neo4j-labs
diff --git a/‎README.md‎
Lines changed: 8 additions & 5 deletions b/‎README.md‎
Lines changed: 8 additions & 5 deletions
diff --git a/‎backend/src/main.py‎
Lines changed: 1 addition & 5 deletions b/‎backend/src/main.py‎
Lines changed: 1 addition & 5 deletions
diff --git a/‎backend/src/shared/constants.py‎
Lines changed: 2 additions & 2 deletions b/‎backend/src/shared/constants.py‎
Lines changed: 2 additions & 2 deletions
diff --git a/‎docs/backend/backend_docs.adoc‎
Lines changed: 94 additions & 2 deletions b/‎docs/backend/backend_docs.adoc‎
Lines changed: 94 additions & 2 deletions
@@ -114,7 +114,7 @@ Run the application using the default `docker-compose` configuration.
    By default, only OpenAI and Diffbot are enabled. Gemini requires additional GCP configurations.  
    Use the `VITE_LLM_MODELS_PROD` variable to configure the models you need. Example:
    ```bash
-   VITE_LLM_MODELS_PROD="openai_gpt_5_mini,diffbot,gemini_2.5_flash"
+   VITE_LLM_MODELS_PROD="gemini_2.5_flash,openai_gpt_5_mini,diffbot,anthropic_claude_4.5_haiku"
    ```
 
 2. **Input Sources:**  
@@ -235,8 +235,6 @@ gcloud run deploy dev-backend \
 
 ---
 
-## [ENV][env-sheet]
-
 ## [ENV][env-sheet]
 | Env Variable Name       | Mandatory/Optional | Default Value | Description                                                                                      |
 |------------------------ |-------------------|---------------|--------------------------------------------------------------------------------------------------|
@@ -251,7 +249,7 @@ gcloud run deploy dev-backend \
 | DUPLICATE_TEXT_DISTANCE | Optional          | 5             | This value is used to find distance for all node pairs in the graph and is calculated based on node properties |
 | DUPLICATE_SCORE_VALUE   | Optional          | 0.97          | Node score value to match duplicate nodes                                                        |
 | EFFECTIVE_SEARCH_RATIO  | Optional          | 1             | Ratio used for effective search calculations                                                     |
-| GRAPH_CLEANUP_MODEL     | Optional          | openai_gpt_4o_mini | Model name to clean up graph in post processing                                            |
+| GRAPH_CLEANUP_MODEL     | Optional          | openai_gpt_5_mini | Model name to clean up graph in post processing                                            |
 | MAX_TOKEN_CHUNK_SIZE    | Optional          | 10000         | Maximum token size to process file content                                                       |
 | YOUTUBE_TRANSCRIPT_PROXY| Mandatory         |               | Proxy key to process YouTube videos for getting transcripts                                      |
 | IS_EMBEDDING           | Optional           | true          | Flag to enable text embedding                                                                    |
@@ -282,7 +280,12 @@ gcloud run deploy dev-backend \
 | VITE_TOKENS_PER_CHUNK  | Optional           | 100           | Variable to configure tokens count per chunk. This gives flexibility for users who may require different chunk sizes for various tokenization tasks |
 | VITE_CHUNK_TO_COMBINE  | Optional           | 1             | Variable to configure number of chunks to combine for parallel processing                        |
 
-### Refer to this link for additional  [Environment Variables][env-vars].
+### Example Environment Files
+
+Refer to the example environment files for additional variables and configuration:
+
+- [Backend example.env](https://github.com/neo4j-labs/llm-graph-builder/blob/main/backend/example.env)
+- [Frontend example.env](https://github.com/neo4j-labs/llm-graph-builder/blob/main/frontend/example.env)
 
 ---
 
 
@@ -515,11 +515,7 @@ async def processing_source(credentials, params, pages, merged_file_path=None, i
       logging.info(obj_source_node)
       #pre checking if user is allowed to process the file
       if get_value_from_env("TRACK_USER_USAGE", "false", "bool"):
-        try:
-          track_token_usage(credentials.email, credentials.uri, 0, params.model, operation_type="precheck")
-        except LLMGraphBuilderException as e:
-          logging.error(str(e))
-          raise RuntimeError(str(e))
+        track_token_usage(credentials.email, credentials.uri, 0, params.model, operation_type="precheck")
       start_update_source_node = time.time()
       graphDb_data_Access.update_source_node(obj_source_node)
       graphDb_data_Access.update_node_relationship_count(params.file_name)
 
@@ -247,8 +247,8 @@
 CHAT_EMBEDDING_FILTER_SCORE_THRESHOLD = 0.10
 
 CHAT_TOKEN_CUT_OFF = {
-     ('openai_gpt_3.5','azure_ai_gpt_35',"gemini_1.0_pro","gemini_1.5_pro", "gemini_1.5_flash","groq-llama3",'groq_llama3_70b','anthropic_claude_3_5_sonnet','fireworks_llama_v3_70b','bedrock_claude_3_5_sonnet', ) : 4, 
-     ("openai-gpt-4","diffbot" ,'azure_ai_gpt_4o',"openai_gpt_4o", "openai_gpt_4o_mini") : 28,
+     ("gemini_2.5_pro", "gemini_2.5_flash","groq-llama3",'groq_llama3_70b','anthropic_claude_4_5_sonnet','anthropic_claude_4') : 4, 
+     ("openai_gpt_5.2","diffbot","openai_gpt_5_mini") : 28,
      ("ollama_llama3") : 2  
 }  
 
