ci: drop python 3.8 (#825 )

chore: bump patch version (#823 )
bump patched version so i can release
2026-07-25 13:15:44 -04:00 · 2025-09-17 15:38:01 -04:00 · 2025-09-17 15:31:09 -04:00 · 2025-09-17 15:03:09 -04:00 · 2025-09-17 15:01:18 -04:00 · 2025-07-09 17:19:18 -04:00
29 changed files with 862 additions and 551 deletions
@@ -1,4 +1,4 @@
 {
-  "contributors": ["eyurtsev", "hwchase17", "nfcampos", "efriis", "jacoblee93", "dqbd", "kreneskyp", "adarsh-jha-dev", "harris", "baskaryan", "hinthornw", "bracesproul", "jakerachleff", "craigsdennis", "anhi", "169", "LarchLiu", "PaulLockett", "RCMatthias", "jwynia", "majiayu000", "mpskex", "shivachittamuru", "sinashaloudegi", "sowsan", "akira", "lucianotonet", "JGalego", "nat-n", "dirien", "donbr", "rahilvora", "WarrenTheRabbit", "StreetLamb", "ccurme", "dennisrall"],
+  "contributors": ["eyurtsev", "hwchase17", "nfcampos", "efriis", "jacoblee93", "dqbd", "kreneskyp", "adarsh-jha-dev", "harris", "baskaryan", "hinthornw", "bracesproul", "jakerachleff", "craigsdennis", "anhi", "169", "LarchLiu", "PaulLockett", "RCMatthias", "jwynia", "majiayu000", "mpskex", "shivachittamuru", "sinashaloudegi", "sowsan", "akira", "lucianotonet", "JGalego", "nat-n", "dirien", "donbr", "rahilvora", "WarrenTheRabbit", "StreetLamb", "ccurme", "dennisrall", "Mingqi2", "xxsl", "joaquin-borggio-lc"],
  "message": "Thank you for your pull request and welcome to our community. We require contributors to sign our Contributor License Agreement, and we don't seem to have the username {{usersWithoutCLA}} on file. In order for us to review and merge your code, please complete the Individual Contributor License Agreement here https://forms.gle/AQFbtkWRoHXUgipM6 .\n\nThis process is done manually on our side, so after signing the form one of the maintainers will add you to the contributors list.\n\nFor more details about why we have a CLA and other contribution guidelines please see: https://github.com/langchain-ai/langserve/blob/main/CONTRIBUTING.md."
 }
@@ -31,7 +31,7 @@ jobs:
        # Starting new jobs is also relatively slow,
        # so linting on fewer versions makes CI faster.
        python-version:
-          - "3.8"
+          - "3.9"
          - "3.11"
    steps:
      - uses: actions/checkout@v3
@@ -7,6 +7,12 @@ on:
        required: true
        type: string
        description: "From which folder this pipeline executes"
+  workflow_dispatch:  # Allows to trigger the workflow manually in GitHub UI
+    inputs:
+      working-directory:
+        required: true
+        type: string
+        description: "From which folder this pipeline executes"

