Merge pull request #3 from AquibPy/dev

Dev

Author: AquibPy

Dockerfile

@@ -1,25 +1,19 @@
-FROM python:3.9-slim
-
+FROM python:3.12.7-slim-bullseye
 
 WORKDIR /app
 
-
 COPY requirements.txt .
 
-RUN apt-get update && apt-get install -y libmagic-dev
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    libmagic-dev \
+    gcc \
+    g++ \
+    && rm -rf /var/lib/apt/lists/*
 
 RUN pip install --upgrade pip
-
 RUN pip install --no-cache-dir -r requirements.txt
 
-
 COPY . .
 
-
-EXPOSE 8000
-
-
-ENV PORT=8000
-
-# Command to run the application
-# CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000"]
+CMD ["uvicorn", "api:app", "--host", "0.0.0.0", "--port", "10000"]

README.md

@@ -192,28 +192,7 @@ percentage, missing keywords, and profile summary.
   - Choose between vector search or summarization for responses.
   - Support for multiple Open Source LLMs models.
 
-### 21. Tech News Agent using Crew ai
-
-- **Route:** `/news_agent`
-- **Description:** This endpoint leverages AI agents to conduct research and generate articles on various tech topics. The agents are designed to uncover groundbreaking technologies and narrate compelling tech stories.
-- **Features:**
-  - Accepts a `topic` parameter specifying the tech topic of interest.
-  - Utilizes caching mechanisms for improved performance by storing and retrieving responses from Redis cache.
-  - Integrates with MongoDB for storing endpoint usage data.
-  - Returns articles and research findings related to the specified tech topic.
-  - Handles exceptions gracefully and returns error messages in JSON format.
-
-### 22. Query Database
-
-- **Route:** `/query_db`
-- **Description:** This API endpoint facilitates querying SQL databases using a Cohere ReAct Agent, integrated with Langchain's SQLDBToolkit.
-- **Feature:**
-  - Upload a `.db` file containing the database to be queried.
-  - Provide a natural language prompt or query to retrieve relevant information
-  from the database.
-  - Utilizes a Cohere ReAct Agent to process user queries and generate responses.
-
-### 23. MediGem: Medical Diagnosis AI Assistant
+### 21. MediGem: Medical Diagnosis AI Assistant
 
 - **Route:** `/MediGem`
 - **Description:** This API endpoint leverages the New Google Gemini AI Model to analyze medical images and identify potential health conditions.
@@ -226,7 +205,7 @@ percentage, missing keywords, and profile summary.
   - **Image Quality Note:** Indicates if certain aspects are 'Unable to be determined based on the provided image.'
   - **Disclaimer:** Includes the disclaimer: "Consult with a Doctor before making any decisions."
 
-### 24. NoteGem: Automated Note-Taking Assistant
+### 22. NoteGem: Automated Note-Taking Assistant
 
 - **Route:** `/NoteGem`
 - **Description:** This API endpoint leverages the Google Gemini AI Model to generate comprehensive notes from YouTube video transcripts.
@@ -236,7 +215,50 @@ percentage, missing keywords, and profile summary.
   - **Error Handling for Transcripts:** If the transcript is not available, it returns a message indicating that the transcript is not available for transcription.
   - **AI Summary Generation:** The AI model generates a structured summary of the transcript focusing on main points, critical information, key takeaways, examples or case studies, quotes, and actionable steps.
 
