+from langchain.agents.agent_toolkits import create_retriever_tool
+from langchain.agents.agent_toolkits import create_conversational_retrieval_agent
+
+from langchain.agents import load_tools
+
+from langchain_openai import ChatOpenAI
+
+
+def init_config(loader):
+    # We use the loader created above to load the document
+    documents = loader.load()
+
+    # We split the document into several chunks as mentioned above
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=50)
+    texts = text_splitter.split_documents(documents)
+
+    CHROMA_PATH = "../data/plant_chroma"
+
+    if os.path.exists(CHROMA_PATH):
+            db = Chroma(persist_directory=CHROMA_PATH,embedding_function=OpenAIEmbeddings())
+
+    else:
+        db = Chroma.from_documents(
+        texts, OpenAIEmbeddings(), persist_directory=CHROMA_PATH
+        )
+        db.persist()
+        print(f"Saved {len(texts)} chunks to {CHROMA_PATH}.")
+
+    retriever = db.as_retriever()
+
+    # This is the prompt to create a RAG agent for us
+
+
+    retriever_name = "plant_os_pdf"
+    retriever_desc = """The purpose of this tool is to answer questions about the blue indigo false plant and its maintenance."""
+
+    rag_tool = create_retriever_tool(
+        retriever,
+        retriever_name,
+        retriever_desc
+    )
+
+    search_tool = load_tools(['serpapi'])
+    tools = [rag_tool, search_tool[0]]
+
+    llm = ChatOpenAI(model_name="gpt-4")
+
+    RAG_executor = create_conversational_retrieval_agent(llm=llm, tools=tools, verbose=True) # setting verbose=True to output the thought process of the agent
+
+    return RAG_executor
+
+def answer_question(agent, question):
+    question = "what is the scientific for the plant?"
+    
+    user_query = {"input": question}
+    
+    result = agent(user_query)
+
+    return result['output']

main.py

@@ -1,6 +1,35 @@
 from fastapi import FastAPI
 
+import os
+import json
+import sys
+
+import pandas as pd
 from langchain.document_loaders import DirectoryLoader
+from agents import master_agent, plant_agent, eda_agent, rag_agent
+
+app = FastAPI()
+
+os.environ['OPENAI_API_KEY'] = os.getenv['openapi-key']
+os.environ['SERPAPI_API_KEY'] = os.getenv['serpapi-key']
+
+master = master_agent.init_config()
+
+print("init master agent")
+
+plant = plant_agent.init_config()
+
+print("init plant agent")
+
+df = pd.read_csv('data/csv/plant_syn.csv')
+
+eda = eda_agent.init_config(df)
+
+print("init eda agent")
+
+loader = DirectoryLoader("data/txt", glob="*.txt")
+
+rag = rag_agent.init_config(loader)
 
 app = FastAPI()