 env:
  POETRY_VERSION: "1.5.1"
@@ -20,7 +20,6 @@ jobs:
    strategy:
      matrix:
        python-version:
-          - "3.8"
          - "3.9"
          - "3.10"
          - "3.11"
@@ -48,7 +48,6 @@ jobs:
    strategy:
      matrix:
        python-version:
-          - "3.8"
          - "3.9"
          - "3.10"
          - "3.11"
@@ -0,0 +1,222 @@
+# LangGraph Platform Migration Guide
+
+We have [recently announced](https://blog.langchain.dev/langgraph-platform-announce/) LangGraph Platform, a ***significantly*** enhanced solution for deploying agentic applications at scale.
+
+LangGraph Platform incorporates [key design patterns and capabilities](https://langchain-ai.github.io/langgraph/concepts/langgraph_platform/#option-2-leveraging-langgraph-platform-for-complex-deployments) essential for production-level deployment of large language model (LLM) applications.
+
+In contrast to LangServe, LangGraph Platform provides comprehensive, out-of-the-box support for [persistence](https://langchain-ai.github.io/langgraph/concepts/application_structure/), [memory](https://langchain-ai.github.io/langgraph/concepts/assistants/), [double-texting handling](https://langchain-ai.github.io/langgraph/concepts/double_texting/), [human-in-the-loop workflows](https://langchain-ai.github.io/langgraph/concepts/assistants/), [cron job scheduling](https://langchain-ai.github.io/langgraph/concepts/langgraph_server/#cron-jobs), [webhooks](https://langchain-ai.github.io/langgraph/concepts/langgraph_server/#webhooks), high-load management, advanced streaming, support for long-running tasks, background task processing, and much more.
+
+The LangGraph Platform ecosystem includes the following components:
+
+- [LangGraph Server](https://langchain-ai.github.io/langgraph/concepts/langgraph_server/): Provides an [Assistants API](https://langchain-ai.github.io/langgraph/cloud/reference/api/api_ref.html) for LLM applications (graphs) built with [LangGraph](https://langchain-ai.github.io/langgraph/). Available in both Python and JavaScript/TypeScript.
+- [LangGraph Studio](https://langchain-ai.github.io/langgraph/concepts/langgraph_studio/): A specialized IDE for real-time visualization, debugging, and interaction via a graphical interface. Available as a web application or macOS desktop app, it's a substantial improvement over LangServe's playground.
+- [SDK](https://langchain-ai.github.io/langgraph/concepts/sdk/): Enables programmatic interaction with the server, available in Python and JavaScript/TypeScript.
+- [RemoteGraph](https://langchain-ai.github.io/langgraph/how-tos/use-remote-graph/): Allows interaction with a remote graph as if it were running locally, serving as LangGraph's equivalent to LangServe's RemoteRunnable. Available in both Python and JavaScript/TypeScript.
+ 
+## Context 
+
+LangServe was built as a deployment solution for LangChain Runnables created using the [LangChain Expression Language (LCEL)](https://python.langchain.com/docs/concepts/lcel). In LangServe, the LCEL was the orchestration layer that managed the execution of the Runnable.
+
+[LangGraph](https://langchain-ai.github.io/langgraph/) is an open source library created by the LangChain team that provides a more flexible orchestration layer that's better suited for creating more complex LLM applications. LangGraph Platform
+is the deployment solution for LangGraph applications.
+
+## LangServe Support
+
+We recommend using LangGraph Platform rather than LangServe for new projects.
+
+We will continue to accept bug fixes for LangServe from the community; however, we will not be accepting new feature contributions.
+
+## Migration
+
+If you would like to migrate an existing LangServe application to LangGraph Platform, you have two options:
+
+1. You can wrap the existing `Runnable` that you expose in the LangServe application via `add_routes` in a `LangGraph` node. This is the quickest way to migrate your application to LangGraph Platform.
+2. You can do a larger refactor to break up the existing LCEL into appropriate `LangGraph` nodes. This is recommended if you want to take advantage of more advanced features in LangGraph Platform.
+
+### Option 1: Wrap Runnable in LangGraph Node
+
+This option is the quickest way to migrate your application to LangGraph Platform. You can wrap the existing `Runnable` that you expose in the LangServe application via `add_routes` in a `LangGraph` node.
+
+
+Original LangServe code:
+
+```python
+from langserve import add_routes
+
+app = FastAPI()
+
+# Some input schema
+class Input(BaseModel):
+    input: str
+    foo: Optional[str]
+
+# Some output schema
+class Output(BaseModel):
+    output: Any
+    
+    
+runnable = .... # Your existing Runnable
+runnable_with_types = runnable.with_types(input_type=Input, output_type=Output)
+
+# Adds routes to the app for using the chain under:
+add_routes(
+    app,
+    runnable_with_types,
+)
+```
+
+Migrated LangGraph Platform code:
+
+```python
+
+@dataclass
+class InputState: # Equivalent to Input in the original code
+    """Defines the input state, representing a narrower interface to the outside world.
+
+    This class is used to define the initial state and structure of incoming data.
+    See: https://langchain-ai.github.io/langgraph/concepts/low_level/#state
+    for more information.
+    """
+
+    input: str
+    foo: Optional[str] = None
+
+
+@dataclass
+class OutputState: # Equivalent to Output in the original code
+    """Defines the output state, representing a narrower interface to the outside world.
+    
+    https://langchain-ai.github.io/langgraph/concepts/low_level/#state
+    """
+    output: Any
+
+@dataclass
+class SharedState:
+    """The full graph state.
+    
+    https://langchain-ai.github.io/langgraph/concepts/low_level/#state
+    """
+    input: str
+    foo: Optional[str] = None
+    output: Any
+    
+runnable = ... # Same code as before
+
+async def my_node(state: InputState, config: RunnableConfig) -> OutputState:
+    """Each node does work."""
+    return await runnable.ainvoke({"input": state.input, "foo": state.foo})
+
+
+# Define a new graph
+builder = StateGraph(
+    SharedState, config_schema=Configuration, input=InputState, output=OutputState
+)
+
+# Add the node to the graph
+builder.add_node("my_node", my_node)
+
+# Set the entrypoint as `call_model`
+builder.add_edge("__start__", "my_node")
+
+# Compile the workflow into an executable graph
+graph = builder.compile()
+graph.name = "New Graph"  # This defines the custom name in LangSmith
+```
+
+### 2. Refactor LCEL into LangGraph Nodes
+
+This option is recommended if you want to take advantage of more advanced features in LangGraph Platform.
+
+#### Memory (alternative to `RunnableWithMessageHistory`)
+
+For example, LangGraph comes with built-in persistence that is more general than LangChain's `RunnableWithMessageHistory`.
+
+Please refer to the guide on [upgrading to LangGraph memory](https://python.langchain.com/docs/versions/migrating_memory/) for more details.
+
+#### Agents
+
+If you're relying on legacy LangChain agents, you can migrate them into the pre-built
+LangGraph agents. Please refer to the guide on [migrating agents](https://python.langchain.com/docs/how_to/migrate_agent/) for more details.
+
+#### Custom Chains
+
+If you created a custom chain and used LCEL to orchestrate it, you will usually be able to refactor it into a LangGraph without too much difficulty.
+
+There isn't a one-size-fits-all guide for this, but generally speaking, consider creating
+a separate node for any long-running step in your LCEL chain or any step that you would
+want to be able to monitor or debug separately.
+
+For example, if you have a simple Retrieval Augmented Generation (RAG) pipeline, you might have a node for the retrieval step and a node for the generation step.
+
+Original LCEL code:
+
+```python
+...
+rag_chain = (
+    {"context": retriever | format_docs, "question": RunnablePassthrough()}
+    | prompt
+    | llm
+    | StrOutputParser()
+)
+rag_chain.with_types(input_type=Input, output_type=Output)
+```
+
+Using LangGraph for the same pipeline:
+
+
+```python
+
+@dataclass
+class InputState: # Equivalent to Input in the original code
+    """Input question from the user."""
+    question: str
+   
+@dataclass 
+class OutputState: # Equivalent to Output in the original code
+    """The output from the graph."""
+    answer: str
+
+@dataclass 
+class SharedState:
+    question: str
+    docs: List[str]
+    response: str
+   
+async def retriever_node(state: InputState) -> SharedState:
+    """Rettrieve documents based on the user's question."""
+    documents = await retriever.ainvoke({"context": state.question})
+    return {
+        "docs": documents
+    }
+
+async def generator_node(state: SharedState) -> OutputState:
+    """Generate an answer using an LLM based on the retrieved documents and question."""
+    context = " -- DOCUMENT -- ".join(state.docs)
+    prompt = [
+        SystemMessage(
+            content=(
+                "Answer the user's question based on the list of documents "
+                "that were retrieved. Here are the documents: \n\n"
+                f"{context}"
+            )
+        ),
+        HumanMessage(content=state.question),
+    ]
+    ai_message = await llm.ainvoke(prompt)
+    return {"answer": ai_message.content}
+    
+# Define a new graph
+builder = StateGraph(
+    SharedState, config_schema=Configuration, input=InputState, output=OutputState
+)
+builder.add_node("retriever", retriever_node)
+builder.add_node("generator", generator_node)
+builder.add_edge("__start__", "retriever")
+builder.add_edge("retriever", "generator")
+graph = builder.compile()
+graph.name = "RAG Graph"
+```
+
+Please see the [LangGraph tutorials](https://langchain-ai.github.io/langgraph/tutorials/)
+for tutorials and examples that will help you get started with LangGraph
+and LangGraph Platform.
@@ -5,6 +5,15 @@
 [![Open Issues](https://img.shields.io/github/issues-raw/langchain-ai/langserve)](https://github.com/langchain-ai/langserve/issues)
 [![](https://dcbadge.vercel.app/api/server/6adMQxSpJS?compact=true&style=flat)](https://discord.com/channels/1038097195422978059/1170024642245832774)