-### 25. Investment Risk Analyst Agent
+### 23. Audio Video Transcriber
+
+- **Route:** `/transcriber`
+- **Description:** This API endpoint allows users to upload audio or video files to be transcribed into text using the OpenAI Whisper model.
+- **Feature:**
+  - **File Upload:** Users can upload audio or video files in various formats.
+  - **Transcription:** The API uses the OpenAI Whisper model to transcribe the uploaded file into text.
+
+### 24. Agrilens
+
+- **Route:** `/agrilens`  
+- **Description:** This API endpoint allows users to upload agricultural images and receive AI-powered insights into crops, pests, diseases, and overall health assessment.
+The analysis also includes actionable recommendations for improving agricultural practices and yields.
+- **Features:**
+  - **Image Upload:** Users can upload agricultural images in JPG, JPEG, or PNG formats.  
+  - **Advanced Detection:** Identifies crops, pests, diseases, and farming equipment within the uploaded image.  
+  - **Health Assessment:** Evaluates crop health, identifying stress factors or signs of disease.  
+  - **Smart Recommendations:** Provides actionable insights for enhancing agricultural productivity, such as fertilizer, pesticide, or irrigation advice.  
+
+### AGENTS Endpoint
+
+### 1. Tech News Agent using Crew ai
+
+- **Route:** `/news_agent`
+- **Description:** This endpoint leverages AI agents to conduct research and generate articles on various tech topics. The agents are designed to uncover groundbreaking technologies and narrate compelling tech stories.
+- **Features:**
+  - Accepts a `topic` parameter specifying the tech topic of interest.
+  - Utilizes caching mechanisms for improved performance by storing and retrieving responses from Redis cache.
+  - Integrates with MongoDB for storing endpoint usage data.
+  - Returns articles and research findings related to the specified tech topic.
+  - Handles exceptions gracefully and returns error messages in JSON format.
+
+### 2. Query Database
+
+- **Route:** `/query_db`
+- **Description:** This API endpoint facilitates querying SQL databases using a Cohere ReAct Agent, integrated with Langchain's SQLDBToolkit.
+- **Feature:**
+  - Upload a `.db` file containing the database to be queried.
+  - Provide a natural language prompt or query to retrieve relevant information
+  from the database.
+  - Utilizes a Cohere ReAct Agent to process user queries and generate responses.
+
+
+### 3. Investment Risk Analyst Agent
 
 - **Route:** `/investment_risk_agent`
 - **Description:** This API endpoint coordinates a team of AI agents to perform comprehensive investment risk analysis and strategy development.
@@ -247,7 +269,7 @@ percentage, missing keywords, and profile summary.
   - **Risk Assessment:** The risk management agent evaluates potential risks associated with the trading strategy and suggests mitigation measures.
   - **Execution Planning:** The execution agent develops a detailed plan for executing the trading strategy, considering the assessed risks.
 
-### 26. Agent Doc
+### 4. Agent Doc
 
 - **Route:** `/agent_doc`
 - **Description:** This API endpoint coordinates a team of AI agents to perform comprehensive healthcare diagnosis and treatment recommendations.
@@ -256,15 +278,7 @@ percentage, missing keywords, and profile summary.
   - **Diagnosis:** The diagnostician agent analyzes the input data to provide a preliminary diagnosis with possible conditions.
   - **Treatment Recommendations:** The treatment advisor agent formulates a suitable treatment plan based on the diagnosis and user-provided information.
 
-### 27. Audio Video Transcriber
-
-- **Route:** `/transcriber`
-- **Description:** This API endpoint allows users to upload audio or video files to be transcribed into text using the OpenAI Whisper model.
-- **Feature:**
-  - **File Upload:** Users can upload audio or video files in various formats.
-  - **Transcription:** The API uses the OpenAI Whisper model to transcribe the uploaded file into text.
-
-### 28. Job Posting Agent
+### 5. Job Posting Agent
 
 - **Route:** `/job_posting_agent`
 - **Description:** This API endpoint coordinates a team of AI agents to generate a detailed and engaging job posting tailored to the company's culture and values.
@@ -275,7 +289,7 @@ percentage, missing keywords, and profile summary.
   - **Job Posting Drafting:** The job description writer agent uses the insights to create a detailed, engaging, and enticing job posting that aligns with the company's culture and values.
   - **Review and Editing:** The review and editing specialist agent reviews the job posting for clarity, engagement, grammatical accuracy, and alignment with company values, refining it to ensure perfection.
 
-### 29. ML Assistant Agent
+### 6. ML Assistant Agent
 
 - **Route:** `/ml_assistant`
 - **Description:** This endpoint coordinates a team of AI agents to process an uploaded CSV file and a user-defined machine learning problem description. It aims to provide a clear problem definition, assess the data quality, recommend suitable machine learning models, and generate starter Python code for the project.

agents/agent_doc/agents.py

@@ -1,13 +1,11 @@
 from crewai import Agent
 from .tools import scrape_tool, search_tool
-from langchain_google_genai import ChatGoogleGenerativeAI
 import os
 import settings
 
