patch: remove usage of llm, chat model __call__ (#20788)

- `llm(prompt)` -> `llm.invoke(prompt)` - `llm(prompt=prompt` -> `llm.invoke(prompt)` (same with `messages=`) - `llm(prompt, callbacks=callbacks)` -> `llm.invoke(prompt, config={"callbacks": callbacks})` - `llm(prompt, **kwargs)` -> `llm.invoke(prompt, **kwargs)`
2025-07-04 04:07:54 +00:00 · 2024-04-24 19:39:23 -04:00 · 2024-04-24 19:39:23 -04:00 · 481d3855dc
commit 481d3855dc
parent 9b7fb381a4
181 changed files with 395 additions and 403 deletions
--- a/cookbook/Multi_modal_RAG_google.ipynb
+++ b/cookbook/Multi_modal_RAG_google.ipynb
@ -256,7 +256,7 @@
    "    \"\"\"Make image summary\"\"\"\n",
    "    model = ChatVertexAI(model_name=\"gemini-pro-vision\", max_output_tokens=1024)\n",
    "\n",
-    "    msg = model(\n",
+    "    msg = model.invoke(\n",
    "        [\n",
    "            HumanMessage(\n",
    "                content=[\n",
--- a/cookbook/camel_role_playing.ipynb
+++ b/cookbook/camel_role_playing.ipynb
@ -90,7 +90,7 @@
    "    ) -> AIMessage:\n",
    "        messages = self.update_messages(input_message)\n",
    "\n",
-    "        output_message = self.model(messages)\n",
+    "        output_message = self.model.invoke(messages)\n",
    "        self.update_messages(output_message)\n",
    "\n",
    "        return output_message"
--- a/cookbook/forward_looking_retrieval_augmented_generation.ipynb
+++ b/cookbook/forward_looking_retrieval_augmented_generation.ipynb
@ -362,7 +362,7 @@
   ],
   "source": [
    "llm = OpenAI()\n",
-    "llm(query)"
+    "llm.invoke(query)"
   ]
  },
  {
--- a/cookbook/gymnasium_agent_simulation.ipynb
+++ b/cookbook/gymnasium_agent_simulation.ipynb
@ -108,7 +108,7 @@
    "        return obs_message\n",
    "\n",
    "    def _act(self):\n",
-    "        act_message = self.model(self.message_history)\n",
+    "        act_message = self.model.invoke(self.message_history)\n",
    "        self.message_history.append(act_message)\n",
    "        action = int(self.action_parser.parse(act_message.content)[\"action\"])\n",
    "        return action\n",
--- a/cookbook/multi_player_dnd.ipynb
+++ b/cookbook/multi_player_dnd.ipynb
@ -74,7 +74,7 @@
    "        Applies the chatmodel to the message history\n",
    "        and returns the message string\n",
    "        \"\"\"\n",
-    "        message = self.model(\n",
+    "        message = self.model.invoke(\n",
    "            [\n",
    "                self.system_message,\n",
    "                HumanMessage(content=\"\\n\".join(self.message_history + [self.prefix])),\n",
--- a/cookbook/multiagent_authoritarian.ipynb
+++ b/cookbook/multiagent_authoritarian.ipynb
@ -79,7 +79,7 @@
    "        Applies the chatmodel to the message history\n",
    "        and returns the message string\n",
    "        \"\"\"\n",
-    "        message = self.model(\n",
+    "        message = self.model.invoke(\n",
    "            [\n",
    "                self.system_message,\n",
    "                HumanMessage(content=\"\\n\".join(self.message_history + [self.prefix])),\n",
@ -234,7 +234,7 @@
    "            termination_clause=self.termination_clause if self.stop else \"\",\n",
    "        )\n",
    "\n",
-    "        self.response = self.model(\n",
+    "        self.response = self.model.invoke(\n",
    "            [\n",
    "                self.system_message,\n",
    "                HumanMessage(content=response_prompt),\n",
@ -263,7 +263,7 @@
    "            speaker_names=speaker_names,\n",
    "        )\n",
    "\n",
-    "        choice_string = self.model(\n",
+    "        choice_string = self.model.invoke(\n",
    "            [\n",
    "                self.system_message,\n",
    "                HumanMessage(content=choice_prompt),\n",
@ -299,7 +299,7 @@
    "                ),\n",
    "                next_speaker=self.next_speaker,\n",
    "            )\n",
-    "            message = self.model(\n",
+    "            message = self.model.invoke(\n",
    "                [\n",
    "                    self.system_message,\n",
    "                    HumanMessage(content=next_prompt),\n",
--- a/cookbook/multiagent_bidding.ipynb
+++ b/cookbook/multiagent_bidding.ipynb
@ -71,7 +71,7 @@
    "        Applies the chatmodel to the message history\n",
    "        and returns the message string\n",
    "        \"\"\"\n",
-    "        message = self.model(\n",
+    "        message = self.model.invoke(\n",
    "            [\n",
    "                self.system_message,\n",
    "                HumanMessage(content=\"\\n\".join(self.message_history + [self.prefix])),\n",
@ -164,7 +164,7 @@
    "            message_history=\"\\n\".join(self.message_history),\n",
    "            recent_message=self.message_history[-1],\n",
    "        )\n",
-    "        bid_string = self.model([SystemMessage(content=prompt)]).content\n",
+    "        bid_string = self.model.invoke([SystemMessage(content=prompt)]).content\n",
    "        return bid_string"
   ]
  },
--- a/cookbook/petting_zoo.ipynb
+++ b/cookbook/petting_zoo.ipynb
@ -129,7 +129,7 @@
    "        return obs_message\n",
    "\n",
    "    def _act(self):\n",
-    "        act_message = self.model(self.message_history)\n",
+    "        act_message = self.model.invoke(self.message_history)\n",
    "        self.message_history.append(act_message)\n",
    "        action = int(self.action_parser.parse(act_message.content)[\"action\"])\n",
    "        return action\n",
--- a/cookbook/two_agent_debate_tools.ipynb
+++ b/cookbook/two_agent_debate_tools.ipynb
@ -84,7 +84,7 @@
    "        Applies the chatmodel to the message history\n",
    "        and returns the message string\n",
    "        \"\"\"\n",
-    "        message = self.model(\n",
+    "        message = self.model.invoke(\n",
    "            [\n",
    "                self.system_message,\n",
    "                HumanMessage(content=\"\\n\".join(self.message_history + [self.prefix])),\n",
--- a/cookbook/two_player_dnd.ipynb
+++ b/cookbook/two_player_dnd.ipynb
@ -70,7 +70,7 @@
    "        Applies the chatmodel to the message history\n",
    "        and returns the message string\n",
    "        \"\"\"\n",
-    "        message = self.model(\n",
+    "        message = self.model.invoke(\n",
    "            [\n",
    "                self.system_message,\n",
    "                HumanMessage(content=\"\\n\".join(self.message_history + [self.prefix])),\n",
--- a/docs/docs/integrations/callbacks/labelstudio.ipynb
+++ b/docs/docs/integrations/callbacks/labelstudio.ipynb
@ -194,7 +194,7 @@
    "llm = OpenAI(\n",
    "    temperature=0, callbacks=[LabelStudioCallbackHandler(project_name=\"My Project\")]\n",
    ")\n",
-    "print(llm(\"Tell me a joke\"))"
+    "print(llm.invoke(\"Tell me a joke\"))"
   ]
  },
  {
@ -270,7 +270,7 @@
    "        )\n",
    "    ]\n",
    ")\n",
-    "llm_results = chat_llm(\n",
+    "llm_results = chat_llm.invoke(\n",
    "    [\n",
    "        SystemMessage(content=\"Always use a lot of emojis\"),\n",
    "        HumanMessage(content=\"Tell me a joke\"),\n",
--- a/docs/docs/integrations/callbacks/llmonitor.md
+++ b/docs/docs/integrations/callbacks/llmonitor.md
@ -107,7 +107,7 @@ User tracking allows you to identify your users, track their cost, conversations
 from langchain_community.callbacks.llmonitor_callback import LLMonitorCallbackHandler, identify

 with identify("user-123"):
-    llm("Tell me a joke")
+    llm.invoke("Tell me a joke")

 with identify("user-456", user_props={"email": "user456@test.com"}):
    agen.run("Who is Leo DiCaprio's girlfriend?")