+> [!WARNING]
+> We recommend using LangGraph Platform rather than LangServe for new projects.
+>
+> Please see the [LangGraph Platform Migration Guide](./MIGRATION.md) for more information.
+>
+> We will continue to accept bug fixes for LangServe from the community; however, we
+> will not be accepting new feature contributions.
+
+
 ## Overview

 [LangServe](https://github.com/langchain-ai/langserve) helps developers
@@ -40,7 +49,7 @@ in [LangChain.js](https://js.langchain.com/docs/ecosystem/langserve).

 ## ⚠️ LangGraph Compatibility

-LangServe is designed to primarily deploy simple Runnables and wok with well-known primitives in langchain-core.
+LangServe is designed to primarily deploy simple Runnables and work with well-known primitives in langchain-core.

 If you need a deployment option for LangGraph, you should instead be looking at [LangGraph Cloud (beta)](https://langchain-ai.github.io/langgraph/cloud/) which will
 be better suited for deploying LangGraph applications.
@@ -48,9 +57,8 @@ be better suited for deploying LangGraph applications.
 ## Limitations

 - Client callbacks are not yet supported for events that originate on the server
- OpenAPI docs will not be generated when using Pydantic V2. Fast API does not
-  support [mixing pydantic v1 and v2 namespaces](https://github.com/tiangolo/fastapi/issues/10360).
-  See section below for more details.
+- Versions of LangServe <= 0.2.0, will not generate OpenAPI docs properly when using Pydantic V2 as Fast API does not support [mixing pydantic v1 and v2 namespaces](https://github.com/tiangolo/fastapi/issues/10360).
+  See section below for more details. Either upgrade to LangServe>=0.3.0 or downgrade Pydantic to pydantic 1.

 ## Security

@@ -92,7 +100,7 @@ langchain app new my-app
 add_routes(app. NotImplemented)
 ```

-### 3. Use `poetry` to add 3rd party packages (e.g., langchain-openai, langchain-anthropic, langchain-mistral etc).
+### 3. Use `poetry` to add 3rd party packages (e.g., langchain-openai, langchain-anthropic, langchain-mistral, etc).

 ```sh
 poetry add [package-name] // e.g `poetry add langchain-openai`
@@ -112,12 +120,7 @@ poetry run langchain serve --port=8100

 ## Examples

-Get your LangServe instance started quickly with
-[LangChain Templates](https://github.com/langchain-ai/langchain/blob/master/templates/README.md).
-
-For more examples, see the templates
-[index](https://github.com/langchain-ai/langchain/blob/master/templates/docs/INDEX.md)
-or the [examples](https://github.com/langchain-ai/langserve/tree/main/examples)
+Get your LangServe instances started quickly with the [examples](https://github.com/langchain-ai/langserve/tree/main/examples)
 directory.

 | Description                                                                                                                                                                                                                                                        | Links                                                                                                                                                                                                                               |
@@ -208,8 +211,9 @@ app.add_middleware(

 If you've deployed the server above, you can view the generated OpenAPI docs using:

