Add documentation for environment variables of engine. (#519)

Co-authored-by: = <=>

services/engine/.env.example

@@ -7,7 +7,7 @@ ORG_ID =
 AGENT_MAX_ITERATIONS = 15
 #timeout in seconds for the engine to return a response. Defaults to 150 seconds
 DH_ENGINE_TIMEOUT = 150
-#tmeout for SQL execution, our agents exceute the SQL query to recover from errors, this is the timeout for that execution. Defaults to 30 seconds
+#timeout for SQL execution, our agents execute the SQL query to recover from errors, this is the timeout for that execution. Defaults to 60 seconds
 SQL_EXECUTION_TIMEOUT = 30
 #The upper limit on number of rows returned from the query engine (equivalent to using LIMIT N in PostgreSQL/MySQL/SQlite). Defauls to 50
 UPPER_LIMIT_QUERY_RETURN_ROWS = 50

services/engine/README.md

@@ -91,6 +91,7 @@ API_BASE = "azure_openai_endpoint"
 AZURE_OPENAI_ENDPOINT = "azure_openai_endpoint" 
 AZURE_API_VERSION = "version of the API to use"
 LLM_MODEL = "name_of_the_deployment"
+EMBEDDING_MODEL = "name_of_deployed_embedding_model"
 ```
 In addition, an embedding model will be also used. There must be a deployment created with name "text-embedding-3-large".
 

services/engine/docs/envars.rst

@@ -39,10 +39,17 @@ provided in the .env.example file with the default values.
   
     ONLY_STORE_CSV_FILES_LOCALLY =
 
+    MINIO_ROOT_USER =
+    MINIO_ROOT_PASSWORD =
+
     AGENT_MAX_ITERATIONS = 15
     DH_ENGINE_TIMEOUT = 150
+    SQL_EXECUTION_TIMEOUT = 30
     UPPER_LIMIT_QUERY_RETURN_ROWS = 50
 
+    CORE_PORT = 
+
+    EMBEDDING_MODEL = "text-embedding-3-large"
 
 .. csv-table::
    :header: "Variable Name", "Description", "Default Value", "Required"
@@ -53,8 +60,8 @@ provided in the .env.example file with the default values.
    "GOLDEN_RECORD_COLLECTION", "The name of the collection in Mongo where golden records will be stored", "``my-golden-records``", "No"
    "PINECONE_API_KEY", "The Pinecone API key used", "None", "Yes if using the Pinecone vector store"
    "PINECONE_ENVIRONMENT", "The Pinecone environment", "None", "Yes if using the Pinecone vector store"
-    "ASTRA_DB_API_ENDPOINT", "The Astra DB API endpoint", "None", "Yes if using the Astra DB"
-    "ASTRA_DB_APPLICATION_TOKEN", "The Astra DB application token", "None", "Yes if using the Astra DB
+   "ASTRA_DB_API_ENDPOINT", "The Astra DB API endpoint", "None", "Yes if using the Astra DB"
+   "ASTRA_DB_APPLICATION_TOKEN", "The Astra DB application token", "None", "Yes if using the Astra DB
    "API_SERVER", "The implementation of the API Module used by the Dataherald Engine.", "``dataherald.api.fastapi.FastAPI``", "Yes"
    "SQL_GENERATOR", "The implementation of the SQLGenerator Module to be used.", "``dataherald.sql_generator.  dataherald_sqlagent. DataheraldSQLAgent``", "Yes"
    "EVALUATOR", "The implementation of the Evaluator Module to be used.", "``dataherald.eval. simple_evaluator.SimpleEvaluator``", "Yes"
@@ -69,7 +76,11 @@ provided in the .env.example file with the default values.
    "ENCRYPT_KEY", "The key that will be used to encrypt data at rest before storing", "None", "Yes"
    "S3_AWS_ACCESS_KEY_ID", "The key used to access credential files if saved to S3", "None", "No"
    "S3_AWS_SECRET_ACCESS_KEY", "The key used to access credential files if saved to S3", "None", "No"
-   "DH_ENGINE_TIMEOUT", "This is used to set the max seconds the process will wait for the response to be generate. If the specified time limit is exceeded, it will trigger an exception", "None", "No"
+   "DH_ENGINE_TIMEOUT", "This is used to set the max seconds the process will wait for the response to be generate. If the specified time limit is exceeded, it will trigger an exception", "``150``", "No"
+   "SQL_EXECUTION_TIMEOUT", "This is the timeout for SQL execution, our agents execute the SQL query to recover from errors, this is the timeout for that execution. If the specified time limit is exceeded, it will trigger an exception", "``60``", "No"
    "UPPER_LIMIT_QUERY_RETURN_ROWS", "The upper limit on number of rows returned from the query engine (equivalent to using LIMIT N in PostgreSQL/MySQL/SQlite).", "None", "No"
    "ONLY_STORE_CSV_FILES_LOCALLY", "Set to True if only want to save generated CSV files locally instead of S3. Note that if stored locally they should be treated as ephemeral, i.e., they will disappear when the engine is restarted.", "None", "No"
-
+   "MINIO_ROOT_USER","The username of the MinIO service.","None","No"
+   "MINIO_ROOT_PASSWORD","The password of the MinIO service.","None","No"
+   "CORE_PORT","The port that will be used by the container to run the engine. Make sure to bind the core port with the desired local port.","``80``","No"
+   "EMBEDDING_MODEL","The name of the embedding model used. If you are using OpenAI, use text-embedding-3-large. If you are using deployed service, make sure to use the name of the deployed embedding model","``text-embedding-3-large``","No"