--- a/docs/docs/integrations/callbacks/promptlayer.ipynb
+++ b/docs/docs/integrations/callbacks/promptlayer.ipynb
@ -103,7 +103,7 @@
    "    temperature=0,\n",
    "    callbacks=[PromptLayerCallbackHandler(pl_tags=[\"chatopenai\"])],\n",
    ")\n",
-    "llm_results = chat_llm(\n",
+    "llm_results = chat_llm.invoke(\n",
    "    [\n",
    "        HumanMessage(content=\"What comes after 1,2,3 ?\"),\n",
    "        HumanMessage(content=\"Tell me another joke?\"),\n",
@ -129,10 +129,11 @@
    "from langchain_community.llms import GPT4All\n",
    "\n",
    "model = GPT4All(model=\"./models/gpt4all-model.bin\", n_ctx=512, n_threads=8)\n",
+    "callbacks = [PromptLayerCallbackHandler(pl_tags=[\"langchain\", \"gpt4all\"])]\n",
    "\n",
-    "response = model(\n",
+    "response = model.invoke(\n",
    "    \"Once upon a time, \",\n",
-    "    callbacks=[PromptLayerCallbackHandler(pl_tags=[\"langchain\", \"gpt4all\"])],\n",
+    "    config={\"callbacks\": callbacks},\n",
    ")"
   ]
  },
@ -181,7 +182,7 @@
    ")\n",
    "\n",
    "example_prompt = promptlayer.prompts.get(\"example\", version=1, langchain=True)\n",
-    "openai_llm(example_prompt.format(product=\"toasters\"))"
+    "openai_llm.invoke(example_prompt.format(product=\"toasters\"))"
   ]
  },
  {
--- a/docs/docs/integrations/callbacks/trubrics.ipynb
+++ b/docs/docs/integrations/callbacks/trubrics.ipynb
@ -315,7 +315,7 @@
    }
   ],
   "source": [
-    "chat_res = chat_llm(\n",
+    "chat_res = chat_llm.invoke(\n",
    "    [\n",
    "        SystemMessage(content=\"Every answer of yours must be about OpenAI.\"),\n",
    "        HumanMessage(content=\"Tell me a joke\"),\n",
--- a/docs/docs/integrations/chat/alibaba_cloud_pai_eas.ipynb
+++ b/docs/docs/integrations/chat/alibaba_cloud_pai_eas.ipynb
@ -72,7 +72,7 @@
   "metadata": {},
   "outputs": [],
   "source": [
-    "output = chat([HumanMessage(content=\"write a funny joke\")])\n",
+    "output = chat.invoke([HumanMessage(content=\"write a funny joke\")])\n",
    "print(\"output:\", output)"
   ]
  },
@ -90,7 +90,7 @@
   "outputs": [],
   "source": [
    "kwargs = {\"temperature\": 0.8, \"top_p\": 0.8, \"top_k\": 5}\n",
-    "output = chat([HumanMessage(content=\"write a funny joke\")], **kwargs)\n",
+    "output = chat.invoke([HumanMessage(content=\"write a funny joke\")], **kwargs)\n",
    "print(\"output:\", output)"
   ]
  },
--- a/docs/docs/integrations/chat/llama_edge.ipynb
+++ b/docs/docs/integrations/chat/llama_edge.ipynb
@ -62,7 +62,7 @@
    "messages = [system_message, user_message]\n",
    "\n",
    "# chat with wasm-chat service\n",
-    "response = chat(messages)\n",
+    "response = chat.invoke(messages)\n",
    "\n",
    "print(f\"[Bot] {response.content}\")"
   ]
--- a/docs/docs/integrations/chat/zhipuai.ipynb
+++ b/docs/docs/integrations/chat/zhipuai.ipynb
@ -119,7 +119,7 @@
   "metadata": {},
   "outputs": [],
   "source": [
-    "response = chat(messages)\n",
+    "response = chat.invoke(messages)\n",
    "print(response.content)  # Displays the AI-generated poem"
   ]
  },
--- a/docs/docs/integrations/llms/anyscale.ipynb
+++ b/docs/docs/integrations/llms/anyscale.ipynb
@ -147,7 +147,7 @@
    "\n",
    "@ray.remote(num_cpus=0.1)\n",
    "def send_query(llm, prompt):\n",
-    "    resp = llm(prompt)\n",
+    "    resp = llm.invoke(prompt)\n",
    "    return resp\n",
    "\n",
    "\n",
--- a/docs/docs/integrations/llms/aphrodite.ipynb
+++ b/docs/docs/integrations/llms/aphrodite.ipynb
@ -96,7 +96,7 @@
    ")\n",
    "\n",
    "print(\n",
-    "    llm(\n",
+    "    llm.invoke(\n",
    "        '<|system|>Enter RP mode. You are Ayumu \"Osaka\" Kasuga.<|user|>Hey Osaka. Tell me about yourself.<|model|>'\n",
    "    )\n",
    ")"
--- a/docs/docs/integrations/llms/baichuan.ipynb
+++ b/docs/docs/integrations/llms/baichuan.ipynb
@ -45,7 +45,7 @@
    "# Load the model\n",
    "llm = BaichuanLLM()\n",
    "\n",
-    "res = llm(\"What's your name?\")\n",
+    "res = llm.invoke(\"What's your name?\")\n",
    "print(res)"
   ]
  },
--- a/docs/docs/integrations/llms/baidu_qianfan_endpoint.ipynb
+++ b/docs/docs/integrations/llms/baidu_qianfan_endpoint.ipynb
@ -80,7 +80,7 @@
    "os.environ[\"QIANFAN_SK\"] = \"your_sk\"\n",
    "\n",
    "llm = QianfanLLMEndpoint(streaming=True)\n",
-    "res = llm(\"hi\")\n",
+    "res = llm.invoke(\"hi\")\n",
    "print(res)"
   ]
  },
@ -185,7 +185,7 @@
    "    model=\"ERNIE-Bot-turbo\",\n",
    "    endpoint=\"eb-instant\",\n",
    ")\n",
-    "res = llm(\"hi\")"
+    "res = llm.invoke(\"hi\")"
   ]
  },
  {
--- a/docs/docs/integrations/llms/bittensor.ipynb
+++ b/docs/docs/integrations/llms/bittensor.ipynb
@ -62,7 +62,7 @@
    "    } \"\"\"\n",
    "\n",
    "multi_response_llm = NIBittensorLLM(top_responses=10)\n",
-    "multi_resp = multi_response_llm(\"What is Neural Network Feeding Mechanism?\")\n",
+    "multi_resp = multi_response_llm.invoke(\"What is Neural Network Feeding Mechanism?\")\n",
    "json_multi_resp = json.loads(multi_resp)\n",
    "pprint(json_multi_resp)"
   ]
--- a/docs/docs/integrations/llms/ctransformers.ipynb
+++ b/docs/docs/integrations/llms/ctransformers.ipynb
@ -62,7 +62,7 @@
   "metadata": {},
   "outputs": [],
   "source": [
-    "print(llm(\"AI is going to\"))"
+    "print(llm.invoke(\"AI is going to\"))"
   ]
  },
  {
@ -85,7 +85,7 @@
    "    model=\"marella/gpt-2-ggml\", callbacks=[StreamingStdOutCallbackHandler()]\n",
    ")\n",
    "\n",
-    "response = llm(\"AI is going to\")"
+    "response = llm.invoke(\"AI is going to\")"
   ]
  },
  {
--- a/docs/docs/integrations/llms/ctranslate2.ipynb
+++ b/docs/docs/integrations/llms/ctranslate2.ipynb
@ -97,7 +97,7 @@
   ],
   "source": [
    "print(\n",
-    "    llm(\n",
+    "    llm.invoke(\n",
    "        \"He presented me with plausible evidence for the existence of unicorns: \",\n",
    "        max_length=256,\n",
    "        sampling_topk=50,\n",
--- a/docs/docs/integrations/llms/deepsparse.ipynb
+++ b/docs/docs/integrations/llms/deepsparse.ipynb
@ -32,7 +32,7 @@
    "    model=\"zoo:nlg/text_generation/codegen_mono-350m/pytorch/huggingface/bigpython_bigquery_thepile/base-none\"\n",
    ")\n",
    "\n",
-    "print(llm(\"def fib():\"))"
+    "print(llm.invoke(\"def fib():\"))"
   ]
  },
  {
--- a/docs/docs/integrations/llms/edenai.ipynb
+++ b/docs/docs/integrations/llms/edenai.ipynb
@ -203,7 +203,7 @@
    "User: Answer the following yes/no question by reasoning step by step. Can a dog drive a car?\n",
    "Assistant:\n",
    "\"\"\"\n",
-    "print(llm(prompt))"
+    "print(llm.invoke(prompt))"
   ]
  },
  {
--- a/docs/docs/integrations/llms/google_vertex_ai_palm.ipynb
+++ b/docs/docs/integrations/llms/google_vertex_ai_palm.ipynb
@ -359,7 +359,7 @@
    "}\n",
    "message = HumanMessage(content=[text_message, image_message])\n",
    "\n",
-    "output = llm([message])\n",
+    "output = llm.invoke([message])\n",
    "print(output.content)"
   ]
  },
@ -432,7 +432,7 @@
    "}\n",
    "message = HumanMessage(content=[text_message, image_message])\n",
    "\n",
-    "output = llm([message])\n",
+    "output = llm.invoke([message])\n",
    "print(output.content)"
   ]
  },
@ -457,7 +457,7 @@
   "outputs": [],
   "source": [
    "message2 = HumanMessage(content=\"And where the image is taken?\")\n",
-    "output2 = llm([message, output, message2])\n",
+    "output2 = llm.invoke([message, output, message2])\n",
    "print(output2.content)"
   ]
  },
@ -486,7 +486,7 @@
    "}\n",
    "message = HumanMessage(content=[text_message, image_message])\n",
    "\n",
-    "output = llm([message])\n",
+    "output = llm.invoke([message])\n",
    "print(output.content)"
   ]
  },
--- a/docs/docs/integrations/llms/koboldai.ipynb
+++ b/docs/docs/integrations/llms/koboldai.ipynb
@ -57,7 +57,9 @@
   },
   "outputs": [],
   "source": [
-    "response = llm(\"### Instruction:\\nWhat is the first book of the bible?\\n### Response:\")"
+    "response = llm.invoke(\n",
+    "    \"### Instruction:\\nWhat is the first book of the bible?\\n### Response:\"\n",
+    ")"
   ]
  }
 ],
--- a/docs/docs/integrations/llms/konko.ipynb
+++ b/docs/docs/integrations/llms/konko.ipynb
@ -90,7 +90,7 @@
    "llm = Konko(model=\"mistralai/mistral-7b-v0.1\", temperature=0.1, max_tokens=128)\n",
    "\n",
    "input_ = \"\"\"You are a helpful assistant. Explain Big Bang Theory briefly.\"\"\"\n",
-    "print(llm(input_))"
+    "print(llm.invoke(input_))"
   ]
  },
  {
--- a/docs/docs/integrations/llms/llm_caching.ipynb
+++ b/docs/docs/integrations/llms/llm_caching.ipynb
@ -1020,7 +1020,7 @@
   "source": [
    "%%time\n",
    "\n",
-    "print(llm(\"Why is the Moon always showing the same side?\"))"
+    "print(llm.invoke(\"Why is the Moon always showing the same side?\"))"
   ]
  },
  {
@ -1044,7 +1044,7 @@
   "source": [
    "%%time\n",
    "\n",
-    "print(llm(\"Why is the Moon always showing the same side?\"))"
+    "print(llm.invoke(\"Why is the Moon always showing the same side?\"))"
   ]
  },
  {
@ -1109,7 +1109,7 @@
   "source": [
    "%%time\n",
    "\n",
-    "print(llm(\"Why is the Moon always showing the same side?\"))"
+    "print(llm.invoke(\"Why is the Moon always showing the same side?\"))"
   ]
  },
  {
@ -1133,7 +1133,7 @@
   "source": [
    "%%time\n",
    "\n",
-    "print(llm(\"How come we always see one face of the moon?\"))"
+    "print(llm.invoke(\"How come we always see one face of the moon?\"))"
   ]
  },
  {
@ -1238,7 +1238,7 @@
   "source": [
    "%%time\n",
    "\n",
-    "print(llm(\"Is a true fakery the same as a fake truth?\"))"
+    "print(llm.invoke(\"Is a true fakery the same as a fake truth?\"))"
   ]
  },
  {
@ -1262,7 +1262,7 @@
   "source": [
    "%%time\n",
    "\n",
-    "print(llm(\"Is a true fakery the same as a fake truth?\"))"
