change to GROQ

Dockerfile

@@ -3,31 +3,31 @@
 
 FROM python:3.11-slim
 
-RUN apt-get update && apt-get install -y curl && \
-    curl -fsSL https://ollama.ai/install.sh | sh && \
-    apt-get clean && rm -rf /var/lib/apt/lists/*
+# RUN apt-get update && apt-get install -y curl && \
+#     curl -fsSL https://ollama.ai/install.sh | sh && \
+#     apt-get clean && rm -rf /var/lib/apt/lists/*
 
-RUN useradd -m -u 1000 user
-USER user
-ENV HOME=/home/user \
-    PATH="/home/user/.local/bin:$PATH"
+# RUN useradd -m -u 1000 user
+# USER user
+# ENV HOME=/home/user \
+#     PATH="/home/user/.local/bin:$PATH"
 
-# Création des répertoires nécessaires
-RUN mkdir -p $HOME/docker_ollama $HOME/logs
-WORKDIR $HOME/docker_ollama
+# # Création des répertoires nécessaires
+# RUN mkdir -p $HOME/docker_ollama $HOME/logs
+# WORKDIR $HOME/docker_ollama
 
-COPY --chown=user requirements.txt .
-RUN pip install --no-cache-dir --upgrade -r requirements.txt
-COPY --chown=user . .
-RUN chmod +x start.sh
-EXPOSE 7860 11434
+# COPY --chown=user requirements.txt .
+# RUN pip install --no-cache-dir --upgrade -r requirements.txt
+# COPY --chown=user . .
+# RUN chmod +x start.sh
+# EXPOSE 7860 11434
 
-CMD ["./start.sh"]
+# CMD ["./start.sh"]
 
-# WORKDIR /app
+WORKDIR /app
 
-# COPY --chown=user ./requirements.txt requirements.txt
-# RUN pip install --no-cache-dir --upgrade -r requirements.txt
+COPY --chown=user ./requirements.txt requirements.txt
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
 
-# COPY --chown=user . /app
-# CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]
+COPY --chown=user . /app
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -11,12 +11,15 @@ from langchain_core.messages import SystemMessage, HumanMessage, AnyMessage
 from langchain_ollama import ChatOllama
 from langgraph.pregel import RetryPolicy
 import json
-import pandas as pd
 from google.oauth2 import service_account
 import os
+from langchain_groq import ChatGroq
+import groq
 
-sheet_url = "https://docs.google.com/spreadsheets/d/1t4bOM4fULdaVsjDDnqEG1g8Zey6M00UuFhTZC03_4xo/edit?gid=0#gid=0"
+sheet_url = os.getenv("SHEET_URL")
 GOOGLESHEETS_CREDENTIALS = os.getenv("GOOGLESHEETS_CREDENTIALS")
+GROQ_API_KEY = os.environ.get("GROQ_API_KEY")
+MODEL = "meta-llama/llama-4-scout-17b-16e-instruct"
 
 class TransactionParser(BaseModel):
     """This Pydantic class is used to parse the transaction message."""
@@ -35,8 +38,8 @@ class Agent:
     def __init__(self, model, system=""):
         self.system = system
         graph = StateGraph(AgentState)
-        graph.add_node("classify_txn_type", self.classify_txn_type)
-        graph.add_node("parse_message", self.parse_message)
+        graph.add_node("classify_txn_type", self.classify_txn_type, retry=RetryPolicy(retry_on=[groq.BadRequestError], max_attempts=2))
+        graph.add_node("parse_message", self.parse_message, retry=RetryPolicy(retry_on=[groq.BadRequestError], max_attempts=2))
         graph.add_node("write_message", self.write_message)
         graph.add_conditional_edges(
             "classify_txn_type",
@@ -119,14 +122,16 @@ def greetings():
 @app.post("/write_message")
 def write_message(data: dict):
     message = data['message']
-    model = ChatOllama(model="gemma3:1b", temperature=1)
+    model = ChatGroq(temperature=1, groq_api_key=GROQ_API_KEY, model_name=MODEL)
+    # model = ChatOllama(model="gemma3:1b", temperature=1)
     transaction_bot = Agent(model, system=prompt)
     transaction_bot.graph.invoke({"messages": [message]})
     return {"message": "Transaction completed successfully"}
 
 @app.get("/ask")
 def ask(prompt: str):
-    model = ChatOllama(model="gemma3:1b", temperature=1)
+    model = ChatGroq(temperature=1, groq_api_key=GROQ_API_KEY, model_name=MODEL)
+    # model = ChatOllama(model="gemma3:1b", temperature=1)
     return model.invoke(prompt)
 
 if __name__ == "__main__":

requirements.txt

@@ -3,4 +3,5 @@ uvicorn[standard]
 langchain-ollama
 langgraph
 pygsheets
-pandas
+pandas
+langchain-groq

start.sh

@@ -9,27 +9,27 @@ export OMP_NUM_THREADS=2
 export MKL_NUM_THREADS=2
 export CUDA_VISIBLE_DEVICES=-1
 
-# Start Ollama in the background
-ollama serve &
+# # Start Ollama in the background
+# ollama serve &
 
-# Pull the model if not already present
-echo "gemma3:1b will be download"
-if ! ollama list | grep -q "gemma3:1b"; then
-    ollama pull gemma3:1b
-fi
+# # Pull the model if not already present
+# echo "gemma3:1b will be download"
+# if ! ollama list | grep -q "gemma3:1b"; then
+#     ollama pull gemma3:1b
+# fi
 
-# Wait for Ollama to start up
-max_attempts=30
-attempt=0
-while ! curl -s http://localhost:11434/api/tags >/dev/null; do
-    sleep 1
-    attempt=$((attempt + 1))
-    if [ $attempt -eq $max_attempts ]; then
-        echo "Ollama failed to start within 30 seconds. Exiting."
-        exit 1
-    fi
-done
+# # Wait for Ollama to start up
+# max_attempts=30
+# attempt=0
+# while ! curl -s http://localhost:11434/api/tags >/dev/null; do
+#     sleep 1
+#     attempt=$((attempt + 1))
+#     if [ $attempt -eq $max_attempts ]; then
+#         echo "Ollama failed to start within 30 seconds. Exiting."
+#         exit 1
+#     fi
+# done
 
-echo "Ollama is Ready - gemma3:1b is Loaded"
+# echo "Ollama is Ready - gemma3:1b is Loaded"
 
 python app.py