arangoml
diff --git a/‎.github/workflows/_comps-workflow.yml
Lines changed: 0 additions & 1 deletion b/‎.github/workflows/_comps-workflow.yml
Lines changed: 0 additions & 1 deletion
diff --git a/‎.github/workflows/_run-helm-chart.yml
Lines changed: 2 additions & 1 deletion b/‎.github/workflows/_run-helm-chart.yml
Lines changed: 2 additions & 1 deletion
diff --git a/‎.github/workflows/docker/compose/chathistory-compose.yaml
Lines changed: 2 additions & 2 deletions b/‎.github/workflows/docker/compose/chathistory-compose.yaml
Lines changed: 2 additions & 2 deletions
diff --git a/‎.github/workflows/manual-comps-test.yml
Lines changed: 1 addition & 1 deletion b/‎.github/workflows/manual-comps-test.yml
Lines changed: 1 addition & 1 deletion
diff --git a/‎.github/workflows/manual-docker-publish.yml
Lines changed: 1 addition & 1 deletion b/‎.github/workflows/manual-docker-publish.yml
Lines changed: 1 addition & 1 deletion
diff --git a/‎.github/workflows/push-image-build.yml
Lines changed: 1 addition & 2 deletions b/‎.github/workflows/push-image-build.yml
Lines changed: 1 addition & 2 deletions
diff --git a/‎README.md
Lines changed: 0 additions & 2 deletions b/‎README.md
Lines changed: 0 additions & 2 deletions
diff --git a/‎comps/__init__.py
Lines changed: 1 addition & 2 deletions b/‎comps/__init__.py
Lines changed: 1 addition & 2 deletions
diff --git a/‎comps/agent/src/README.md
Lines changed: 90 additions & 49 deletions b/‎comps/agent/src/README.md
Lines changed: 90 additions & 49 deletions
diff --git a/‎comps/agent/src/agent.py
Lines changed: 41 additions & 26 deletions b/‎comps/agent/src/agent.py
Lines changed: 41 additions & 26 deletions
diff --git a/‎comps/agent/src/integrations/agent.py
Lines changed: 6 additions & 2 deletions b/‎comps/agent/src/integrations/agent.py
Lines changed: 6 additions & 2 deletions
diff --git a/‎comps/agent/src/integrations/strategy/base_agent.py
Lines changed: 20 additions & 6 deletions b/‎comps/agent/src/integrations/strategy/base_agent.py
Lines changed: 20 additions & 6 deletions
@@ -71,7 +71,6 @@ jobs:
           fi
           if [[ $(grep -c "vllm-gaudi:" ${docker_compose_yml}) != 0 ]]; then
               git clone --depth 1 --branch v0.6.4.post2+Gaudi-1.19.0 https://github.com/HabanaAI/vllm-fork.git
-              sed -i 's/triton/triton==3.1.0/g' vllm-fork/requirements-hpu.txt
           fi
       - name: Get build list
         id: get-build-list
 
@@ -134,8 +134,9 @@ jobs:
           if [[ "${service,,}" == *"third_parties"* ]]; then
             CHART_NAME="$(echo "${service,,}"|cut -d'/' -f2)"  # bridgetower
           else
-            CHART_NAME="${service_name}"  # agent
+            CHART_NAME="${service_name}"  # web_retrievers
           fi
+          CHART_NAME=$(echo "$CHART_NAME" | tr -cd 'a-z0-9')
           echo "service_name=$service_name" >> $GITHUB_ENV
           echo "CHART_NAME=$CHART_NAME" >> $GITHUB_ENV
           echo "RELEASE_NAME=${CHART_NAME}$(date +%d%H%M%S)" >> $GITHUB_ENV
 
@@ -3,7 +3,7 @@
 
 # this file should be run in the root of the repo
 services:
-  chathistory-mongo-server:
+  chathistory-mongo:
     build:
       dockerfile: comps/chathistory/src/Dockerfile
-    image: ${REGISTRY:-opea}/chathistory-mongo-server:${TAG:-latest}
+    image: ${REGISTRY:-opea}/chathistory-mongo:${TAG:-latest}
@@ -7,7 +7,7 @@ on:
     inputs:
       services:
         default: "asr"
-        description: "List of services to test [agent,asr,chathistory,dataprep,embeddings,feedback_management,finetuning,guardrails,knowledgegraphs,llms,lvms,nginx,prompt_registry,ragas,rerankings,retrievers,tts,web_retrievers]"
+        description: "List of services to test [agent,asr,chathistory,animation,dataprep,embeddings,feedback_management,finetuning,guardrails,image2image,image2video,intent_detection,llms,lvms,prompt_registry,ragas,rerankings,retrievers,text2image,text2sql,third_parties,tts,vectorstores,web_retrievers]"
         required: true
         type: string
       build:
 