-> ⚠️ If using pydantic v2, docs will not be generated for _invoke_, _batch_, _stream_,
+> ⚠️ If using LangServe <= 0.2.0 and pydantic v2, docs will not be generated for _invoke_, _batch_, _stream_,
 > _stream_log_. See [Pydantic](#pydantic) section below for more details.
+> To resolve please upgrade to LangServe 0.3.0.

 ```sh
 curl localhost:8000/docs
@@ -472,7 +476,9 @@ gcloud run deploy [your-service-name] --source . --port 8001 --allow-unauthentic

 ## Pydantic

-LangServe provides support for Pydantic 2 with some limitations.
+LangServe>=0.3 fully supports Pydantic 2.
+
+If you're using an earlier version of LangServe (<= 0.2), then please note that support for Pydantic 2 has the following limitations:

 1. OpenAPI docs will not be generated for invoke/batch/stream/stream_log when using
   Pydantic V2. Fast API does not support [mixing pydantic v1 and v2 namespaces]. To fix this, use `pip install pydantic==1.10.17`.
@@ -35,7 +35,7 @@ from typing import Any, List, Optional, Union

 from fastapi import Depends, FastAPI, HTTPException, Request, Response, status
 from fastapi.security import OAuth2PasswordBearer, OAuth2PasswordRequestForm
-from langchain_community.vectorstores.chroma import Chroma
+from langchain_chroma import Chroma
 from langchain_core.documents import Document
 from langchain_core.runnables import (
    ConfigurableField,
@@ -36,7 +36,7 @@ from typing import Any, Dict, List, Optional, Union

 from fastapi import Depends, FastAPI, HTTPException, Request, status
 from fastapi.security import OAuth2PasswordBearer, OAuth2PasswordRequestForm
-from langchain_community.vectorstores.chroma import Chroma
+from langchain_chroma import Chroma
 from langchain_core.documents import Document
 from langchain_core.runnables import (
    ConfigurableField,
@@ -23,14 +23,7 @@
    "tags": []
   },
   "outputs": [],
-   "source": [
-    "import requests\n",
-    "\n",
-    "inputs = {\"input\": {\"topic\": \"sports\"}}\n",
-    "response = requests.post(\"http://localhost:8000/configurable_temp/invoke\", json=inputs)\n",
-    "\n",
-    "response.json()"
-   ]
+   "source": ["import requests\n\ninputs = {\"input\": {\"topic\": \"sports\"}}\nresponse = requests.post(\"http://localhost:8000/configurable_temp/invoke\", json=inputs)\n\nresponse.json()"]
  },
  {
   "cell_type": "markdown",
@@ -46,11 +39,7 @@
    "tags": []
   },
   "outputs": [],
-   "source": [
-    "from langserve import RemoteRunnable\n",
-    "\n",
-    "remote_runnable = RemoteRunnable(\"http://localhost:8000/configurable_temp\")"
-   ]
+   "source": ["from langserve import RemoteRunnable\n\nremote_runnable = RemoteRunnable(\"http://localhost:8000/configurable_temp\")"]
  },
  {
   "cell_type": "markdown",
@@ -66,9 +55,7 @@
    "tags": []
   },
   "outputs": [],
-   "source": [
-    "response = await remote_runnable.ainvoke({\"topic\": \"sports\"})"
-   ]
+   "source": ["response = await remote_runnable.ainvoke({\"topic\": \"sports\"})"]
  },
  {
   "cell_type": "markdown",
@@ -84,11 +71,7 @@
    "tags": []
   },
   "outputs": [],
-   "source": [
-    "from langchain.schema.runnable.config import RunnableConfig\n",
-    "\n",
-    "remote_runnable.batch([{\"topic\": \"sports\"}, {\"topic\": \"cars\"}])"
-   ]
+   "source": ["from langchain_core.runnables import RunnableConfig\n\nremote_runnable.batch([{\"topic\": \"sports\"}, {\"topic\": \"cars\"}])"]
  },
  {
   "cell_type": "markdown",
@@ -104,10 +87,7 @@
    "tags": []
   },
   "outputs": [],
-   "source": [
-    "async for chunk in remote_runnable.astream({\"topic\": \"bears, but a bit verbose\"}):\n",
-    "    print(chunk, end=\"\", flush=True)"
-   ]
+   "source": ["async for chunk in remote_runnable.astream({\"topic\": \"bears, but a bit verbose\"}):\n    print(chunk, end=\"\", flush=True)"]
  },
  {
   "cell_type": "markdown",
@@ -157,14 +137,7 @@
    "tags": []
   },
   "outputs": [],
-   "source": [
-    "await remote_runnable.ainvoke(\n",
-    "    {\"topic\": \"sports\"},\n",
-    "    config={\n",
-    "        \"configurable\": {\"prompt\": \"how to say {topic} in french\", \"llm\": \"low_temp\"}\n",
-    "    },\n",
-    ")"
-   ]
+   "source": ["await remote_runnable.ainvoke(\n    {\"topic\": \"sports\"},\n    config={\n        \"configurable\": {\"prompt\": \"how to say {topic} in french\", \"llm\": \"low_temp\"}\n    },\n)"]
  },
  {
   "cell_type": "markdown",
@@ -221,13 +194,7 @@
   "execution_count": null,
   "metadata": {},
   "outputs": [],
-   "source": [
-    "# The model will fail with an auth error\n",
-    "unauthenticated_response = requests.post(\n",
-    "    \"http://localhost:8000/auth_from_header/invoke\", json={\"input\": \"hello\"}\n",
-    ")\n",
-    "unauthenticated_response.json()"
-   ]
+   "source": ["# The model will fail with an auth error\nunauthenticated_response = requests.post(\n    \"http://localhost:8000/auth_from_header/invoke\", json={\"input\": \"hello\"}\n)\nunauthenticated_response.json()"]
  },
  {
   "cell_type": "markdown",
@@ -244,25 +211,14 @@
   "execution_count": null,
   "metadata": {},
   "outputs": [],
-   "source": [
-    "# The model will succeed as long as the above shell script is run previously\n",
-    "import os\n",
-    "\n",
-    "test_key = os.environ[\"TEST_API_KEY\"]\n",
-    "authenticated_response = requests.post(\n",
-    "    \"http://localhost:8000/auth_from_header/invoke\",\n",
-    "    json={\"input\": \"hello\"},\n",
