Merge branch 'main' into fix-pg-textgen-readme

.github/workflows/docker/compose/dataprep-compose.yaml

@@ -67,3 +67,7 @@ services:
     build:
       dockerfile: comps/dataprep/elasticsearch/langchain/Dockerfile
     image: ${REGISTRY:-opea}/dataprep-elasticsearch:${TAG:-latest}
+  dataprep-opensearch:
+    build:
+      dockerfile: comps/dataprep/opensearch/langchain/Dockerfile
+    image: ${REGISTRY:-opea}/dataprep-opensearch:${TAG:-latest}

.github/workflows/docker/compose/retrievers-compose.yaml

@@ -15,10 +15,6 @@ services:
     build:
       dockerfile: comps/retrievers/vdms/langchain/Dockerfile
     image: ${REGISTRY:-opea}/retriever-vdms:${TAG:-latest}
-  retriever-multimodal-redis:
-    build:
-      dockerfile: comps/retrievers/multimodal/redis/langchain/Dockerfile
-    image: ${REGISTRY:-opea}/retriever-multimodal-redis:${TAG:-latest}
   retriever-pgvector:
     build:
       dockerfile: comps/retrievers/pgvector/langchain/Dockerfile
@@ -51,3 +47,7 @@ services:
     build:
       dockerfile: comps/retrievers/elasticsearch/langchain/Dockerfile
     image: ${REGISTRY:-opea}/retriever-elasticsearch:${TAG:-latest}
+  retriever-opensearch:
+    build:
+      dockerfile: comps/retrievers/opensearch/langchain/Dockerfile
+    image: ${REGISTRY:-opea}/retriever-opensearch:${TAG:-latest}