@@ -7,7 +7,7 @@ on:
     inputs:
       services:
         default: ""
-        description: "List of services to test [agent,asr,chathistory,dataprep,embeddings,feedback_management,finetuning,guardrails,knowledgegraphs,llms,lvms,nginx,prompt_registry,ragas,rerankings,retrievers,tts,web_retrievers]"
+        description: "List of services to test [agent,asr,chathistory,animation,dataprep,embeddings,feedback_management,finetuning,guardrails,image2image,image2video,intent_detection,llms,lvms,prompt_registry,ragas,rerankings,retrievers,text2image,text2sql,third_parties,tts,vectorstores,web_retrievers]"
         required: false
         type: string
       images:
 
@@ -62,7 +62,7 @@ jobs:
 
   image-build:
     needs: get-build-matrix
-    if: ${{ fromJSON(needs.get-build-matrix.outputs.services).length != 0 }}
+    if: needs.get-build-matrix.outputs.services != '[]'
     strategy:
       matrix:
         service: ${{ fromJSON(needs.get-build-matrix.outputs.services) }}
@@ -96,7 +96,6 @@ jobs:
           fi
           if [[ $(grep -c "vllm-gaudi:" ${docker_compose_path}) != 0 ]]; then
               git clone --depth 1 --branch v0.6.4.post2+Gaudi-1.19.0 https://github.com/HabanaAI/vllm-fork.git
-              sed -i 's/triton/triton==3.1.0/g' vllm-fork/requirements-hpu.txt
           fi
 