-    "    headers={\"x-api-key\": test_key},\n",
-    ")\n",
-    "authenticated_response.json()"
-   ]
+   "source": ["# The model will succeed as long as the above shell script is run previously\nimport os\n\ntest_key = os.environ[\"TEST_API_KEY\"]\nauthenticated_response = requests.post(\n    \"http://localhost:8000/auth_from_header/invoke\",\n    json={\"input\": \"hello\"},\n    headers={\"x-api-key\": test_key},\n)\nauthenticated_response.json()"]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
-   "source": []
+   "source": [""]
  }
 ],
 "metadata": {
@@ -16,9 +16,7 @@
    "tags": []
   },
   "outputs": [],
-   "source": [
-    "from langchain.prompts.chat import ChatPromptTemplate"
-   ]
+   "source": ["from langchain_core.prompts import ChatPromptTemplate"]
  },
  {
   "cell_type": "code",
@@ -27,12 +25,7 @@
    "tags": []
   },
   "outputs": [],
-   "source": [
-    "from langserve import RemoteRunnable\n",
-    "\n",
-    "openai_llm = RemoteRunnable(\"http://localhost:8000/openai/\")\n",
-    "anthropic = RemoteRunnable(\"http://localhost:8000/anthropic/\")"
-   ]
+   "source": ["from langserve import RemoteRunnable\n\nopenai_llm = RemoteRunnable(\"http://localhost:8000/openai/\")\nanthropic = RemoteRunnable(\"http://localhost:8000/anthropic/\")"]
  },
  {
   "cell_type": "markdown",
@@ -48,18 +41,7 @@
    "tags": []
   },
   "outputs": [],
-   "source": [
-    "prompt = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\n",
-    "            \"system\",\n",
-    "            \"You are a highly educated person who loves to use big words. \"\n",
-    "            + \"You are also concise. Never answer in more than three sentences.\",\n",
-    "        ),\n",
-    "        (\"human\", \"Tell me about your favorite novel\"),\n",
-    "    ]\n",
-    ").format_messages()"
-   ]
+   "source": ["prompt = ChatPromptTemplate.from_messages(\n    [\n        (\n            \"system\",\n            \"You are a highly educated person who loves to use big words. \"\n            + \"You are also concise. Never answer in more than three sentences.\",\n        ),\n        (\"human\", \"Tell me about your favorite novel\"),\n    ]\n).format_messages()"]
  },
  {
   "cell_type": "markdown",
@@ -86,9 +68,7 @@
     "output_type": "execute_result"
    }
   ],
-   "source": [
-    "anthropic.invoke(prompt)"
-   ]
+   "source": ["anthropic.invoke(prompt)"]
  },
  {
   "cell_type": "code",
@@ -97,9 +77,7 @@
    "tags": []
   },
   "outputs": [],
-   "source": [
-    "openai_llm.invoke(prompt)"
-   ]
+   "source": ["openai_llm.invoke(prompt)"]
  },
  {
   "cell_type": "markdown",
@@ -126,9 +104,7 @@
     "output_type": "execute_result"
    }
   ],
-   "source": [
-    "await openai_llm.ainvoke(prompt)"
-   ]
+   "source": ["await openai_llm.ainvoke(prompt)"]
  },
  {
   "cell_type": "code",
@@ -149,9 +125,7 @@
     "output_type": "execute_result"
    }
   ],
-   "source": [
-    "anthropic.batch([prompt, prompt])"
-   ]
+   "source": ["anthropic.batch([prompt, prompt])"]
  },
  {
   "cell_type": "code",
@@ -172,9 +146,7 @@
     "output_type": "execute_result"
    }
   ],
-   "source": [
-    "await anthropic.abatch([prompt, prompt])"
-   ]
+   "source": ["await anthropic.abatch([prompt, prompt])"]
  },
  {
   "cell_type": "markdown",
@@ -198,10 +170,7 @@
     ]
    }
   ],
-   "source": [
-    "for chunk in anthropic.stream(prompt):\n",
-    "    print(chunk.content, end=\"\", flush=True)"
-   ]
+   "source": ["for chunk in anthropic.stream(prompt):\n    print(chunk.content, end=\"\", flush=True)"]
  },
  {
   "cell_type": "code",
@@ -218,19 +187,14 @@
     ]
    }
   ],
-   "source": [
-    "async for chunk in anthropic.astream(prompt):\n",
-    "    print(chunk.content, end=\"\", flush=True)"
-   ]
+   "source": ["async for chunk in anthropic.astream(prompt):\n    print(chunk.content, end=\"\", flush=True)"]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
-   "source": [
-    "from langchain.schema.runnable import RunnablePassthrough"
-   ]
+   "source": ["from langchain_core.runnables import RunnablePassthrough"]
  },
  {
   "cell_type": "code",
@@ -239,37 +203,7 @@
    "tags": []
   },
   "outputs": [],
-   "source": [
-    "comedian_chain = (\n",
-    "    ChatPromptTemplate.from_messages(\n",
-    "        [\n",
-    "            (\n",
-    "                \"system\",\n",
-    "                \"You are a comedian that sometimes tells funny jokes and other times you just state facts that are not funny. Please either tell a joke or state fact now but only output one.\",\n",
-    "            ),\n",
-    "        ]\n",
-    "    )\n",
-    "    | openai_llm\n",
-    ")\n",
-    "\n",
-    "joke_classifier_chain = (\n",
-    "    ChatPromptTemplate.from_messages(\n",
-    "        [\n",
-    "            (\n",
-    "                \"system\",\n",
-    "                \"Please determine if the joke is funny. Say `funny` if it's funny and `not funny` if not funny. Then repeat the first five words of the joke for reference...\",\n",
-    "            ),\n",
-    "            (\"human\", \"{joke}\"),\n",
-    "        ]\n",
-    "    )\n",
-    "    | anthropic\n",
-    ")\n",
-    "\n",
-    "\n",
-    "chain = {\"joke\": comedian_chain} | RunnablePassthrough.assign(\n",
-    "    classification=joke_classifier_chain\n",
-    ")"
-   ]