+    "print(llm.invoke(\"Is a true fakery the same as a fake truth?\"))"
   ]
  },
  {
@ -1327,7 +1327,7 @@
   "source": [
    "%%time\n",
    "\n",
-    "print(llm(\"Are there truths that are false?\"))"
+    "print(llm.invoke(\"Are there truths that are false?\"))"
   ]
  },
  {
@ -1351,7 +1351,7 @@
   "source": [
    "%%time\n",
    "\n",
-    "print(llm(\"Is is possible that something false can be also true?\"))"
+    "print(llm.invoke(\"Is is possible that something false can be also true?\"))"
   ]
  },
  {
--- a/docs/docs/integrations/llms/predibase.ipynb
+++ b/docs/docs/integrations/llms/predibase.ipynb
@ -96,7 +96,7 @@
   "metadata": {},
   "outputs": [],
   "source": [
-    "response = model(\"Can you recommend me a nice dry wine?\")\n",
+    "response = model.invoke(\"Can you recommend me a nice dry wine?\")\n",
    "print(response)"
   ]
  },
@ -269,7 +269,7 @@
   "metadata": {},
   "outputs": [],
   "source": [
-    "# response = model(\"Can you help categorize the following emails into positive, negative, and neutral?\")"
+    "# response = model.invoke(\"Can you help categorize the following emails into positive, negative, and neutral?\")"
   ]
  }
 ],
--- a/docs/docs/integrations/llms/replicate.ipynb
+++ b/docs/docs/integrations/llms/replicate.ipynb
@ -323,7 +323,7 @@
    "User: Answer the following yes/no question by reasoning step by step. Can a dog drive a car?\n",
    "Assistant:\n",
    "\"\"\"\n",
-    "_ = llm(prompt)"
+    "_ = llm.invoke(prompt)"
   ]
  },
  {
@ -376,13 +376,13 @@
    "Assistant:\n",
    "\"\"\"\n",
    "start_time = time.perf_counter()\n",
-    "raw_output = llm(prompt)  # raw output, no stop\n",
+    "raw_output = llm.invoke(prompt)  # raw output, no stop\n",
    "end_time = time.perf_counter()\n",
    "print(f\"Raw output:\\n {raw_output}\")\n",
    "print(f\"Raw output runtime: {end_time - start_time} seconds\")\n",
    "\n",
    "start_time = time.perf_counter()\n",
-    "stopped_output = llm(prompt, stop=[\"\\n\\n\"])  # stop on double newlines\n",
+    "stopped_output = llm.invoke(prompt, stop=[\"\\n\\n\"])  # stop on double newlines\n",
    "end_time = time.perf_counter()\n",
    "print(f\"Stopped output:\\n {stopped_output}\")\n",
    "print(f\"Stopped output runtime: {end_time - start_time} seconds\")"
--- a/docs/docs/integrations/llms/sparkllm.ipynb
+++ b/docs/docs/integrations/llms/sparkllm.ipynb
@ -65,7 +65,7 @@
    "# Load the model\n",
    "llm = SparkLLM()\n",
    "\n",
-    "res = llm(\"What's your name?\")\n",
+    "res = llm.invoke(\"What's your name?\")\n",
    "print(res)"
   ]
  },
--- a/docs/docs/integrations/providers/ctransformers.mdx
+++ b/docs/docs/integrations/providers/ctransformers.mdx
@ -23,7 +23,7 @@ It provides a unified interface for all models:
 ```python
 llm = CTransformers(model='/path/to/ggml-gpt-2.bin', model_type='gpt2')

-print(llm('AI is going to'))
+print(llm.invoke('AI is going to'))
 ```

 If you are getting `illegal instruction` error, try using `lib='avx'` or `lib='basic'`:
--- a/docs/docs/integrations/providers/deepsparse.mdx
+++ b/docs/docs/integrations/providers/deepsparse.mdx
@ -22,7 +22,7 @@ It provides a unified interface for all models:
 ```python
 llm = DeepSparse(model='zoo:nlg/text_generation/codegen_mono-350m/pytorch/huggingface/bigpython_bigquery_thepile/base-none')

-print(llm('def fib():'))
+print(llm.invoke('def fib():'))
 ```

 Additional parameters can be passed using the `config` parameter:
--- a/docs/docs/integrations/providers/flyte.mdx
+++ b/docs/docs/integrations/providers/flyte.mdx
@ -83,7 +83,7 @@ def langchain_llm() -> str:
        temperature=0.2,
        callbacks=[FlyteCallbackHandler()],
    )
-    return llm([HumanMessage(content="Tell me a joke")]).content
+    return llm.invoke([HumanMessage(content="Tell me a joke")]).content
 ```

 ### Chain
--- a/docs/docs/integrations/providers/gpt4all.mdx
+++ b/docs/docs/integrations/providers/gpt4all.mdx
@ -27,7 +27,7 @@ from langchain_community.llms import GPT4All
 model = GPT4All(model="./models/mistral-7b-openorca.Q4_0.gguf", n_threads=8)

 # Generate text
-response = model("Once upon a time, ")
+response = model.invoke("Once upon a time, ")
 ```

 You can also customize the generation parameters, such as n_predict, temp, top_p, top_k, and others.
--- a/docs/docs/integrations/providers/helicone.mdx
+++ b/docs/docs/integrations/providers/helicone.mdx
@ -29,7 +29,7 @@ openai.api_base = "https://oai.hconeai.com/v1"

 llm = OpenAI(temperature=0.9, headers={"Helicone-Cache-Enabled": "true"})
 text = "What is a helicone?"
-print(llm(text))
+print(llm.invoke(text))
 ```

 [Helicone caching docs](https://docs.helicone.ai/advanced-usage/caching)
@ -47,7 +47,7 @@ llm = OpenAI(temperature=0.9, headers={
        "Helicone-Property-App": "mobile",
      })
 text = "What is a helicone?"
-print(llm(text))
+print(llm.invoke(text))
 ```

 [Helicone property docs](https://docs.helicone.ai/advanced-usage/custom-properties)
--- a/docs/docs/integrations/providers/konko.mdx
+++ b/docs/docs/integrations/providers/konko.mdx
@ -44,7 +44,7 @@ See a usage [example](/docs/integrations/llms/konko).
  from langchain.llms import Konko
  llm = Konko(max_tokens=800, model='mistralai/Mistral-7B-v0.1')
  prompt = "Generate a Product Description for Apple Iphone 15"
-  response = llm(prompt)
+  response = llm.invoke(prompt)
  ```

 ## Chat Models
--- a/docs/docs/integrations/providers/predibase.md
+++ b/docs/docs/integrations/providers/predibase.md
@ -23,7 +23,7 @@ model = Predibase(
    predibase_sdk_version=None,  # optional parameter (defaults to the latest Predibase SDK version if omitted)
 )

-response = model("Can you recommend me a nice dry wine?")
+response = model.invoke("Can you recommend me a nice dry wine?")
 print(response)
 ```

@ -44,7 +44,7 @@ model = Predibase(
    adapter_version=1,
 )

-response = model("Can you recommend me a nice dry wine?")
+response = model.invoke("Can you recommend me a nice dry wine?")
 print(response)
 ```

@ -64,6 +64,6 @@ model = Predibase(
    adapter_id="predibase/e2e_nlg",
 )

-response = model("Can you recommend me a nice dry wine?")
+response = model.invoke("Can you recommend me a nice dry wine?")
 print(response)
 ```
--- a/docs/docs/integrations/providers/rwkv.mdx
+++ b/docs/docs/integrations/providers/rwkv.mdx
@ -44,7 +44,7 @@ def generate_prompt(instruction, input=None):


 model = RWKV(model="./models/RWKV-4-Raven-3B-v7-Eng-20230404-ctx4096.pth", strategy="cpu fp32", tokens_path="./rwkv/20B_tokenizer.json")
-response = model(generate_prompt("Once upon a time, "))
+response = model.invoke(generate_prompt("Once upon a time, "))
 ```
 ## Model File

--- a/docs/docs/use_cases/data_generation.ipynb
+++ b/docs/docs/use_cases/data_generation.ipynb
@ -545,7 +545,7 @@
    ")\n",
    "\n",
    "_input = prompt.format_prompt(text=dataset[0][\"text\"])\n",
-    "output = llm(_input.to_string())\n",
+    "output = llm.invoke(_input.to_string())\n",
    "\n",
    "parsed = parser.parse(output)\n",
    "parsed"
--- a/libs/community/langchain_community/cache.py
+++ b/libs/community/langchain_community/cache.py
@ -1115,7 +1115,8 @@ class CassandraCache(BaseCache):
    ) -> None:
        """
        A wrapper around `delete` with the LLM being passed.
-        In case the llm(prompt) calls have a `stop` param, you should pass it here
+        In case the llm.invoke(prompt) calls have a `stop` param, you should
+        pass it here
        """
        llm_string = get_prompts(
            {**llm.dict(), **{"stop": stop}},
@ -1505,7 +1506,8 @@ class AstraDBCache(BaseCache):
    ) -> None:
        """
        A wrapper around `delete` with the LLM being passed.
-        In case the llm(prompt) calls have a `stop` param, you should pass it here
+        In case the llm.invoke(prompt) calls have a `stop` param, you should
+        pass it here
        """
        llm_string = get_prompts(
            {**llm.dict(), **{"stop": stop}},
@ -1518,7 +1520,8 @@ class AstraDBCache(BaseCache):
    ) -> None:
        """
        A wrapper around `adelete` with the LLM being passed.
-        In case the llm(prompt) calls have a `stop` param, you should pass it here
+        In case the llm.invoke(prompt) calls have a `stop` param, you should
+        pass it here
        """
        llm_string = (
            await aget_prompts(
--- a/libs/community/langchain_community/callbacks/context_callback.py
+++ b/libs/community/langchain_community/callbacks/context_callback.py
@ -58,7 +58,7 @@ class ContextCallbackHandler(BaseCallbackHandler):
        ...     SystemMessage(content="You translate English to French."),
        ...     HumanMessage(content="I love programming with LangChain."),
        ... ]
-        >>> chat(messages)
+        >>> chat.invoke(messages)

    Chain Example:
        >>> from langchain.chains import LLMChain
--- a/libs/community/langchain_community/chat_models/azureml_endpoint.py
+++ b/libs/community/langchain_community/chat_models/azureml_endpoint.py
@ -263,7 +263,7 @@ class AzureMLChatOnlineEndpoint(BaseChatModel, AzureMLBaseEndpoint):
            The string generated by the model.
        Example:
            .. code-block:: python
-                response = azureml_model("Tell me a joke.")
+                response = azureml_model.invoke("Tell me a joke.")
        """
        _model_kwargs = self.model_kwargs or {}
        _model_kwargs.update(kwargs)
--- a/libs/community/langchain_community/chat_models/baidu_qianfan_endpoint.py
+++ b/libs/community/langchain_community/chat_models/baidu_qianfan_endpoint.py
@ -250,7 +250,7 @@ class QianfanChatEndpoint(BaseChatModel):

        Example:
            .. code-block:: python
-                response = qianfan_model("Tell me a joke.")