       - name: Build Image
 
@@ -61,8 +61,6 @@ The initially supported `Microservices` are described in the below table. More `
 A `Microservices` can be created by using the decorator `register_microservice`. Taking the `embedding microservice` as an example:
 
 ```python
-from langchain_community.embeddings import HuggingFaceHubEmbeddings
-
 from comps import register_microservice, EmbedDoc, ServiceType, TextDoc
 
 
 
@@ -51,8 +51,7 @@
 from comps.cores.mega.micro_service import MicroService, register_microservice, opea_microservices
 
 # Telemetry
-if os.getenv("ENABLE_OPEA_TELEMETRY", "false").lower() == "true":
-    from comps.cores.telemetry.opea_telemetry import opea_telemetry
+from comps.cores.telemetry.opea_telemetry import opea_telemetry
 
 # Common
 from comps.cores.common.component import OpeaComponent, OpeaComponentRegistry, OpeaComponentLoader
 
@@ -18,7 +18,7 @@
 from comps.agent.src.integrations.agent import instantiate_agent
 from comps.agent.src.integrations.global_var import assistants_global_kv, threads_global_kv
 from comps.agent.src.integrations.thread import instantiate_thread_memory, thread_completion_callback
-from comps.agent.src.integrations.utils import assemble_store_messages, get_args
+from comps.agent.src.integrations.utils import assemble_store_messages, get_args, get_latest_human_message_from_store
 from comps.cores.proto.api_protocol import (
     AssistantsObject,
     ChatCompletionRequest,
@@ -40,7 +40,7 @@
 
 logger.info("========initiating agent============")
 logger.info(f"args: {args}")
-agent_inst = instantiate_agent(args, args.strategy, with_memory=args.with_memory)
+agent_inst = instantiate_agent(args)
 
 
 class AgentCompletionRequest(ChatCompletionRequest):
@@ -76,7 +76,7 @@ async def llm_generate(input: AgentCompletionRequest):
     if isinstance(input.messages, str):
         messages = input.messages
     else:
-        # TODO: need handle multi-turn messages
+        # last user message
         messages = input.messages[-1]["content"]
 
     # 2. prepare the input for the agent
@@ -90,7 +90,6 @@ async def llm_generate(input: AgentCompletionRequest):
     else:
         logger.info("-----------NOT STREAMING-------------")
         response = await agent_inst.non_streaming_run(messages, config)
-        logger.info("-----------Response-------------")
         return GeneratedDoc(text=response, prompt=messages)
 
 
@@ -100,14 +99,14 @@ class RedisConfig(BaseModel):
 
 class AgentConfig(BaseModel):
     stream: Optional[bool] = False
-    agent_name: Optional[str] = "OPEA_Default_Agent"
+    agent_name: Optional[str] = "OPEA_Agent"
     strategy: Optional[str] = "react_llama"
-    role_description: Optional[str] = "LLM enhanced agent"
+    role_description: Optional[str] = "AI assistant"
     tools: Optional[str] = None
     recursion_limit: Optional[int] = 5
 
-    model: Optional[str] = "meta-llama/Meta-Llama-3-8B-Instruct"
-    llm_engine: Optional[str] = None
+    model: Optional[str] = "meta-llama/Llama-3.3-70B-Instruct"
+    llm_engine: Optional[str] = "vllm"
     llm_endpoint_url: Optional[str] = None
     max_new_tokens: Optional[int] = 1024
     top_k: Optional[int] = 10
@@ -117,10 +116,14 @@ class AgentConfig(BaseModel):
     return_full_text: Optional[bool] = False
     custom_prompt: Optional[str] = None
 
-    # short/long term memory
-    with_memory: Optional[bool] = False
-    # persistence
-    with_store: Optional[bool] = False
+    # # short/long term memory
+    with_memory: Optional[bool] = True
+    # agent memory config
+    # chat_completion api: only supports checkpointer memory
+    # assistants api: supports checkpointer and store memory
+    # checkpointer: in-memory checkpointer - MemorySaver()
+    # store: redis store
+    memory_type: Optional[str] = "checkpointer"  # choices: checkpointer, store
     store_config: Optional[RedisConfig] = None
 
     timeout: Optional[int] = 60
@@ -147,18 +150,17 @@ class CreateAssistant(CreateAssistantsRequest):
 )
 def create_assistants(input: CreateAssistant):
     # 1. initialize the agent
-    agent_inst = instantiate_agent(
-        input.agent_config, input.agent_config.strategy, with_memory=input.agent_config.with_memory
-    )
+    print("@@@ Initializing agent with config: ", input.agent_config)
+    agent_inst = instantiate_agent(input.agent_config)
     assistant_id = agent_inst.id
     created_at = int(datetime.now().timestamp())
     with assistants_global_kv as g_assistants:
         g_assistants[assistant_id] = (agent_inst, created_at)
     logger.info(f"Record assistant inst {assistant_id} in global KV")
 
-    if input.agent_config.with_store:
+    if input.agent_config.memory_type == "store":
         logger.info("Save Agent Config to database")
-        agent_inst.with_store = input.agent_config.with_store
+        # agent_inst.memory_type = input.agent_config.memory_type
         print(input)
         global db_client
         if db_client is None:
@@ -172,6 +174,7 @@ def create_assistants(input: CreateAssistant):
     return AssistantsObject(
         id=assistant_id,
         created_at=created_at,
+        model=input.agent_config.model,
     )
 
 
@@ -211,7 +214,7 @@ def create_messages(thread_id, input: CreateMessagesRequest):
     if isinstance(input.content, str):
         query = input.content
     else:
-        query = input.content[-1]["text"]
+        query = input.content[-1]["text"]  # content is a list of MessageContent