README.md

@@ -125,20 +125,6 @@ class ExampleService:
         self.megaservice.flow_to(embedding, llm)
 ```
 
-## Gateway
-
-The `Gateway` serves as the interface for users to access the `Megaservice`, providing customized access based on user requirements. It acts as the entry point for incoming requests, routing them to the appropriate `Microservices` within the `Megaservice` architecture.
-
-`Gateways` support API definition, API versioning, rate limiting, and request transformation, allowing for fine-grained control over how users interact with the underlying `Microservices`. By abstracting the complexity of the underlying infrastructure, `Gateways` provide a seamless and user-friendly experience for interacting with the `Megaservice`.
-
-For example, the `Gateway` for `ChatQnA` can be built like this:
-
-```python
-from comps import ChatQnAGateway
-
-self.gateway = ChatQnAGateway(megaservice=self.megaservice, host="0.0.0.0", port=self.port)
-```
-
 ## Contributing to OPEA
 
 Welcome to the OPEA open-source community! We are thrilled to have you here and excited about the potential contributions you can bring to the OPEA platform. Whether you are fixing bugs, adding new GenAI components, improving documentation, or sharing your unique use cases, your contributions are invaluable.

comps/__init__.py

@@ -38,6 +38,7 @@
     PIIResponseDoc,
     Audio2text,
     DocSumDoc,
+    DocSumLLMParams,
 )
 
 # Constants
@@ -47,23 +48,6 @@
 from comps.cores.mega.orchestrator import ServiceOrchestrator
 from comps.cores.mega.orchestrator_with_yaml import ServiceOrchestratorWithYaml
 from comps.cores.mega.micro_service import MicroService, register_microservice, opea_microservices
-from comps.cores.mega.gateway import (
-    Gateway,
-    ChatQnAGateway,
-    CodeGenGateway,
-    CodeTransGateway,
-    DocSumGateway,
-    TranslationGateway,
-    SearchQnAGateway,
-    AudioQnAGateway,
-    RetrievalToolGateway,
-    FaqGenGateway,
-    VideoQnAGateway,
-    VisualQnAGateway,
-    MultimodalQnAGateway,
-    GraphragGateway,
-    AvatarChatbotGateway,
-)
 
 # Telemetry
 from comps.cores.telemetry.opea_telemetry import opea_telemetry

comps/agent/langchain/src/strategy/sqlagent/README.md

@@ -14,7 +14,7 @@ The agent node takes user question, hints (optional) and history (when available
 
 ### Database schema:
 
-We use langchain's [SQLDatabase](https://python.langchain.com/api_reference/community/utilities/langchain_community.utilities.sql_database.SQLDatabase.html#langchain_community.utilities.sql_database.SQLDatabase) API to get table names and schemas from the SQL database. User just need to specify `db_path` and `db_name`. The table schemas are incorporated into the prompts for the agent.
+We use langchain's [SQLDatabase](https://python.langchain.com/docs/integrations/tools/sql_database/) API to get table names and schemas from the SQL database. User just need to specify `db_path` and `db_name`. The table schemas are incorporated into the prompts for the agent.
 
 ### Hints module:
 
@@ -37,8 +37,8 @@ The agent node takes user question, hints (optional) and history (when available
 
 ## Limitations
 
-1. Agent connects to local SQLite databases with uri.
-2. Agent is only allowed to issue "SELECT" commands to databases, i.e., agent can only query databases but cannot update databases.
-3. We currently does not support "streaming" agent outputs on the fly for `sql_agent_llama`.
+1. Agent is only allowed to issue "SELECT" commands to databases, i.e., agent can only query databases but cannot update databases.
+2. We currently does not support "streaming" agent outputs on the fly for `sql_agent_llama`.
+3. Users need to pass the SQL database URI to the agent with the `db_path` environment variable. We have only validated SQLite database connected in such way.
 
 Please submit issues if you want new features to be added. We also welcome community contributions!

comps/agent/langchain/src/strategy/sqlagent/hint.py

@@ -44,11 +44,13 @@ def get_topk_cols(topk, cols_descriptions, similarities):
 
 
 def pick_hints(query, model, column_embeddings, complete_descriptions, topk=5):
-    # use similarity to get the topk columns
-    query_embedding = model.encode(query, convert_to_tensor=True)
-    similarities = model.similarity(query_embedding, column_embeddings).flatten()
-
-    topk_cols_descriptions = get_topk_cols(topk, complete_descriptions, similarities)
+    if len(complete_descriptions) < topk:
+        topk_cols_descriptions = complete_descriptions
+    else:
+        # use similarity to get the topk columns
+        query_embedding = model.encode(query, convert_to_tensor=True)
+        similarities = model.similarity(query_embedding, column_embeddings).flatten()
+        topk_cols_descriptions = get_topk_cols(topk, complete_descriptions, similarities)
 
     hint = ""
     for col in topk_cols_descriptions:

comps/agent/langchain/src/strategy/sqlagent/planner.py

@@ -55,11 +55,13 @@ def __init__(self, args, tools):
             self.cols_descriptions, self.values_descriptions = read_hints(args.hints_file)
             self.embed_model = SentenceTransformer("BAAI/bge-large-en-v1.5")
             self.column_embeddings = self.embed_model.encode(self.values_descriptions)
+            print("Done embedding column descriptions")
 
     def __call__(self, state):
         print("----------Call Agent Node----------")
         question = state["messages"][0].content
         table_schema, num_tables = get_table_schema(self.args.db_path)
+        print("@@@@ Table Schema: ", table_schema)
         if self.args.use_hints:
             if not state["hint"]:
                 hints = pick_hints(question, self.embed_model, self.column_embeddings, self.cols_descriptions)

comps/agent/langchain/src/strategy/sqlagent/sql_tools.py

@@ -6,8 +6,7 @@
 
 
 def connect_to_db(db_path):
-    uri = "sqlite:///{path}".format(path=db_path)
-    db = SQLDatabase.from_uri(uri)
+    db = SQLDatabase.from_uri(db_path)
     return db
 
 

comps/agent/langchain/src/tools.py

@@ -125,18 +125,19 @@ def load_python_tools(file_dir_path: str):
 
 def get_tools_descriptions(file_dir_path: str):
     tools = []
-    file_path_list = []
-    if os.path.isdir(file_dir_path):
-        file_path_list += glob.glob(file_dir_path + "/*")
-    else:
-        file_path_list.append(file_dir_path)
-    for file in file_path_list:
-        if os.path.basename(file).endswith(".yaml"):
-            tools += load_yaml_tools(file)
-        elif os.path.basename(file).endswith(".yml"):
-            tools += load_yaml_tools(file)
-        elif os.path.basename(file).endswith(".py"):
-            tools += load_python_tools(file)
+    if file_dir_path:
+        file_path_list = []
+        if os.path.isdir(file_dir_path):
+            file_path_list += glob.glob(file_dir_path + "/*")
         else:
-            pass
+            file_path_list.append(file_dir_path)
+        for file in file_path_list:
+            if os.path.basename(file).endswith(".yaml"):
+                tools += load_yaml_tools(file)
+            elif os.path.basename(file).endswith(".yml"):
+                tools += load_yaml_tools(file)
+            elif os.path.basename(file).endswith(".py"):
+                tools += load_python_tools(file)
+            else:
+                pass
     return tools

comps/agent/langchain/src/utils.py

@@ -120,7 +120,7 @@ def get_args():
     parser.add_argument("--agent_name", type=str, default="OPEA_Default_Agent")
     parser.add_argument("--strategy", type=str, default="react_langchain")
     parser.add_argument("--role_description", type=str, default="LLM enhanced agent")
-    parser.add_argument("--tools", type=str, default="tools/custom_tools.yaml")
+    parser.add_argument("--tools", type=str, default=None, help="path to the tools file")
     parser.add_argument("--recursion_limit", type=int, default=5)
     parser.add_argument("--require_human_feedback", action="store_true", help="If this agent requires human feedback")
     parser.add_argument("--debug", action="store_true", help="Test with endpoint mode")