+                response = qianfan_model.invoke("Tell me a joke.")
        """
        if self.streaming:
            completion = ""
--- a/libs/community/langchain_community/llms/aleph_alpha.py
+++ b/libs/community/langchain_community/llms/aleph_alpha.py
@ -284,4 +284,4 @@ class AlephAlpha(LLM):
 if __name__ == "__main__":
    aa = AlephAlpha()

-    print(aa("How are you?"))  # noqa: T201
+    print(aa.invoke("How are you?"))  # noqa: T201
--- a/libs/community/langchain_community/llms/anthropic.py
+++ b/libs/community/langchain_community/llms/anthropic.py
@ -170,13 +170,13 @@ class Anthropic(LLM, _AnthropicCommon):

            # Simplest invocation, automatically wrapped with HUMAN_PROMPT
            # and AI_PROMPT.
-            response = model("What are the biggest risks facing humanity?")
+            response = model.invoke("What are the biggest risks facing humanity?")

            # Or if you want to use the chat mode, build a few-shot-prompt, or
            # put words in the Assistant's mouth, use HUMAN_PROMPT and AI_PROMPT:
            raw_prompt = "What are the biggest risks facing humanity?"
            prompt = f"{anthropic.HUMAN_PROMPT} {prompt}{anthropic.AI_PROMPT}"
-            response = model(prompt)
+            response = model.invoke(prompt)
    """

    class Config:
@ -236,7 +236,7 @@ class Anthropic(LLM, _AnthropicCommon):

                prompt = "What are the biggest risks facing humanity?"
                prompt = f"\n\nHuman: {prompt}\n\nAssistant:"
-                response = model(prompt)
+                response = model.invoke(prompt)

        """
        if self.streaming:
--- a/libs/community/langchain_community/llms/anyscale.py
+++ b/libs/community/langchain_community/llms/anyscale.py
@ -75,7 +75,7 @@ class Anyscale(BaseOpenAI):
            # To leverage Ray for parallel processing
            @ray.remote(num_cpus=1)
            def send_query(llm, text):
-                resp = llm(text)
+                resp = llm.invoke(text)
                return resp
            futures = [send_query.remote(anyscalellm, text) for text in texts]
            results = ray.get(futures)
--- a/libs/community/langchain_community/llms/azureml_endpoint.py
+++ b/libs/community/langchain_community/llms/azureml_endpoint.py
@ -528,7 +528,7 @@ class AzureMLOnlineEndpoint(BaseLLM, AzureMLBaseEndpoint):
            The string generated by the model.
        Example:
            .. code-block:: python
-                response = azureml_model("Tell me a joke.")
+                response = azureml_model.invoke("Tell me a joke.")
        """
        _model_kwargs = self.model_kwargs or {}
        _model_kwargs.update(kwargs)
--- a/libs/community/langchain_community/llms/baidu_qianfan_endpoint.py
+++ b/libs/community/langchain_community/llms/baidu_qianfan_endpoint.py
@ -172,7 +172,7 @@ class QianfanLLMEndpoint(LLM):

        Example:
            .. code-block:: python
-                response = qianfan_model("Tell me a joke.")
+                response = qianfan_model.invoke("Tell me a joke.")
        """
        if self.streaming:
            completion = ""
--- a/libs/community/langchain_community/llms/bedrock.py
+++ b/libs/community/langchain_community/llms/bedrock.py
@ -829,7 +829,7 @@ class Bedrock(LLM, BedrockBase):
        Example:
            .. code-block:: python

-                response = llm("Tell me a joke.")
+                response = llm.invoke("Tell me a joke.")
        """

        if self.streaming:
--- a/libs/community/langchain_community/llms/chatglm.py
+++ b/libs/community/langchain_community/llms/chatglm.py
@ -72,7 +72,7 @@ class ChatGLM(LLM):
        Example:
            .. code-block:: python

-                response = chatglm_llm("Who are you?")
+                response = chatglm_llm.invoke("Who are you?")
        """

        _model_kwargs = self.model_kwargs or {}
--- a/libs/community/langchain_community/llms/chatglm3.py
+++ b/libs/community/langchain_community/llms/chatglm3.py
@ -106,7 +106,7 @@ class ChatGLM3(LLM):
        Example:
            .. code-block:: python

-                response = chatglm_llm("Who are you?")
+                response = chatglm_llm.invoke("Who are you?")
        """
        import httpx

--- a/libs/community/langchain_community/llms/clarifai.py
+++ b/libs/community/langchain_community/llms/clarifai.py
@ -128,7 +128,7 @@ class Clarifai(LLM):
        Example:
            .. code-block:: python

-                response = clarifai_llm("Tell me a joke.")
+                response = clarifai_llm.invoke("Tell me a joke.")
        """

        try:
--- a/libs/community/langchain_community/llms/ctransformers.py
+++ b/libs/community/langchain_community/llms/ctransformers.py
@ -97,7 +97,7 @@ class CTransformers(LLM):
        Example:
            .. code-block:: python

-                response = llm("Tell me a joke.")
+                response = llm.invoke("Tell me a joke.")
        """
        text = []
        _run_manager = run_manager or CallbackManagerForLLMRun.get_noop_manager()
@ -125,7 +125,7 @@ class CTransformers(LLM):

        Example:
            .. code-block:: python
-                response = llm("Once upon a time, ")
+                response = llm.invoke("Once upon a time, ")
        """
        text_callback = None
        if run_manager:
--- a/libs/community/langchain_community/llms/deepsparse.py
+++ b/libs/community/langchain_community/llms/deepsparse.py
@ -92,7 +92,7 @@ class DeepSparse(LLM):
            .. code-block:: python
                from langchain_community.llms import DeepSparse
                llm = DeepSparse(model="zoo:nlg/text_generation/codegen_mono-350m/pytorch/huggingface/bigpython_bigquery_thepile/base_quant-none")
-                llm("Tell me a joke.")
+                llm.invoke("Tell me a joke.")
        """
        if self.streaming:
            combined_output = ""
@ -130,7 +130,7 @@ class DeepSparse(LLM):
            .. code-block:: python
                from langchain_community.llms import DeepSparse
                llm = DeepSparse(model="zoo:nlg/text_generation/codegen_mono-350m/pytorch/huggingface/bigpython_bigquery_thepile/base_quant-none")
-                llm("Tell me a joke.")
+                llm.invoke("Tell me a joke.")
        """
        if self.streaming:
            combined_output = ""
--- a/libs/community/langchain_community/llms/gpt4all.py
+++ b/libs/community/langchain_community/llms/gpt4all.py
@ -21,7 +21,7 @@ class GPT4All(LLM):
            model = GPT4All(model="./models/gpt4all-model.bin", n_threads=8)

            # Simplest invocation
-            response = model("Once upon a time, ")
+            response = model.invoke("Once upon a time, ")
    """

    model: str
@ -197,7 +197,7 @@ class GPT4All(LLM):
            .. code-block:: python

                prompt = "Once upon a time, "
-                response = model(prompt, n_predict=55)
+                response = model.invoke(prompt, n_predict=55)
        """
        text_callback = None
        if run_manager:
--- a/libs/community/langchain_community/llms/huggingface_endpoint.py
+++ b/libs/community/langchain_community/llms/huggingface_endpoint.py
@ -43,7 +43,7 @@ class HuggingFaceEndpoint(LLM):
                repetition_penalty=1.03,
                huggingfacehub_api_token="my-api-key"
            )
-            print(llm("What is Deep Learning?"))
+            print(llm.invoke("What is Deep Learning?"))

            # Streaming response example
            from langchain_core.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
@ -61,7 +61,7 @@ class HuggingFaceEndpoint(LLM):
                streaming=True,
                huggingfacehub_api_token="my-api-key"
            )
-            print(llm("What is Deep Learning?"))
+            print(llm.invoke("What is Deep Learning?"))

    """  # noqa: E501

--- a/libs/community/langchain_community/llms/huggingface_text_gen_inference.py
+++ b/libs/community/langchain_community/llms/huggingface_text_gen_inference.py
@ -36,7 +36,7 @@ class HuggingFaceTextGenInference(LLM):
                temperature=0.01,
                repetition_penalty=1.03,
            )
-            print(llm("What is Deep Learning?"))  # noqa: T201
+            print(llm.invoke("What is Deep Learning?"))  # noqa: T201

            # Streaming response example
            from langchain_community.callbacks import streaming_stdout
@ -53,7 +53,7 @@ class HuggingFaceTextGenInference(LLM):
                callbacks=callbacks,
                streaming=True
            )
-            print(llm("What is Deep Learning?"))  # noqa: T201
+            print(llm.invoke("What is Deep Learning?"))  # noqa: T201

    """

--- a/libs/community/langchain_community/llms/koboldai.py
+++ b/libs/community/langchain_community/llms/koboldai.py
@ -147,7 +147,7 @@ class KoboldApiLLM(LLM):
                from langchain_community.llms import KoboldApiLLM

                llm = KoboldApiLLM(endpoint="http://localhost:5000")
-                llm("Write a story about dragons.")
+                llm.invoke("Write a story about dragons.")
        """
        data: Dict[str, Any] = {
            "prompt": prompt,
--- a/libs/community/langchain_community/llms/llamacpp.py
+++ b/libs/community/langchain_community/llms/llamacpp.py
@ -278,7 +278,7 @@ class LlamaCpp(LLM):

                from langchain_community.llms import LlamaCpp
                llm = LlamaCpp(model_path="/path/to/local/llama/model.bin")
-                llm("This is a prompt.")
+                llm.invoke("This is a prompt.")
        """
        if self.streaming:
            # If streaming is enabled, we use the stream
--- a/libs/community/langchain_community/llms/mosaicml.py
+++ b/libs/community/langchain_community/llms/mosaicml.py
@ -115,7 +115,7 @@ class MosaicML(LLM):
        Example:
            .. code-block:: python

-                response = mosaic_llm("Tell me a joke.")
+                response = mosaic_llm.invoke("Tell me a joke.")
        """
        _model_kwargs = self.model_kwargs or {}

--- a/libs/community/langchain_community/llms/opaqueprompts.py
+++ b/libs/community/langchain_community/llms/opaqueprompts.py
@ -84,7 +84,7 @@ class OpaquePrompts(LLM):
        Example:
            .. code-block:: python

-                response = op_llm("Tell me a joke.")
+                response = op_llm.invoke("Tell me a joke.")
        """
        import opaqueprompts as op

--- a/libs/community/langchain_community/llms/openllm.py
+++ b/libs/community/langchain_community/llms/openllm.py
@ -63,7 +63,7 @@ class OpenLLM(LLM):
                model_name='flan-t5',
                model_id='google/flan-t5-large',
            )
-            llm("What is the difference between a duck and a goose?")