     msg_id, created_at = thread_inst.add_query(query)
 
     structured_content = MessageContent(text=query)
@@ -224,15 +227,18 @@ def create_messages(thread_id, input: CreateMessagesRequest):
         assistant_id=input.assistant_id,
     )
 
-    # save messages using assistant_id as key
+    # save messages using assistant_id_thread_id as key
     if input.assistant_id is not None:
         with assistants_global_kv as g_assistants:
             agent_inst, _ = g_assistants[input.assistant_id]
-        if agent_inst.with_store:
-            logger.info(f"Save Agent Messages, assistant_id: {input.assistant_id}, thread_id: {thread_id}")
+        if agent_inst.memory_type == "store":
+            logger.info(f"Save Messages, assistant_id: {input.assistant_id}, thread_id: {thread_id}")
             # if with store, db_client initialized already
             global db_client
-            db_client.put(msg_id, message.model_dump_json(), input.assistant_id)
+            namespace = f"{input.assistant_id}_{thread_id}"
+            # put(key: str, val: dict, collection: str = DEFAULT_COLLECTION)
+            db_client.put(msg_id, message.model_dump_json(), namespace)
+            logger.info(f"@@@ Save message to db: {msg_id}, {message.model_dump_json()}, {namespace}")
 
     return message
 
@@ -254,15 +260,24 @@ def create_run(thread_id, input: CreateRunResponse):
     with assistants_global_kv as g_assistants:
         agent_inst, _ = g_assistants[assistant_id]
 
-    config = {"recursion_limit": args.recursion_limit}
+    config = {
+        "recursion_limit": args.recursion_limit,
+        "configurable": {"session_id": thread_id, "thread_id": thread_id, "user_id": assistant_id},
+    }
 
-    if agent_inst.with_store:
-        # assemble multi-turn messages
+    if agent_inst.memory_type == "store":
         global db_client
-        input_query = assemble_store_messages(db_client.get_all(assistant_id))
+        namespace = f"{assistant_id}_{thread_id}"
+        # get the latest human message from store in the namespace
+        input_query = get_latest_human_message_from_store(db_client, namespace)
+        print("@@@@ Input_query from store: ", input_query)
     else:
         input_query = thread_inst.get_query()
+        print("@@@@ Input_query from thread_inst: ", input_query)
 
+    print("@@@ Agent instance:")
+    print(agent_inst.id)
+    print(agent_inst.args)
     try:
         return StreamingResponse(
             thread_completion_callback(agent_inst.stream_generator(input_query, config, thread_id), thread_id),
 
@@ -1,9 +1,13 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
+from .storage.persistence_redis import RedisPersistence
 from .utils import load_python_prompt
 
 
-def instantiate_agent(args, strategy="react_langchain", with_memory=False):
+def instantiate_agent(args):
+    strategy = args.strategy
+    with_memory = args.with_memory
+
     if args.custom_prompt is not None:
         print(f">>>>>> custom_prompt enabled, {args.custom_prompt}")
         custom_prompt = load_python_prompt(args.custom_prompt)
@@ -22,7 +26,7 @@ def instantiate_agent(args, strategy="react_langchain", with_memory=False):
         print("Initializing ReAct Agent with LLAMA")
         from .strategy.react import ReActAgentLlama
 
-        return ReActAgentLlama(args, with_memory, custom_prompt=custom_prompt)
+        return ReActAgentLlama(args, custom_prompt=custom_prompt)
     elif strategy == "plan_execute":
         from .strategy.planexec import PlanExecuteAgentWithLangGraph
 
 
@@ -3,6 +3,9 @@
 
 from uuid import uuid4
 
+from langgraph.checkpoint.memory import MemorySaver
+
+from ..storage.persistence_redis import RedisPersistence
 from ..tools import get_tools_descriptions
 from ..utils import adapt_custom_prompt, setup_chat_model
 
@@ -12,11 +15,25 @@ def __init__(self, args, local_vars=None, **kwargs) -> None:
         self.llm = setup_chat_model(args)
         self.tools_descriptions = get_tools_descriptions(args.tools)
         self.app = None
-        self.memory = None
         self.id = f"assistant_{self.__class__.__name__}_{uuid4()}"
         self.args = args
         adapt_custom_prompt(local_vars, kwargs.get("custom_prompt"))
-        print(self.tools_descriptions)
+        print("Registered tools: ", self.tools_descriptions)
+
+        if args.with_memory:
+            if args.memory_type == "checkpointer":
+                self.memory_type = "checkpointer"
+                self.checkpointer = MemorySaver()
+                self.store = None
+            elif args.memory_type == "store":
+                # print("Using Redis as store: ", args.store_config.redis_uri)
+                self.store = RedisPersistence(args.store_config.redis_uri)
+                self.memory_type = "store"
+            else:
+                raise ValueError("Invalid memory type!")
+        else:
+            self.store = None
+            self.checkpointer = None
 
     @property
     def is_vllm(self):
@@ -60,10 +77,7 @@ async def non_streaming_run(self, query, config):
         try:
             async for s in self.app.astream(initial_state, config=config, stream_mode="values"):
                 message = s["messages"][-1]
-                if isinstance(message, tuple):
-                    print(message)
-                else:
-                    message.pretty_print()
+                message.pretty_print()
 
             last_message = s["messages"][-1]
             print("******Response: ", last_message.content)