+   "source": ["comedian_chain = (\n    ChatPromptTemplate.from_messages(\n        [\n            (\n                \"system\",\n                \"You are a comedian that sometimes tells funny jokes and other times you just state facts that are not funny. Please either tell a joke or state fact now but only output one.\",\n            ),\n        ]\n    )\n    | openai_llm\n)\n\njoke_classifier_chain = (\n    ChatPromptTemplate.from_messages(\n        [\n            (\n                \"system\",\n                \"Please determine if the joke is funny. Say `funny` if it's funny and `not funny` if not funny. Then repeat the first five words of the joke for reference...\",\n            ),\n            (\"human\", \"{joke}\"),\n        ]\n    )\n    | anthropic\n)\n\n\nchain = {\"joke\": comedian_chain} | RunnablePassthrough.assign(\n    classification=joke_classifier_chain\n)"]
  },
  {
   "cell_type": "code",
@@ -290,9 +224,7 @@
     "output_type": "execute_result"
    }
   ],
-   "source": [
-    "chain.invoke({})"
-   ]
+   "source": ["chain.invoke({})"]
  }
 ],
 "metadata": {
@@ -18,9 +18,7 @@
    "tags": []
   },
   "outputs": [],
-   "source": [
-    "from langchain.prompts.chat import ChatPromptTemplate"
-   ]
+   "source": ["from langchain_core.prompts import ChatPromptTemplate"]
  },
  {
   "cell_type": "code",
@@ -29,11 +27,7 @@
    "tags": []
   },
   "outputs": [],
-   "source": [
-    "from langserve import RemoteRunnable\n",
-    "\n",
-    "model = RemoteRunnable(\"http://localhost:8000/ollama/\")"
-   ]
+   "source": ["from langserve import RemoteRunnable\n\nmodel = RemoteRunnable(\"http://localhost:8000/ollama/\")"]
  },
  {
   "cell_type": "markdown",
@@ -49,9 +43,7 @@
    "tags": []
   },
   "outputs": [],
-   "source": [
-    "prompt = \"Tell me a 3 sentence story about a cat.\""
-   ]
+   "source": ["prompt = \"Tell me a 3 sentence story about a cat.\""]
  },
  {
   "cell_type": "code",
@@ -71,9 +63,7 @@
     "output_type": "execute_result"
    }
   ],
-   "source": [
-    "model.invoke(prompt)"
-   ]
+   "source": ["model.invoke(prompt)"]
  },
  {
   "cell_type": "code",
@@ -93,9 +83,7 @@
     "output_type": "execute_result"
    }
   ],
-   "source": [
-    "await model.ainvoke(prompt)"
-   ]
+   "source": ["await model.ainvoke(prompt)"]
  },
  {
   "cell_type": "markdown",
@@ -131,10 +119,7 @@
     "output_type": "execute_result"
    }
   ],
-   "source": [
-    "%%time\n",
-    "model.batch([prompt, prompt])"
-   ]
+   "source": ["%%time\nmodel.batch([prompt, prompt])"]
  },
  {
   "cell_type": "code",
@@ -152,11 +137,7 @@
     ]
    }
   ],
-   "source": [
-    "%%time\n",
-    "for _ in range(2):\n",
-    "    model.invoke(prompt)"
-   ]
+   "source": ["%%time\nfor _ in range(2):\n    model.invoke(prompt)"]
  },
  {
   "cell_type": "code",
@@ -177,9 +158,7 @@
     "output_type": "execute_result"
    }
   ],
-   "source": [
-    "await model.abatch([prompt, prompt])"
-   ]
+   "source": ["await model.abatch([prompt, prompt])"]
  },
  {
   "cell_type": "markdown",
@@ -206,10 +185,7 @@
     ]
    }
   ],
-   "source": [
-    "for chunk in model.stream(prompt):\n",
-    "    print(chunk.content, end=\"|\", flush=True)"
-   ]
+   "source": ["for chunk in model.stream(prompt):\n    print(chunk.content, end=\"|\", flush=True)"]
  },
  {
   "cell_type": "code",
@@ -227,10 +203,7 @@
     ]
    }
   ],
-   "source": [
-    "async for chunk in model.astream(prompt):\n",
-    "    print(chunk.content, end=\"|\", flush=True)"
-   ]
+   "source": ["async for chunk in model.astream(prompt):\n    print(chunk.content, end=\"|\", flush=True)"]
  },
  {
   "cell_type": "markdown",
@@ -266,15 +239,7 @@
     ]
    }
   ],
-   "source": [
-    "i = 0\n",
-    "async for event in model.astream_events(prompt, version='v1'):\n",
-    "    print(event)\n",
-    "    if i > 10:\n",
-    "        print('...')\n",
-    "        break\n",
-    "    i += 1"
-   ]
+   "source": ["i = 0\nasync for event in model.astream_events(prompt, version='v1'):\n    print(event)\n    if i > 10:\n        print('...')\n        break\n    i += 1"]
  }
 ],
 "metadata": {
@@ -16,9 +16,7 @@
    "tags": []
   },
   "outputs": [],
-   "source": [
-    "from langchain.prompts.chat import ChatPromptTemplate"
-   ]
+   "source": ["from langchain_core.prompts import ChatPromptTemplate"]
  },
  {
   "cell_type": "code",
@@ -27,11 +25,7 @@
    "tags": []
   },
   "outputs": [],
-   "source": [
-    "from langserve import RemoteRunnable\n",
-    "\n",
-    "chain = RemoteRunnable(\"http://localhost:8000/v1/\")"
-   ]
+   "source": ["from langserve import RemoteRunnable\n\nchain = RemoteRunnable(\"http://localhost:8000/v1/\")"]
  },
  {
   "cell_type": "markdown",
@@ -59,9 +53,7 @@
     "output_type": "execute_result"
    }
   ],
-   "source": [
-    "chain.invoke({'thing': 'apple', 'language': 'italian', 'info': {\"user_id\": 42, \"user_info\": {\"address\": 42}}})"
-   ]
+   "source": ["chain.invoke({'thing': 'apple', 'language': 'italian', 'info': {\"user_id\": 42, \"user_info\": {\"address\": 42}}})"]
  },
  {
   "cell_type": "code",
@@ -82,10 +74,7 @@
     ]
    }
   ],
-   "source": [
-    "for chunk in chain.stream({'thing': 'apple', 'language': 'italian', 'info': {\"user_id\": 42, \"user_info\": {\"address\": 42}}}):\n",
-    "    print(chunk)"
-   ]
+   "source": ["for chunk in chain.stream({'thing': 'apple', 'language': 'italian', 'info': {\"user_id\": 42, \"user_info\": {\"address\": 42}}}):\n    print(chunk)"]
  },
  {
   "cell_type": "code",
@@ -94,11 +83,7 @@
    "tags": []