+            llm.invoke("What is the difference between a duck and a goose?")

    For all available supported models, you can run 'openllm models'.

--- a/libs/community/langchain_community/llms/predictionguard.py
+++ b/libs/community/langchain_community/llms/predictionguard.py
@ -100,7 +100,7 @@ class PredictionGuard(LLM):
            The string generated by the model.
        Example:
            .. code-block:: python
-                response = pgllm("Tell me a joke.")
+                response = pgllm.invoke("Tell me a joke.")
        """
        import predictionguard as pg

--- a/libs/community/langchain_community/llms/rwkv.py
+++ b/libs/community/langchain_community/llms/rwkv.py
@ -25,7 +25,7 @@ class RWKV(LLM, BaseModel):
            model = RWKV(model="./models/rwkv-3b-fp16.bin", strategy="cpu fp32")

            # Simplest invocation
-            response = model("Once upon a time, ")
+            response = model.invoke("Once upon a time, ")
    """

    model: str
@ -225,7 +225,7 @@ class RWKV(LLM, BaseModel):
            .. code-block:: python

                prompt = "Once upon a time, "
-                response = model(prompt, n_predict=55)
+                response = model.invoke(prompt, n_predict=55)
        """
        text = self.rwkv_generate(prompt)

--- a/libs/community/langchain_community/llms/textgen.py
+++ b/libs/community/langchain_community/llms/textgen.py
@ -199,7 +199,7 @@ class TextGen(LLM):

                from langchain_community.llms import TextGen
                llm = TextGen(model_url="http://localhost:5000")
-                llm("Write a story about llamas.")
+                llm.invoke("Write a story about llamas.")
        """
        if self.streaming:
            combined_text_output = ""
@ -245,7 +245,7 @@ class TextGen(LLM):

                from langchain_community.llms import TextGen
                llm = TextGen(model_url="http://localhost:5000")
-                llm("Write a story about llamas.")
+                llm.invoke("Write a story about llamas.")
        """
        if self.streaming:
            combined_text_output = ""
--- a/libs/community/langchain_community/llms/watsonxllm.py
+++ b/libs/community/langchain_community/llms/watsonxllm.py
@ -320,7 +320,7 @@ class WatsonxLLM(BaseLLM):
        Example:
            .. code-block:: python

-                response = watsonx_llm("What is a molecule")
+                response = watsonx_llm.invoke("What is a molecule")
        """
        result = self._generate(
            prompts=[prompt], stop=stop, run_manager=run_manager, **kwargs
--- a/libs/community/langchain_community/llms/weight_only_quantization.py
+++ b/libs/community/langchain_community/llms/weight_only_quantization.py
@ -222,7 +222,7 @@ class WeightOnlyQuantPipeline(LLM):
                    model_id="google/flan-t5-large",
                    task="text2text-generation",
                )
-                llm("This is a prompt.")
+                llm.invoke("This is a prompt.")
        """
        response = self.pipeline(prompt)
        if self.pipeline.task == "text-generation":
--- a/libs/community/langchain_community/llms/xinference.py
+++ b/libs/community/langchain_community/llms/xinference.py
@ -62,7 +62,7 @@ class Xinference(LLM):
            model_uid = {model_uid} # replace model_uid with the model UID return from launching the model
        )

-        llm(
+        llm.invoke(
            prompt="Q: where can we visit in the capital of France? A:",
            generate_config={"max_tokens": 1024, "stream": True},
        )
--- a/libs/community/langchain_community/llms/yuan2.py
+++ b/libs/community/langchain_community/llms/yuan2.py
@ -26,7 +26,7 @@ class Yuan2(LLM):
                top_k=40,
            )
            print(yuan_llm)
-            print(yuan_llm("你是谁？"))
+            print(yuan_llm.invoke("你是谁？"))
    """

    infer_api: str = "http://127.0.0.1:8000/yuan"
@ -137,7 +137,7 @@ class Yuan2(LLM):
        Example:
            .. code-block:: python

-                response = yuan_llm("你能做什么?")
+                response = yuan_llm.invoke("你能做什么?")
        """

        if self.use_history:
--- a/libs/community/tests/integration_tests/callbacks/test_openai_callback.py
+++ b/libs/community/tests/integration_tests/callbacks/test_openai_callback.py
@ -9,14 +9,14 @@ from langchain_community.llms import OpenAI
 async def test_openai_callback() -> None:
    llm = OpenAI(temperature=0)
    with get_openai_callback() as cb:
-        llm("What is the square root of 4?")
+        llm.invoke("What is the square root of 4?")

    total_tokens = cb.total_tokens
    assert total_tokens > 0

    with get_openai_callback() as cb:
-        llm("What is the square root of 4?")
-        llm("What is the square root of 4?")
+        llm.invoke("What is the square root of 4?")
+        llm.invoke("What is the square root of 4?")

    assert cb.total_tokens == total_tokens * 2

@ -44,8 +44,8 @@ def test_openai_callback_batch_llm() -> None:
    total_tokens = cb.total_tokens

    with get_openai_callback() as cb:
-        llm("What is the square root of 4?")
-        llm("What is the square root of 4?")
+        llm.invoke("What is the square root of 4?")
+        llm.invoke("What is the square root of 4?")

    assert cb.total_tokens == total_tokens

--- a/libs/community/tests/integration_tests/chat_models/test_anthropic.py
+++ b/libs/community/tests/integration_tests/chat_models/test_anthropic.py
@ -17,7 +17,7 @@ def test_anthropic_call() -> None:
    """Test valid call to anthropic."""
    chat = ChatAnthropic(model="test")
    message = HumanMessage(content="Hello")
-    response = chat([message])
+    response = chat.invoke([message])
    assert isinstance(response, AIMessage)
    assert isinstance(response.content, str)

@ -44,7 +44,7 @@ def test_anthropic_streaming() -> None:
    """Test streaming tokens from anthropic."""
    chat = ChatAnthropic(model="test", streaming=True)
    message = HumanMessage(content="Hello")
-    response = chat([message])
+    response = chat.invoke([message])
    assert isinstance(response, AIMessage)
    assert isinstance(response.content, str)

@ -61,7 +61,7 @@ def test_anthropic_streaming_callback() -> None:
        verbose=True,
    )
    message = HumanMessage(content="Write me a sentence with 10 words.")
-    chat([message])
+    chat.invoke([message])
    assert callback_handler.llm_streams > 1


--- a/libs/community/tests/integration_tests/chat_models/test_azure_openai.py
+++ b/libs/community/tests/integration_tests/chat_models/test_azure_openai.py
@ -40,7 +40,7 @@ def llm() -> AzureChatOpenAI:
 def test_chat_openai(llm: AzureChatOpenAI) -> None:
    """Test AzureChatOpenAI wrapper."""
    message = HumanMessage(content="Hello")
-    response = llm([message])
+    response = llm.invoke([message])
    assert isinstance(response, BaseMessage)
    assert isinstance(response.content, str)

@ -87,7 +87,7 @@ def test_chat_openai_streaming() -> None:
        verbose=True,
    )
    message = HumanMessage(content="Hello")
-    response = chat([message])
+    response = chat.invoke([message])
    assert callback_handler.llm_streams > 0
    assert isinstance(response, BaseMessage)

--- a/libs/community/tests/integration_tests/chat_models/test_baichuan.py
+++ b/libs/community/tests/integration_tests/chat_models/test_baichuan.py
@ -9,7 +9,7 @@ from langchain_community.chat_models.baichuan import ChatBaichuan
 def test_chat_baichuan_default() -> None:
    chat = ChatBaichuan(streaming=True)
    message = HumanMessage(content="请完整背诵将进酒，背诵5遍")
-    response = chat([message])
+    response = chat.invoke([message])
    assert isinstance(response, AIMessage)
    assert isinstance(response.content, str)

@ -17,7 +17,7 @@ def test_chat_baichuan_default() -> None:
 def test_chat_baichuan_default_non_streaming() -> None:
    chat = ChatBaichuan()
    message = HumanMessage(content="请完整背诵将进酒，背诵5遍")
-    response = chat([message])
+    response = chat.invoke([message])
    assert isinstance(response, AIMessage)
    assert isinstance(response.content, str)

@ -25,7 +25,7 @@ def test_chat_baichuan_default_non_streaming() -> None:
 def test_chat_baichuan_turbo() -> None:
    chat = ChatBaichuan(model="Baichuan2-Turbo", streaming=True)
    message = HumanMessage(content="Hello")
-    response = chat([message])
+    response = chat.invoke([message])
    assert isinstance(response, AIMessage)
    assert isinstance(response.content, str)

@ -33,7 +33,7 @@ def test_chat_baichuan_turbo() -> None:
 def test_chat_baichuan_turbo_non_streaming() -> None:
    chat = ChatBaichuan(model="Baichuan2-Turbo")
    message = HumanMessage(content="Hello")
-    response = chat([message])
+    response = chat.invoke([message])
    assert isinstance(response, AIMessage)
    assert isinstance(response.content, str)

@ -41,7 +41,7 @@ def test_chat_baichuan_turbo_non_streaming() -> None:
 def test_chat_baichuan_with_temperature() -> None:
    chat = ChatBaichuan(temperature=1.0)
    message = HumanMessage(content="Hello")
-    response = chat([message])
+    response = chat.invoke([message])
    assert isinstance(response, AIMessage)
    assert isinstance(response.content, str)

@ -49,7 +49,9 @@ def test_chat_baichuan_with_temperature() -> None:
 def test_chat_baichuan_with_kwargs() -> None:
    chat = ChatBaichuan()
    message = HumanMessage(content="百川192K API是什么时候上线的？")
-    response = chat([message], temperature=0.88, top_p=0.7, with_search_enhance=True)
+    response = chat.invoke(
+        [message], temperature=0.88, top_p=0.7, with_search_enhance=True
+    )
    print(response)  # noqa: T201
    assert isinstance(response, AIMessage)
    assert isinstance(response.content, str)
--- a/libs/community/tests/integration_tests/chat_models/test_bedrock.py
+++ b/libs/community/tests/integration_tests/chat_models/test_bedrock.py
@ -25,7 +25,7 @@ def test_chat_bedrock(chat: BedrockChat) -> None:
    """Test BedrockChat wrapper."""
    system = SystemMessage(content="You are a helpful assistant.")
    human = HumanMessage(content="Hello")
-    response = chat([system, human])
+    response = chat.invoke([system, human])
    assert isinstance(response, BaseMessage)
    assert isinstance(response.content, str)

@ -70,7 +70,7 @@ def test_chat_bedrock_streaming() -> None:
        verbose=True,
    )
    message = HumanMessage(content="Hello")
-    response = chat([message])
+    response = chat.invoke([message])
    assert callback_handler.llm_streams > 0
    assert isinstance(response, BaseMessage)

--- a/libs/community/tests/integration_tests/chat_models/test_dappier.py
+++ b/libs/community/tests/integration_tests/chat_models/test_dappier.py
@ -17,7 +17,7 @@ def test_dappier_chat() -> None:
        dappier_model="dm_01hpsxyfm2fwdt2zet9cg6fdxt",
    )
    message = HumanMessage(content="Who are you ?")
