feat: introduce gemini calls

Author: neagualexa

.github/workflows/dev.yml

@@ -16,6 +16,8 @@ jobs:
     env:
       OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
       OPENAI_MODEL: ${{ vars.OPENAI_MODEL }}
+      GOOGLE_AI_API_KEY: ${{ secrets.GOOGLE_AI_API_KEY }}
+      GOOGLE_AI_MODEL: ${{ vars.GOOGLE_AI_MODEL }}
     steps:
       - name: Checkout Code
         uses: actions/checkout@v4

.github/workflows/main.yml

@@ -16,6 +16,8 @@ jobs:
     env:
       OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
       OPENAI_MODEL: ${{ vars.OPENAI_MODEL }}
+      GOOGLE_AI_API_KEY: ${{ secrets.GOOGLE_AI_API_KEY }}
+      GOOGLE_AI_MODEL: ${{ vars.GOOGLE_AI_MODEL }}
     steps:
       - name: Checkout Code
         uses: actions/checkout@v4

README.md

@@ -9,7 +9,19 @@ This chapter helps you to quickly set up a new Python chat module function using
 > [!NOTE]
 > To develop this function further, you will require the following environment variables in your `.env` file:
 ```bash
-> If you use azure-openai:
+> If you use OpenAI:
+OPENAI_API_KEY
+OPENAI_MODEL
+
+> If you use GoogleAI:
+GOOGLE_AI_API_KEY
+GOOGLE_AI_MODEL
+```
+
+> [!Note]
+> If you decide to use another endpoint such as Azure or Ollama or any other, please update the github workflow files to use the right secrets and variables for testing.
+```bash
+> If you use Azure-OpenAI:
 AZURE_OPENAI_API_KEY
 AZURE_OPENAI_ENDPOINT
 AZURE_OPENAI_API_VERSION
@@ -19,11 +31,7 @@ AZURE_OPENAI_EMBEDDING_1536_DEPLOYMENT
 AZURE_OPENAI_EMBEDDING_3072_MODEL
 AZURE_OPENAI_EMBEDDING_1536_MODEL
 
-> If you use openai:
-OPENAI_API_KEY
-OPENAI_MODEL
-
-> For monitoring of the LLM calls (follow instructions on how to set up on langsmith):
+> For monitoring of the LLM calls (follow instructions on how to set up on langsmith online):
 LANGCHAIN_TRACING_V2
 LANGCHAIN_ENDPOINT
 LANGCHAIN_API_KEY

src/agents/base_agent/base_agent.py

@@ -1,10 +1,10 @@
 try:
-    from ..llm_factory import OpenAILLMs
+    from ..llm_factory import OpenAILLMs, GoogleAILLMs
     from .base_prompts import \
         role_prompt, conv_pref_prompt, update_conv_pref_prompt, summary_prompt, update_summary_prompt, summary_system_prompt
     from ..utils.types import InvokeAgentResponseType
 except ImportError:
-    from src.agents.llm_factory import OpenAILLMs
+    from src.agents.llm_factory import OpenAILLMs, GoogleAILLMs
     from src.agents.base_agent.base_prompts import \
         role_prompt, conv_pref_prompt, update_conv_pref_prompt, summary_prompt, update_summary_prompt, summary_system_prompt
     from src.agents.utils.types import InvokeAgentResponseType
@@ -35,9 +35,9 @@ class State(TypedDict):
 
 class BaseAgent:
     def __init__(self):
-        llm = OpenAILLMs()
+        llm = OpenAILLMs()                  # OpenAILLMs() or GoogleAILLMs()
         self.llm = llm.get_llm()
-        summarisation_llm = OpenAILLMs()
+        summarisation_llm = OpenAILLMs()    # OpenAILLMs() or GoogleAILLMs()
         self.summarisation_llm = summarisation_llm.get_llm()
         self.summary = ""
         self.conversationalStyle = ""
@@ -120,12 +120,12 @@ def summarize_conversation(self, state: State, config: RunnableConfig) -> dict:
             conversationalStyle_message = self.conversation_preference_prompt
 
         # STEP 1: Summarize the conversation
-        messages = state["messages"][:-1] + [SystemMessage(content=summary_message)] 
+        messages = state["messages"][:-1] + [HumanMessage(content=summary_message)] 
         valid_messages = self.check_for_valid_messages(messages)
         summary_response = self.summarisation_llm.invoke(valid_messages)
 
         # STEP 2: Analyze the conversational style
-        messages = state["messages"][:-1] + [SystemMessage(content=conversationalStyle_message)]
+        messages = state["messages"][:-1] + [HumanMessage(content=conversationalStyle_message)]
         valid_messages = self.check_for_valid_messages(messages)
         conversationalStyle_response = self.summarisation_llm.invoke(valid_messages)
 

src/agents/base_agent/base_prompts.py

@@ -64,11 +64,13 @@
 Structured: Organize the summary into sections such as 'Topics Discussed' and 'Top 3 Key Detailed Ideas'.
 Neutral and Accurate: Avoid adding interpretations or opinions; focus only on the content shared.
 When summarizing: If the conversation is technical, highlight significant concepts, solutions, and terminology. If context involves problem-solving, detail the problem and the steps or solutions provided. If the user asks for creative input, briefly describe the ideas presented.
-Last messages: Include the most recent 4 messages to provide context for the summary.
+Last messages: Include the most recent 5 messages to provide context for the summary.
 
 Provide the summary in a bulleted format for clarity. Avoid redundant details while preserving the core intent of the discussion."""
 
-summary_prompt = f"""Summarize the conversation between a student and a tutor. Your summary should highlight the major topics discussed during the session, followed by a detailed recollection of the last five significant points or ideas. Ensure the summary flows smoothly to maintain the continuity of the discussion."""
+summary_prompt = f"""Summarize the conversation between a student and a tutor. Your summary should highlight the major topics discussed during the session, followed by a detailed recollection of the last five significant points or ideas. Ensure the summary flows smoothly to maintain the continuity of the discussion.
+
+{summary_guidelines}"""
 
 update_summary_prompt = f"""Update the summary by taking into account the new messages above.