   },
   "outputs": [],
-   "source": [
-    "from langserve import RemoteRunnable\n",
-    "\n",
-    "chain = RemoteRunnable(\"http://localhost:8000/v2/\")"
-   ]
+   "source": ["from langserve import RemoteRunnable\n\nchain = RemoteRunnable(\"http://localhost:8000/v2/\")"]
  },
  {
   "cell_type": "code",
@@ -119,9 +104,7 @@
     "output_type": "execute_result"
    }
   ],
-   "source": [
-    "chain.invoke({'thing': 'apple', 'language': 'italian', 'info': {\"user_id\": 42, \"user_info\": {\"address\": 42}}})"
-   ]
+   "source": ["chain.invoke({'thing': 'apple', 'language': 'italian', 'info': {\"user_id\": 42, \"user_info\": {\"address\": 42}}})"]
  }
 ],
 "metadata": {
@@ -42,6 +42,7 @@ from langsmith import client as ls_client
 from langsmith.schemas import FeedbackIngestToken
 from langsmith.utils import tracing_is_enabled
 from pydantic import BaseModel, Field, RootModel, ValidationError, create_model
+from pydantic.v1 import BaseModel as BaseModelV1
 from starlette.requests import Request
 from starlette.responses import JSONResponse, Response
 from typing_extensions import TypedDict
@@ -61,7 +62,7 @@ from langserve.schema import (
    PublicTraceLink,
    PublicTraceLinkCreateRequest,
 )
-from langserve.serialization import WellKnownLCSerializer
+from langserve.serialization import Serializer, WellKnownLCSerializer
 from langserve.validation import (
    BatchBaseResponse,
    BatchRequestShallowValidator,
@@ -534,6 +535,8 @@ class APIHandler:
        per_req_config_modifier: Optional[PerRequestConfigModifier] = None,
        stream_log_name_allow_list: Optional[Sequence[str]] = None,
        playground_type: Literal["default", "chat"] = "default",
+        astream_events_version: Literal["v1", "v2"] = "v2",
+        serializer: Optional[Serializer] = None,
    ) -> None:
        """Create an API handler for the given runnable.

@@ -568,6 +571,7 @@ class APIHandler:
                If true, the client will be able to show trace information
                including events that occurred on the server side.
                Be sure not to include any sensitive information in the callback events.
+                This is a **beta** API.
            enable_feedback_endpoint: Whether to enable an endpoint for logging feedback
                to LangSmith. Disabled by default. If this flag is disabled or LangSmith
                tracing is not enabled for the runnable, then 4xx errors will be thrown
@@ -595,6 +599,10 @@ class APIHandler:
                If not provided, then all logs will be allowed to be streamed.
                Use to also limit the events that can be streamed by the stream_events.
                TODO: Introduce deprecation for this parameter to rename it
+            astream_events_version: version of the stream events endpoint to use.
+                By default "v2".
+            serializer: optional serializer to use for serializing the output.
+                If not provided, the default serializer will be used.
        """
        if importlib.util.find_spec("sse_starlette") is None:
            raise ImportError(
@@ -626,12 +634,18 @@ class APIHandler:
        # and when tracing information is logged, we'll be able to see
        # traces for the path /foo/bar.
        self._run_name = self._base_url
+        if include_callback_events:
+            warn_beta(
+                message="Including callback events in the response is in beta. "
+                "This API may change in the future."
+            )
        self._include_callback_events = include_callback_events
        self._per_req_config_modifier = per_req_config_modifier
-        self._serializer = WellKnownLCSerializer()
+        self._serializer = serializer or WellKnownLCSerializer()
        self._enable_feedback_endpoint = enable_feedback_endpoint
        self._enable_public_trace_link_endpoint = enable_public_trace_link_endpoint
        self._names_in_stream_allow_list = stream_log_name_allow_list
+        self._astream_events_version = astream_events_version

        if token_feedback_config:
            if len(token_feedback_config["key_configs"]) != 1:
@@ -671,15 +685,57 @@ class APIHandler:

        model_namespace = _replace_non_alphanumeric_with_underscores(path.strip("/"))

-        input_type_ = _resolve_model(
-            runnable.get_input_schema(), "Input", model_namespace
-        )
+        try:
+            input_type_ = _resolve_model(
+                runnable.get_input_schema(), "Input", model_namespace
+            )
+        except Exception as e:
+            # Attempt to surface a more informative user facing error
+            raise_original_error = True
+            try:
+                if isinstance(runnable.get_input_schema(), BaseModelV1):
+                    raise_original_error = False
+                    raise ValueError(
+                        "Found an input type which is a pydantic v1 model."
+                        "Please use pydantic.BaseModel rather than "
+                        "pydantic.v1.BaseModel."
+                    )
+            finally:  # noqa
+                if raise_original_error:
+                    print(
+                        "Encountered an error while resolving the inputs of "
+                        "the Runnable. Try specifying the input type explicitly "
+                        "using the `with_types` method on the runnable.\n"