-    response = chat([message])
+    response = chat.invoke([message])
    assert isinstance(response, AIMessage)
    assert isinstance(response.content, str)

--- a/libs/community/tests/integration_tests/chat_models/test_edenai.py
+++ b/libs/community/tests/integration_tests/chat_models/test_edenai.py
@ -17,7 +17,7 @@ def test_chat_edenai() -> None:
        provider="openai", model="gpt-3.5-turbo", temperature=0, max_tokens=1000
    )
    message = HumanMessage(content="Who are you ?")
-    response = chat([message])
+    response = chat.invoke([message])
    assert isinstance(response, AIMessage)
    assert isinstance(response.content, str)

--- a/libs/community/tests/integration_tests/chat_models/test_ernie.py
+++ b/libs/community/tests/integration_tests/chat_models/test_ernie.py
@ -7,7 +7,7 @@ from langchain_community.chat_models.ernie import ErnieBotChat
 def test_chat_ernie_bot() -> None:
    chat = ErnieBotChat()
    message = HumanMessage(content="Hello")
-    response = chat([message])
+    response = chat.invoke([message])
    assert isinstance(response, AIMessage)
    assert isinstance(response.content, str)

@ -15,7 +15,7 @@ def test_chat_ernie_bot() -> None:
 def test_chat_ernie_bot_with_model_name() -> None:
    chat = ErnieBotChat(model_name="ERNIE-Bot")
    message = HumanMessage(content="Hello")
-    response = chat([message])
+    response = chat.invoke([message])
    assert isinstance(response, AIMessage)
    assert isinstance(response.content, str)

@ -23,7 +23,7 @@ def test_chat_ernie_bot_with_model_name() -> None:
 def test_chat_ernie_bot_with_temperature() -> None:
    chat = ErnieBotChat(model_name="ERNIE-Bot", temperature=1.0)
    message = HumanMessage(content="Hello")
-    response = chat([message])
+    response = chat.invoke([message])
    assert isinstance(response, AIMessage)
    assert isinstance(response.content, str)

@ -31,7 +31,7 @@ def test_chat_ernie_bot_with_temperature() -> None:
 def test_chat_ernie_bot_with_kwargs() -> None:
    chat = ErnieBotChat()
    message = HumanMessage(content="Hello")
-    response = chat([message], temperature=0.88, top_p=0.7)
+    response = chat.invoke([message], temperature=0.88, top_p=0.7)
    assert isinstance(response, AIMessage)
    assert isinstance(response.content, str)

@ -46,7 +46,7 @@ def test_wrong_temperature_1() -> None:
    chat = ErnieBotChat()
    message = HumanMessage(content="Hello")
    with pytest.raises(ValueError) as e:
-        chat([message], temperature=1.2)
+        chat.invoke([message], temperature=1.2)
    assert "parameter check failed, temperature range is (0, 1.0]" in str(e)


@ -54,5 +54,5 @@ def test_wrong_temperature_2() -> None:
    chat = ErnieBotChat()
    message = HumanMessage(content="Hello")
    with pytest.raises(ValueError) as e:
-        chat([message], temperature=0)
+        chat.invoke([message], temperature=0)
    assert "parameter check failed, temperature range is (0, 1.0]" in str(e)
--- a/libs/community/tests/integration_tests/chat_models/test_fireworks.py
+++ b/libs/community/tests/integration_tests/chat_models/test_fireworks.py
@ -21,7 +21,7 @@ def chat() -> ChatFireworks:
 def test_chat_fireworks(chat: ChatFireworks) -> None:
    """Test ChatFireworks wrapper."""
    message = HumanMessage(content="What is the weather in Redwood City, CA today")
-    response = chat([message])
+    response = chat.invoke([message])
    assert isinstance(response, BaseMessage)
    assert isinstance(response.content, str)

@ -38,7 +38,7 @@ def test_chat_fireworks_system_message(chat: ChatFireworks) -> None:
    """Test ChatFireworks wrapper with system message."""
    system_message = SystemMessage(content="You are to chat with the user.")
    human_message = HumanMessage(content="Hello")
-    response = chat([system_message, human_message])
+    response = chat.invoke([system_message, human_message])
    assert isinstance(response, BaseMessage)
    assert isinstance(response.content, str)

--- a/libs/community/tests/integration_tests/chat_models/test_friendli.py
+++ b/libs/community/tests/integration_tests/chat_models/test_friendli.py
@ -15,14 +15,6 @@ def friendli_chat() -> ChatFriendli:
    return ChatFriendli(temperature=0, max_tokens=10)


-def test_friendli_call(friendli_chat: ChatFriendli) -> None:
-    """Test call."""
-    message = HumanMessage(content="What is generative AI?")
-    output = friendli_chat([message])
-    assert isinstance(output, AIMessage)
-    assert isinstance(output.content, str)
-
-
 def test_friendli_invoke(friendli_chat: ChatFriendli) -> None:
    """Test invoke."""
    output = friendli_chat.invoke("What is generative AI?")
--- a/libs/community/tests/integration_tests/chat_models/test_google_palm.py
+++ b/libs/community/tests/integration_tests/chat_models/test_google_palm.py
@ -14,7 +14,7 @@ def test_chat_google_palm() -> None:
    """Test Google PaLM Chat API wrapper."""
    chat = ChatGooglePalm()
    message = HumanMessage(content="Hello")
-    response = chat([message])
+    response = chat.invoke([message])
    assert isinstance(response, BaseMessage)
    assert isinstance(response.content, str)

@ -24,7 +24,7 @@ def test_chat_google_palm_system_message() -> None:
    chat = ChatGooglePalm()
    system_message = SystemMessage(content="You are to chat with the user.")
    human_message = HumanMessage(content="Hello")
-    response = chat([system_message, human_message])
+    response = chat.invoke([system_message, human_message])
    assert isinstance(response, BaseMessage)
    assert isinstance(response.content, str)

--- a/libs/community/tests/integration_tests/chat_models/test_gpt_router.py
+++ b/libs/community/tests/integration_tests/chat_models/test_gpt_router.py
@ -43,7 +43,7 @@ def test_gpt_router_call() -> None:
    )
    chat = GPTRouter(models_priority_list=[anthropic_claude])
    message = HumanMessage(content="Hello World")
-    response = chat([message])
+    response = chat.invoke([message])
    assert isinstance(response, AIMessage)
    assert isinstance(response.content, str)

@ -56,7 +56,7 @@ def test_gpt_router_call_incorrect_model() -> None:
    chat = GPTRouter(models_priority_list=[anthropic_claude])
    message = HumanMessage(content="Hello World")
    with pytest.raises(Exception):
-        chat([message])
+        chat.invoke([message])


 def test_gpt_router_generate() -> None:
@ -85,7 +85,7 @@ def test_gpt_router_streaming() -> None:
    )
    chat = GPTRouter(models_priority_list=[anthropic_claude], streaming=True)
    message = HumanMessage(content="Hello")
-    response = chat([message])
+    response = chat.invoke([message])
    assert isinstance(response, AIMessage)
    assert isinstance(response.content, str)

@ -104,5 +104,5 @@ def test_gpt_router_streaming_callback() -> None:
        verbose=True,
    )
    message = HumanMessage(content="Write me a 5 line poem.")
-    chat([message])
+    chat.invoke([message])
    assert callback_handler.llm_streams > 1
--- a/libs/community/tests/integration_tests/chat_models/test_hunyuan.py
+++ b/libs/community/tests/integration_tests/chat_models/test_hunyuan.py
@ -6,7 +6,7 @@ from langchain_community.chat_models.hunyuan import ChatHunyuan
 def test_chat_hunyuan() -> None:
    chat = ChatHunyuan()
    message = HumanMessage(content="Hello")
-    response = chat([message])
+    response = chat.invoke([message])
    assert isinstance(response, AIMessage)
    assert isinstance(response.content, str)

@ -14,7 +14,7 @@ def test_chat_hunyuan() -> None:
 def test_chat_hunyuan_with_temperature() -> None:
    chat = ChatHunyuan(temperature=0.6)
    message = HumanMessage(content="Hello")
-    response = chat([message])
+    response = chat.invoke([message])
    assert isinstance(response, AIMessage)
    assert isinstance(response.content, str)

--- a/libs/community/tests/integration_tests/chat_models/test_jinachat.py
+++ b/libs/community/tests/integration_tests/chat_models/test_jinachat.py
@ -51,7 +51,7 @@ def test_jinachat() -> None:
    """Test JinaChat wrapper."""
    chat = JinaChat(max_tokens=10)
    message = HumanMessage(content="Hello")
-    response = chat([message])
+    response = chat.invoke([message])
    assert isinstance(response, BaseMessage)
    assert isinstance(response.content, str)

@ -61,7 +61,7 @@ def test_jinachat_system_message() -> None:
    chat = JinaChat(max_tokens=10)
    system_message = SystemMessage(content="You are to chat with the user.")
    human_message = HumanMessage(content="Hello")
-    response = chat([system_message, human_message])
+    response = chat.invoke([system_message, human_message])
    assert isinstance(response, BaseMessage)
    assert isinstance(response.content, str)

@ -93,7 +93,7 @@ def test_jinachat_streaming() -> None:
        verbose=True,
    )
    message = HumanMessage(content="Hello")
-    response = chat([message])
+    response = chat.invoke([message])
    assert callback_handler.llm_streams > 0
    assert isinstance(response, BaseMessage)

--- a/libs/community/tests/integration_tests/chat_models/test_konko.py
+++ b/libs/community/tests/integration_tests/chat_models/test_konko.py
@ -57,7 +57,7 @@ def test_konko_chat_test() -> None:
    """Evaluate basic ChatKonko functionality."""
    chat_instance = ChatKonko(max_tokens=10)
    msg = HumanMessage(content="Hi")
-    chat_response = chat_instance([msg])
+    chat_response = chat_instance.invoke([msg])
    assert isinstance(chat_response, BaseMessage)
    assert isinstance(chat_response.content, str)

@ -66,7 +66,7 @@ def test_konko_chat_test_openai() -> None:
    """Evaluate basic ChatKonko functionality."""
