add support for Gemini 2.5 Flash model and update README

README.md

@@ -44,6 +44,8 @@ If you have a resource-constrained PC, try increasing `HEALTHCHECK_START_PERIOD`
 enough before healthcheck begins.
 For more information, please refer to this [link](https://docs.docker.com/reference/compose-file/services/#healthcheck)
 
+
+Set the model by updating your `.env` file:
 ```bash
 cd backend
 cp .env.example .env
@@ -60,9 +62,9 @@ make docker-down
 
 ### Prerequisites
 
-- [`uv`](https://docs.astral.sh/uv/) (for managing Python, virtual environments, and dependencies)  
-- `wget`  
-- `pandoc`  
+- [`uv`](https://docs.astral.sh/uv/) (for managing Python, virtual environments, and dependencies)
+- `wget`
+- `pandoc`
 - `git`
 
 **Step 1**: Install the required dependencies.
@@ -141,12 +143,12 @@ flowchart LR
     id1([Vectorstore]) --- id3([MMR Retriever])
     id1([Vectorstore]) --- id4([BM25 Retriever])
 
-    id2([Semantic Retriever]) -- Retrieved Docs ---> id5([Reranking]) 
+    id2([Semantic Retriever]) -- Retrieved Docs ---> id5([Reranking])
     id3([MMR Retriever]) -- Retrieved Docs ---> id5([Reranking])
     id4([BM25 Retriever]) -- Retrieved Docs ---> id5([Reranking])
 
     id5([Reranking]) ---> id6(top-n docs)
- 
+
 ```
 
 Depending on the input query, each query can be forwarded to any one of the following retrievers,

backend/src/api/routers/chains.py

@@ -54,12 +54,18 @@
     llm = ChatOllama(model=model_name, temperature=llm_temp)
 
 elif os.getenv("LLM_MODEL") == "gemini":
-    if os.getenv("GOOGLE_GEMINI") == "1_pro":
-        llm = ChatGoogleGenerativeAI(model="gemini-pro", temperature=llm_temp)
-    elif os.getenv("GOOGLE_GEMINI") == "1.5_flash":
-        llm = ChatVertexAI(model_name="gemini-1.5-flash", temperature=llm_temp)
-    elif os.getenv("GOOGLE_GEMINI") == "1.5_pro":
-        llm = ChatVertexAI(model_name="gemini-1.5-pro", temperature=llm_temp)
+    gemini_model = os.getenv("GOOGLE_GEMINI")
+    if gemini_model in {"1_pro", "1.5_flash", "1.5_pro"}:
+        raise ValueError(
+            f"The selected Gemini model '{gemini_model}' (version 1.0–1.5) is disabled. "
+            "Please upgrade to version 2.0 or higher (e.g., 2.0_flash, 2.5_pro)."
+        )
+    elif gemini_model == "2.0_flash":
+        llm = ChatVertexAI(model_name="gemini-2.0-flash", temperature=llm_temp)
+    elif gemini_model == "2.5_flash":
+        llm = ChatVertexAI(model_name="gemini-2.5-flash", temperature=llm_temp)
+    elif gemini_model == "2.5_pro":
+        llm = ChatVertexAI(model_name="gemini-2.5-pro", temperature=llm_temp)
     else:
         raise ValueError("GOOGLE_GEMINI environment variable not set to a valid value.")
 

backend/src/api/routers/graphs.py

@@ -75,12 +75,18 @@
     llm = ChatOllama(model=model_name, temperature=llm_temp)
 
 elif os.getenv("LLM_MODEL") == "gemini":
-    if os.getenv("GOOGLE_GEMINI") == "1_pro":
-        llm = ChatGoogleGenerativeAI(model="gemini-pro", temperature=llm_temp)
-    elif os.getenv("GOOGLE_GEMINI") == "1.5_flash":
-        llm = ChatVertexAI(model_name="gemini-1.5-flash", temperature=llm_temp)
-    elif os.getenv("GOOGLE_GEMINI") == "1.5_pro":
-        llm = ChatVertexAI(model_name="gemini-1.5-pro", temperature=llm_temp)
+    gemini_model = os.getenv("GOOGLE_GEMINI")
+    if gemini_model in {"1_pro", "1.5_flash", "1.5_pro"}:
+        raise ValueError(
+            f"The selected Gemini model '{gemini_model}' (version 1.0–1.5) is disabled. "
+            "Please upgrade to version 2.0 or higher (e.g., 2.0_flash, 2.5_pro)."
+        )
+    elif gemini_model == "2.0_flash":
+        llm = ChatVertexAI(model_name="gemini-2.0-flash", temperature=llm_temp)
+    elif gemini_model == "2.5_flash":
+        llm = ChatVertexAI(model_name="gemini-2.5-flash", temperature=llm_temp)
+    elif gemini_model == "2.5_pro":
+        llm = ChatVertexAI(model_name="gemini-2.5-pro", temperature=llm_temp)
     else:
         raise ValueError("GOOGLE_GEMINI environment variable not set to a valid value.")