-llm=ChatGoogleGenerativeAI(model=settings.GEMINI_FLASH,
-                           verbose=True,
-                           temperature=0.7,
-                           google_api_key=os.getenv("GOOGLE_API_KEY"))
+os.environ["GEMINI_API_KEY"] = os.environ.get('GEMINI_API_KEY')
+
+llm = "gemini/gemini-1.5-flash-8b"
 
 
 diagnostician = Agent(

agents/agent_doc/crew.py

@@ -5,13 +5,12 @@
 
 doc_crew = Crew(
     agents=[diagnostician, treatment_advisor],
-    tasks=[diagnose_task, treatment_task],
-    verbose=2
+    tasks=[diagnose_task, treatment_task]
 )
 
 def run_doc_crew(input_data):
     result = doc_crew.kickoff(inputs=input_data)
-    return result
+    return str(result)
 
 if __name__=='__main__':
     doc_agent_input ={

agents/investment_risk_analyst_agent/agents.py

@@ -2,14 +2,12 @@
 from .tools import search_tool,scrape_tool
 from dotenv import load_dotenv
 load_dotenv()
-from langchain_google_genai import ChatGoogleGenerativeAI
 import os
 import settings
 
-llm=ChatGoogleGenerativeAI(model=settings.GEMINI_FLASH,
-                           verbose=True,
-                           temperature=0.5,
-                           google_api_key=os.getenv("GOOGLE_API_KEY"))
+os.environ["GEMINI_API_KEY"] = os.environ.get('GEMINI_API_KEY')
+
+llm = "gemini/gemini-1.5-flash-8b"
 
 data_analyst_agent = Agent(
     role="Data Analyst",

agents/investment_risk_analyst_agent/crew.py

@@ -7,10 +7,9 @@
 from .agents import data_analyst_agent,trading_strategy_agent,execution_agent,risk_management_agent
 from .tasks import data_analysis_task,strategy_development_task,risk_assessment_task,execution_planning_task
 
-llm=ChatGoogleGenerativeAI(model="gemini-1.5-flash-latest",
-                           verbose=True,
-                           temperature=0.7,
-                           google_api_key=os.getenv("GOOGLE_API_KEY"))
+os.environ["GEMINI_API_KEY"] = os.environ.get('GEMINI_API_KEY')
+
+llm = "gemini/gemini-1.5-flash-8b"
 
 
 financial_trading_crew = Crew(
@@ -31,7 +30,7 @@
 
 def run_investment_crew(input_data):
     result = financial_trading_crew.kickoff(inputs=input_data)
-    return result
+    return str(result)
 
 if __name__=='__main__':
     financial_trading_inputs ={

agents/job_posting_agent/agents.py

@@ -2,12 +2,10 @@
 from .tools import web_search_tool, serper_search_tool
 import os
 import settings
-from langchain_google_genai import ChatGoogleGenerativeAI
 
-llm=ChatGoogleGenerativeAI(model=settings.GEMINI_FLASH,
-                           verbose=True,
-                           temperature=0.7,
-                           google_api_key=os.getenv("GOOGLE_API_KEY"))
+os.environ["GEMINI_API_KEY"] = os.environ.get('GEMINI_API_KEY')
+
+llm = "gemini/gemini-1.5-flash-8b"
 
 
 class JobAgents():

agents/job_posting_agent/crew.py

@@ -32,7 +32,7 @@
 
 def run_job_crew(input_data):
     result = job_crew.kickoff(input_data)
-    return result
+    return str(result)
 
 if __name__=='__main__':
     job_agent_input = {

agents/ml_assistant/agents.py

@@ -6,9 +6,8 @@
 
 class MLAgents():
     def __init__(self,model) -> None:
-        self.llm = ChatGroq(
-            api_key=os.environ['GROQ_API_KEY'],
-            model_name=model)
+        os.environ["GROQ_API_KEY"] = os.environ.get('GROQ_API_KEY')
+        self.llm = f"groq/{model}"
 
     def problem_definition_agent(self):
         return Agent(

agents/ml_assistant/crew.py

@@ -28,7 +28,7 @@ def run_ml_crew(file_path, user_question, model="llama3-70b-8192"):
     # Format the input data for agents
     input_data = {
         "ml_problem": user_question,
-        "df": df.head(),
+        "df": df.head().to_json(orient="records"),
         "file_name": file_path
     }
 
@@ -40,7 +40,7 @@ def run_ml_crew(file_path, user_question, model="llama3-70b-8192"):
     )
 
     result = ml_crew.kickoff(input_data)
-    return result
+    return str(result)
 
 if __name__=="__main__":
     print(run_ml_crew(file_path="data/iris.csv",