    chat_instance = ChatKonko(max_tokens=10, model="meta-llama/llama-2-70b-chat")
    msg = HumanMessage(content="Hi")
-    chat_response = chat_instance([msg])
+    chat_response = chat_instance.invoke([msg])
    assert isinstance(chat_response, BaseMessage)
    assert isinstance(chat_response.content, str)

@ -91,7 +91,7 @@ def test_konko_system_msg_test() -> None:
    chat_instance = ChatKonko(max_tokens=10)
    sys_msg = SystemMessage(content="Initiate user chat.")
    user_msg = HumanMessage(content="Hi there")
-    chat_response = chat_instance([sys_msg, user_msg])
+    chat_response = chat_instance.invoke([sys_msg, user_msg])
    assert isinstance(chat_response, BaseMessage)
    assert isinstance(chat_response.content, str)

@ -135,7 +135,7 @@ def test_konko_streaming_callback_test() -> None:
        verbose=True,
    )
    msg = HumanMessage(content="Hi")
-    chat_response = chat_instance([msg])
+    chat_response = chat_instance.invoke([msg])
    assert callback_instance.llm_streams > 0
    assert isinstance(chat_response, BaseMessage)

--- a/libs/community/tests/integration_tests/chat_models/test_litellm.py
+++ b/libs/community/tests/integration_tests/chat_models/test_litellm.py
@ -17,7 +17,7 @@ def test_litellm_call() -> None:
        model="test",
    )
    message = HumanMessage(content="Hello")
-    response = chat([message])
+    response = chat.invoke([message])
    assert isinstance(response, AIMessage)
    assert isinstance(response.content, str)

@ -42,7 +42,7 @@ def test_litellm_streaming() -> None:
    """Test streaming tokens from anthropic."""
    chat = ChatLiteLLM(model="test", streaming=True)
    message = HumanMessage(content="Hello")
-    response = chat([message])
+    response = chat.invoke([message])
    assert isinstance(response, AIMessage)
    assert isinstance(response.content, str)

@ -58,5 +58,5 @@ def test_litellm_streaming_callback() -> None:
        verbose=True,
    )
    message = HumanMessage(content="Write me a sentence with 10 words.")
-    chat([message])
+    chat.invoke([message])
    assert callback_handler.llm_streams > 1
--- a/libs/community/tests/integration_tests/chat_models/test_litellm_router.py
+++ b/libs/community/tests/integration_tests/chat_models/test_litellm_router.py
@ -184,7 +184,7 @@ def test_litellm_router_call(
    chat = ChatLiteLLMRouter(router=litellm_router)
    message = HumanMessage(content="Hello")

-    response = chat([message])
+    response = chat.invoke([message])

    assert isinstance(response, AIMessage)
    assert isinstance(response.content, str)
@ -232,7 +232,7 @@ def test_litellm_router_streaming(
    chat = ChatLiteLLMRouter(router=litellm_router, streaming=True)
    message = HumanMessage(content="Hello")

-    response = chat([message])
+    response = chat.invoke([message])

    assert isinstance(response, AIMessage)
    assert isinstance(response.content, str)
@ -255,7 +255,7 @@ def test_litellm_router_streaming_callback(
    )
    message = HumanMessage(content="Write me a sentence with 10 words.")

-    response = chat([message])
+    response = chat.invoke([message])

    assert callback_handler.llm_streams > 1
    assert isinstance(response, AIMessage)
--- a/libs/community/tests/integration_tests/chat_models/test_llama_edge.py
+++ b/libs/community/tests/integration_tests/chat_models/test_llama_edge.py
@ -20,7 +20,7 @@ def test_chat_wasm_service() -> None:
    messages = [system_message, user_message]

    # chat with wasm-chat service
-    response = chat(messages)
+    response = chat.invoke(messages)

    # check response
    assert isinstance(response, AIMessage)
--- a/libs/community/tests/integration_tests/chat_models/test_octoai.py
+++ b/libs/community/tests/integration_tests/chat_models/test_octoai.py
@ -6,6 +6,6 @@ from langchain_community.chat_models.octoai import ChatOctoAI
 def test_chat_octoai() -> None:
    chat = ChatOctoAI()
    message = HumanMessage(content="Hello")
-    response = chat([message])
+    response = chat.invoke([message])
    assert isinstance(response, AIMessage)
    assert isinstance(response.content, str)
--- a/libs/community/tests/integration_tests/chat_models/test_openai.py
+++ b/libs/community/tests/integration_tests/chat_models/test_openai.py
@ -33,7 +33,7 @@ def test_chat_openai() -> None:
        default_query=None,
    )
    message = HumanMessage(content="Hello")
-    response = chat([message])
+    response = chat.invoke([message])
    assert isinstance(response, BaseMessage)
    assert isinstance(response.content, str)

@ -51,7 +51,7 @@ def test_chat_openai_system_message() -> None:
    chat = ChatOpenAI(max_tokens=10)
    system_message = SystemMessage(content="You are to chat with the user.")
    human_message = HumanMessage(content="Hello")
-    response = chat([system_message, human_message])
+    response = chat.invoke([system_message, human_message])
    assert isinstance(response, BaseMessage)
    assert isinstance(response.content, str)

@ -99,7 +99,7 @@ def test_chat_openai_streaming() -> None:
        verbose=True,
    )
    message = HumanMessage(content="Hello")
-    response = chat([message])
+    response = chat.invoke([message])
    assert callback_handler.llm_streams > 0
    assert isinstance(response, BaseMessage)

--- a/libs/community/tests/integration_tests/chat_models/test_pai_eas_chat_endpoint.py
+++ b/libs/community/tests/integration_tests/chat_models/test_pai_eas_chat_endpoint.py
@ -14,7 +14,7 @@ def test_pai_eas_call() -> None:
        eas_service_url=os.getenv("EAS_SERVICE_URL"),
        eas_service_token=os.getenv("EAS_SERVICE_TOKEN"),
    )
-    response = chat(messages=[HumanMessage(content="Say foo:")])
+    response = chat.invoke([HumanMessage(content="Say foo:")])
    assert isinstance(response, BaseMessage)
    assert isinstance(response.content, str)

@ -26,8 +26,8 @@ def test_multiple_history() -> None:
        eas_service_token=os.getenv("EAS_SERVICE_TOKEN"),
    )

-    response = chat(
-        messages=[
+    response = chat.invoke(
+        [
            HumanMessage(content="Hello."),
            AIMessage(content="Hello!"),
            HumanMessage(content="How are you doing?"),
@ -46,14 +46,14 @@ def test_stream() -> None:
    )
    callback_handler = FakeCallbackHandler()
    callback_manager = CallbackManager([callback_handler])
-    response = chat(
-        messages=[
+    response = chat.invoke(
+        [
            HumanMessage(content="Hello."),
            AIMessage(content="Hello!"),
            HumanMessage(content="Who are you?"),
        ],
        stream=True,
-        callbacks=callback_manager,
+        config={"callbacks": callback_manager},
    )
    assert callback_handler.llm_streams > 0
    assert isinstance(response.content, str)
--- a/libs/community/tests/integration_tests/chat_models/test_premai.py
+++ b/libs/community/tests/integration_tests/chat_models/test_premai.py
@ -21,7 +21,7 @@ def test_chat_premai() -> None:
    """Test ChatPremAI wrapper."""
    chat = ChatPremAI(project_id=8)
    message = HumanMessage(content="Hello")
-    response = chat([message])
+    response = chat.invoke([message])
    assert isinstance(response, BaseMessage)
    assert isinstance(response.content, str)

@ -31,7 +31,7 @@ def test_chat_prem_system_message() -> None:
    chat = ChatPremAI(project_id=8)
    system_message = SystemMessage(content="You are to chat with the user.")
    human_message = HumanMessage(content="Hello")
-    response = chat([system_message, human_message])
+    response = chat.invoke([system_message, human_message])
    assert isinstance(response, BaseMessage)
    assert isinstance(response.content, str)

--- a/libs/community/tests/integration_tests/chat_models/test_promptlayer_openai.py
+++ b/libs/community/tests/integration_tests/chat_models/test_promptlayer_openai.py
@ -13,7 +13,7 @@ def test_promptlayer_chat_openai() -> None:
    """Test PromptLayerChatOpenAI wrapper."""
    chat = PromptLayerChatOpenAI(max_tokens=10)
    message = HumanMessage(content="Hello")
-    response = chat([message])
+    response = chat.invoke([message])
    assert isinstance(response, BaseMessage)
    assert isinstance(response.content, str)

@ -23,7 +23,7 @@ def test_promptlayer_chat_openai_system_message() -> None:
    chat = PromptLayerChatOpenAI(max_tokens=10)
    system_message = SystemMessage(content="You are to chat with the user.")
    human_message = HumanMessage(content="Hello")
-    response = chat([system_message, human_message])
+    response = chat.invoke([system_message, human_message])
    assert isinstance(response, BaseMessage)
    assert isinstance(response.content, str)

@ -67,7 +67,7 @@ def test_promptlayer_chat_openai_streaming() -> None:
        verbose=True,
    )
    message = HumanMessage(content="Hello")
-    response = chat([message])
+    response = chat.invoke([message])
    assert callback_handler.llm_streams > 0
    assert isinstance(response, BaseMessage)

--- a/libs/community/tests/integration_tests/chat_models/test_qianfan_endpoint.py
+++ b/libs/community/tests/integration_tests/chat_models/test_qianfan_endpoint.py
@ -98,9 +98,9 @@ def test_initialization() -> None:


 def test_default_call() -> None:
-    """Test default model(`ERNIE-Bot`) call."""