 
@@ -36,6 +36,64 @@ Based on the response from this API, the frontend UI displays the connection sta
 }
 ----
 
+=== Get Token Limits
+----
+POST /get_token_limits
+----
+
+Fetches the token usage limits/quota for the configured LLM provider (OpenAI, Gemini, Anthropic, etc.) for the logged‑in user.
+
+**API Parameters :**
+* `uri` = Neo4j URI
+* `userName` = Neo4j database username
+* `password` = Neo4j database password
+* `database` = Neo4j database name
+* `email` = Logged in User Email
+
+**Response :**
+[source,json,indent=0]
+----
+{
+    "status": "Success",
+    "data": {
+        "daily_remaining": 250000,
+        "monthly_remaining": 815234,
+        "daily_limit": 250000,
+        "monthly_limit": 1000000,
+        "daily_used": 0,
+        "monthly_used": 184766
+    },
+    "message": "Token limits fetched successfully"
+}
+----
+
+=== Fetch Embedding Models
+----
+POST /fetch_embedding_model
+----
+
+This API returns the currently selected embedding provider, embedding model, embedding dimension, and whether the vector index needs to be recreated.
+
+**API Parameters :**
+* `uri`        = Neo4j URI
+* `userName`   = Neo4j database username
+* `password`   = Neo4j database password
+* `database`   = Neo4j database name
+* `email`      = Logged in User Email
+
+**Response :**
+[source,json,indent=0]
+----
+{
+    "status": "Success",
+    "data": [
+        "openai",
+        "text-embedding-3-small",
+        1536,
+        true
+    ]
+}
+----
 
 === Upload Files from Local
 ----
@@ -441,8 +499,8 @@ The API responsible for a chatbot system designed to leverage multiple AI models
 
 **Components :** 
 
-** Embedding Models - Includes OpenAI Embeddings, VertexAI Embeddings, and SentenceTransformer Embeddings(Default) to support vector-based query operations.
-** AI Models - OpenAI GPT 3.5, GPT 4o, GPT 40 mini, gemini_1.5_flash can be configured for the chatbot backend to generate responses and process natural language.
+** Embedding Models - Includes OpenAI Embeddings, VertexAI Embeddings, BedrockEmbeddings and SentenceTransformer Embeddings(Default) to support vector-based query operations.
+** AI Models - OpenAI GPT 5 mini, gemini_2.5_flash, anthropic claude 4.5 haiku can be configured for the chatbot backend to generate responses and process natural language.
 ** Graph Database (Neo4jGraph) - Manages interactions with the Neo4j database, retrieving, and storing conversation histories.
 ** Response Generation - Utilizes Vector Embeddings from the Neo4j database, chat history, and the knowledge base of the LLM used.
 ** Chat Modes - Vector , Graph, Vector + Graph, Fulltext, Vector + Graph+Fulltext, Entity Search + Vector, Global search Vector 
@@ -1140,6 +1198,40 @@ The API is used to merge duplicate entities from database selected by user.
     "message": "Duplicate entities merged successfully"
 }
 ....
+
+=== Change Embedding Model
+----
+POST /change_embedding_model
+----
+
+This API updates the active embedding provider and embedding model for the backend.  
+If the selected model has a different embedding dimension from the existing vector index,  
+the backend automatically drops and recreates the vector index.
+
+**API Parameters :**
+* `uri`                 = Neo4j URI
+* `userName`            = Neo4j database username
+* `password`            = Neo4j database password
+* `database`            = Neo4j database name
+* `embedding_provider`  = Selected embedding provider (openai, gemini, vertexai, bedrock, sentence_transformer)
+* `embedding_model`     = Embedding model chosen by the user
+* `email`               = Logged in User Email
+
+**Response :**
+[source,json,indent=0]
+----
+{
+    "status": "Success",
+    "data": {
+        "embedding_provider": "gemini",
+        "embedding_model": "gemini-embedding-001",
+        "embedding_dimension": 3072,
+        "change_index": true
+    },
+    "message": "Embedding model changed successfully. Vector index was dropped and recreated."
+}
+----
+
 === Drop and create vector index
 ----
 POST /drop_create_vector_index
Original file line number	Diff line number	Diff line change
`@@ -247,8 +247,8 @@`
`247`	`247`	`CHAT_EMBEDDING_FILTER_SCORE_THRESHOLD = 0.10`
`248`	`248`
`249`	`249`	`CHAT_TOKEN_CUT_OFF = {`
`250`		`- ('openai_gpt_3.5','azure_ai_gpt_35',"gemini_1.0_pro","gemini_1.5_pro", "gemini_1.5_flash","groq-llama3",'groq_llama3_70b','anthropic_claude_3_5_sonnet','fireworks_llama_v3_70b','bedrock_claude_3_5_sonnet', ) : 4,`
`251`		`- ("openai-gpt-4","diffbot" ,'azure_ai_gpt_4o',"openai_gpt_4o", "openai_gpt_4o_mini") : 28,`
	`250`	`+ ("gemini_2.5_pro", "gemini_2.5_flash","groq-llama3",'groq_llama3_70b','anthropic_claude_4_5_sonnet','anthropic_claude_4') : 4,`
	`251`	`+ ("openai_gpt_5.2","diffbot","openai_gpt_5_mini") : 28,`
`252`	`252`	`("ollama_llama3") : 2`
`253`	`253`	`}`
`254`	`254`