+    """Test default model.invoke(`ERNIE-Bot`) call."""
    chat = QianfanChatEndpoint()
-    response = chat(messages=[HumanMessage(content="Hello")])
+    response = chat.invoke([HumanMessage(content="Hello")])
    assert isinstance(response, BaseMessage)
    assert isinstance(response.content, str)

@ -108,7 +108,7 @@ def test_default_call() -> None:
 def test_model() -> None:
    """Test model kwarg works."""
    chat = QianfanChatEndpoint(model="BLOOMZ-7B")
-    response = chat(messages=[HumanMessage(content="Hello")])
+    response = chat.invoke([HumanMessage(content="Hello")])
    assert isinstance(response, BaseMessage)
    assert isinstance(response.content, str)

@ -116,7 +116,7 @@ def test_model() -> None:
 def test_model_param() -> None:
    """Test model params works."""
    chat = QianfanChatEndpoint()
-    response = chat(model="BLOOMZ-7B", messages=[HumanMessage(content="Hello")])
+    response = chat.invoke([HumanMessage(content="Hello")], model="BLOOMZ-7B")
    assert isinstance(response, BaseMessage)
    assert isinstance(response.content, str)

@ -124,7 +124,7 @@ def test_model_param() -> None:
 def test_endpoint() -> None:
    """Test user custom model deployments like some open source models."""
    chat = QianfanChatEndpoint(endpoint="qianfan_bloomz_7b_compressed")
-    response = chat(messages=[HumanMessage(content="Hello")])
+    response = chat.invoke([HumanMessage(content="Hello")])
    assert isinstance(response, BaseMessage)
    assert isinstance(response.content, str)

@ -132,10 +132,8 @@ def test_endpoint() -> None:
 def test_endpoint_param() -> None:
    """Test user custom model deployments like some open source models."""
    chat = QianfanChatEndpoint()
-    response = chat(
-        messages=[
-            HumanMessage(endpoint="qianfan_bloomz_7b_compressed", content="Hello")
-        ]
+    response = chat.invoke(
+        [HumanMessage(endpoint="qianfan_bloomz_7b_compressed", content="Hello")]
    )
    assert isinstance(response, BaseMessage)
    assert isinstance(response.content, str)
@ -145,8 +143,8 @@ def test_multiple_history() -> None:
    """Tests multiple history works."""
    chat = QianfanChatEndpoint()

-    response = chat(
-        messages=[
+    response = chat.invoke(
+        [
            HumanMessage(content="Hello."),
            AIMessage(content="Hello!"),
            HumanMessage(content="How are you doing?"),
@ -180,14 +178,14 @@ def test_stream() -> None:
    chat = QianfanChatEndpoint(streaming=True)
    callback_handler = FakeCallbackHandler()
    callback_manager = CallbackManager([callback_handler])
-    response = chat(
-        messages=[
+    response = chat.invoke(
+        [
            HumanMessage(content="Hello."),
            AIMessage(content="Hello!"),
            HumanMessage(content="Who are you?"),
        ],
        stream=True,
-        callbacks=callback_manager,
+        config={"callbacks": callback_manager},
    )
    assert callback_handler.llm_streams > 0
    assert isinstance(response.content, str)
--- a/libs/community/tests/integration_tests/chat_models/test_sparkllm.py
+++ b/libs/community/tests/integration_tests/chat_models/test_sparkllm.py
@ -15,7 +15,7 @@ def test_initialization() -> None:
 def test_chat_spark_llm() -> None:
    chat = ChatSparkLLM()
    message = HumanMessage(content="Hello")
-    response = chat([message])
+    response = chat.invoke([message])
    assert isinstance(response, AIMessage)
    assert isinstance(response.content, str)

@ -30,7 +30,7 @@ def test_chat_spark_llm_streaming() -> None:
 def test_chat_spark_llm_with_domain() -> None:
    chat = ChatSparkLLM(spark_llm_domain="generalv3")
    message = HumanMessage(content="Hello")
-    response = chat([message])
+    response = chat.invoke([message])
    print(response)  # noqa: T201
    assert isinstance(response, AIMessage)
    assert isinstance(response.content, str)
@ -39,7 +39,7 @@ def test_chat_spark_llm_with_domain() -> None:
 def test_chat_spark_llm_with_temperature() -> None:
    chat = ChatSparkLLM(temperature=0.9, top_k=2)
    message = HumanMessage(content="Hello")
-    response = chat([message])
+    response = chat.invoke([message])
    print(response)  # noqa: T201
    assert isinstance(response, AIMessage)
    assert isinstance(response.content, str)
--- a/libs/community/tests/integration_tests/chat_models/test_tongyi.py
+++ b/libs/community/tests/integration_tests/chat_models/test_tongyi.py
@ -61,7 +61,7 @@ def test_api_key_masked_when_passed_via_constructor(
 def test_default_call() -> None:
    """Test default model call."""
    chat = ChatTongyi()
-    response = chat(messages=[HumanMessage(content="Hello")])
+    response = chat.invoke([HumanMessage(content="Hello")])
    assert isinstance(response, BaseMessage)
    assert isinstance(response.content, str)

@ -69,7 +69,7 @@ def test_default_call() -> None:
 def test_model() -> None:
    """Test model kwarg works."""
    chat = ChatTongyi(model="qwen-plus")
-    response = chat(messages=[HumanMessage(content="Hello")])
+    response = chat.invoke([HumanMessage(content="Hello")])
    assert isinstance(response, BaseMessage)
    assert isinstance(response.content, str)

@ -95,8 +95,8 @@ def test_multiple_history() -> None:
    """Tests multiple history works."""
    chat = ChatTongyi()

-    response = chat(
-        messages=[
+    response = chat.invoke(
+        [
            HumanMessage(content="Hello."),
            AIMessage(content="Hello!"),
            HumanMessage(content="How are you doing?"),
@ -111,14 +111,14 @@ def test_stream() -> None:
    chat = ChatTongyi(streaming=True)
    callback_handler = FakeCallbackHandler()
    callback_manager = CallbackManager([callback_handler])
-    response = chat(
-        messages=[
+    response = chat.invoke(
+        [
            HumanMessage(content="Hello."),
            AIMessage(content="Hello!"),
            HumanMessage(content="Who are you?"),
        ],
        stream=True,
-        callbacks=callback_manager,
+        config={"callbacks": callback_manager},
    )
    assert callback_handler.llm_streams > 0
    assert isinstance(response.content, str)
--- a/libs/community/tests/integration_tests/chat_models/test_vertexai.py
+++ b/libs/community/tests/integration_tests/chat_models/test_vertexai.py
@ -50,7 +50,7 @@ def test_vertexai_single_call(model_name: str) -> None:
    else:
        model = ChatVertexAI()
    message = HumanMessage(content="Hello")
-    response = model([message])
+    response = model.invoke([message])
    assert isinstance(response, AIMessage)
    assert isinstance(response.content, str)

@ -104,7 +104,7 @@ def test_vertexai_single_call_with_context() -> None:
    )
    context = SystemMessage(content=raw_context)
    message = HumanMessage(content=question)
-    response = model([context, message])
+    response = model.invoke([context, message])
    assert isinstance(response, AIMessage)
    assert isinstance(response.content, str)

@ -124,7 +124,7 @@ def test_multimodal() -> None:
        "text": "What is shown in this image?",
    }
    message = HumanMessage(content=[text_message, image_message])
-    output = llm([message])
+    output = llm.invoke([message])
    assert isinstance(output.content, str)


@ -151,7 +151,7 @@ def test_multimodal_history() -> None:
        )
    )
    message3 = HumanMessage(content="What time of day is it?")
-    response = llm([message1, message2, message3])
+    response = llm.invoke([message1, message2, message3])
    assert isinstance(response, AIMessage)
    assert isinstance(response.content, str)

@ -166,7 +166,7 @@ def test_vertexai_single_call_with_examples() -> None:
    output = AIMessage(content=text_answer)
    context = SystemMessage(content=raw_context)
    message = HumanMessage(content=question)
-    response = model([context, message], examples=[inp, output])
+    response = model.invoke([context, message], examples=[inp, output])
    assert isinstance(response, AIMessage)
    assert isinstance(response.content, str)

@ -183,7 +183,7 @@ def test_vertexai_single_call_with_history(model_name: str) -> None:
    message1 = HumanMessage(content=text_question1)
    message2 = AIMessage(content=text_answer1)
    message3 = HumanMessage(content=text_question2)
-    response = model([message1, message2, message3])
+    response = model.invoke([message1, message2, message3])
    assert isinstance(response, AIMessage)
    assert isinstance(response.content, str)

@ -219,7 +219,7 @@ def test_parse_chat_history_correct() -> None:
 def test_vertexai_single_call_fails_no_message() -> None:
    chat = ChatVertexAI()
    with pytest.raises(ValueError) as exc_info:
-        _ = chat([])
+        _ = chat.invoke([])
    assert (
        str(exc_info.value)
        == "You should provide at least one message to start the chat!"
@ -251,9 +251,9 @@ def test_vertexai_args_passed(stop: Optional[str]) -> None:
        model = ChatVertexAI(**prompt_params)
        message = HumanMessage(content=user_prompt)
        if stop:
-            response = model([message], stop=[stop])
+            response = model.invoke([message], stop=[stop])
        else:
-            response = model([message])
+            response = model.invoke([message])

        assert response.content == response_text
        mock_send_message.assert_called_once_with(user_prompt, candidate_count=1)
--- a/libs/community/tests/integration_tests/chat_models/test_volcengine_maas.py
+++ b/libs/community/tests/integration_tests/chat_models/test_volcengine_maas.py
@ -11,7 +11,7 @@ from tests.unit_tests.callbacks.fake_callback_handler import FakeCallbackHandler
 def test_default_call() -> None:
    """Test valid chat call to volc engine."""
    chat = VolcEngineMaasChat()
-    response = chat(messages=[HumanMessage(content="Hello")])
+    response = chat.invoke([HumanMessage(content="Hello")])
    assert isinstance(response, BaseMessage)
    assert isinstance(response.content, str)

@ -20,8 +20,8 @@ def test_multiple_history() -> None:
    """Tests multiple history works."""
    chat = VolcEngineMaasChat()

-    response = chat(
-        messages=[
+    response = chat.invoke(
+        [
            HumanMessage(content="Hello"),
            AIMessage(content="Hello!"),
            HumanMessage(content="How are you?"),
@ -36,14 +36,14 @@ def test_stream() -> None:
    chat = VolcEngineMaasChat(streaming=True)
    callback_handler = FakeCallbackHandler()
    callback_manager = CallbackManager([callback_handler])
-    response = chat(
-        messages=[
+    response = chat.invoke(
+        [
            HumanMessage(content="Hello"),
            AIMessage(content="Hello!"),
            HumanMessage(content="How are you?"),
        ],
        stream=True,
-        callbacks=callback_manager,
+        config={"callbacks": callback_manager},
    )
    assert callback_handler.llm_streams > 0
    assert isinstance(response.content, str)
@ -56,14 +56,14 @@ def test_stop() -> None:
    )
    callback_handler = FakeCallbackHandler()
    callback_manager = CallbackManager([callback_handler])
-    response = chat(
-        messages=[
+    response = chat.invoke(
+        [
            HumanMessage(content="repeat: hello world"),
            AIMessage(content="hello world"),
            HumanMessage(content="repeat: hello world"),
        ],
        stream=True,
-        callbacks=callback_manager,
+        config={"callbacks": callback_manager},
        stop=["world"],
    )
    assert callback_handler.llm_streams > 0
--- a/Show More
+++ b/Show More