+                        "See https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.base.Runnable.html "  # noqa: E501
+                    )
+                    raise e

-        output_type_ = _resolve_model(
-            runnable.get_output_schema(),
-            "Output",
-            model_namespace,
-        )
+        try:
+            output_type_ = _resolve_model(
+                runnable.get_output_schema(),
+                "Output",
+                model_namespace,
+            )
+        except Exception as e:
+            # Attempt to surface a more informative user facing error
+            raise_original_error = True
+            try:
+                if isinstance(runnable.get_output_schema(), BaseModelV1):
+                    raise_original_error = False
+                    raise ValueError(
+                        "Found an output type which is a pydantic v1 model."
+                        "Please use pydantic.BaseModel rather than "
+                        "pydantic.v1.BaseModel."
+                    )
+            finally:  # noqa
+                if raise_original_error:
+                    print(
+                        "Encountered an error while resolving the inputs of "
+                        "the Runnable. Try specifying the output type explicitly "
+                        "using the `with_types` method on the runnable.\n"
+                        "See https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.base.Runnable.html "  # noqa: E501
+                    )
+                    raise e

        self._ConfigPayload = _add_namespace_to_model(
            model_namespace, runnable.config_schema(include=config_keys)
@@ -1343,7 +1399,7 @@ class APIHandler:
                    exclude_names=stream_events_request.exclude_names,
                    exclude_types=stream_events_request.exclude_types,
                    exclude_tags=stream_events_request.exclude_tags,
-                    version="v1",
+                    version=self._astream_events_version,
                ):
                    if (
                        self._names_in_stream_allow_list is None
@@ -48,7 +48,7 @@ class AsyncEventAggregatorCallback(AsyncCallbackHandler):

    async def on_chat_model_start(
        self,
-        serialized: Dict[str, Any],
+        serialized: Optional[Dict[str, Any]],
        messages: List[List[BaseMessage]],
        *,
        run_id: UUID,
@@ -73,7 +73,7 @@ class AsyncEventAggregatorCallback(AsyncCallbackHandler):

    async def on_chain_start(
        self,
-        serialized: Dict[str, Any],
+        serialized: Optional[Dict[str, Any]],
        inputs: Dict[str, Any],
        *,
        run_id: UUID,
@@ -138,7 +138,7 @@ class AsyncEventAggregatorCallback(AsyncCallbackHandler):

    async def on_retriever_start(
        self,
-        serialized: Dict[str, Any],
+        serialized: Optional[Dict[str, Any]],
        query: str,
        *,
        run_id: UUID,
@@ -202,7 +202,7 @@ class AsyncEventAggregatorCallback(AsyncCallbackHandler):

    async def on_tool_start(
        self,
-        serialized: Dict[str, Any],
+        serialized: Optional[Dict[str, Any]],
        input_str: str,
        *,
        run_id: UUID,
@@ -306,7 +306,7 @@ class AsyncEventAggregatorCallback(AsyncCallbackHandler):

    async def on_llm_start(
        self,
-        serialized: Dict[str, Any],
+        serialized: Optional[Dict[str, Any]],
        prompts: List[str],
        *,
        run_id: UUID,
@@ -445,7 +445,14 @@ async def ahandle_callbacks(
        if event["parent_run_id"] is None:  # How do we make sure it's None!?
            event["parent_run_id"] = callback_manager.run_id

-        event_data = {key: value for key, value in event.items() if key != "type"}
+        event_data = {
+            key: value
+            for key, value in event.items()
+            if key != "type" and key != "kwargs"
+        }
+
+        if "kwargs" in event:
+            event_data.update(event["kwargs"])

        await ahandle_event(
            # Unpacking like this may not work
@@ -467,7 +474,14 @@ def handle_callbacks(
        if event["parent_run_id"] is None:  # How do we make sure it's None!?
            event["parent_run_id"] = callback_manager.run_id

-        event_data = {key: value for key, value in event.items() if key != "type"}
+        event_data = {
+            key: value
+            for key, value in event.items()
+            if key != "type" and key != "kwargs"
+        }
+
+        if "kwargs" in event:
+            event_data.update(event["kwargs"])

        handle_event(
            # Unpacking like this may not work
@@ -46,7 +46,12 @@
    "postcss": "^8.4.31",
    "tailwindcss": "^3.3.3",
    "typescript": "^5.0.2",
-    "vite": "^4.4.5",
+    "vite": "^4.5.2",
    "vite-plugin-svgr": "^4.1.0"
+  },
+  "resolutions": {
+    "braces": "^3.0.3",
+    "cross-spawn": "^7.0.5",
+    "rollup": "^3.29.5"
  }
 }
@@ -1311,12 +1311,12 @@ brace-expansion@^1.1.7:
    balanced-match "^1.0.0"
    concat-map "0.0.1"

-braces@^3.0.2, braces@~3.0.2:
-  version "3.0.2"
-  resolved "https://registry.yarnpkg.com/braces/-/braces-3.0.2.tgz#3454e1a462ee8d599e236df336cd9ea4f8afe107"
-  integrity sha512-b8um+L1RzM3WDSzvhm6gIz1yfTbBt6YTlcEKAvsmqCZZFw46z626lVj9j1yEPW33H5H+lBQpZMP1k8l+78Ha0A==
+braces@^3.0.2, braces@^3.0.3, braces@~3.0.2:
+  version "3.0.3"
+  resolved "https://registry.yarnpkg.com/braces/-/braces-3.0.3.tgz#490332f40919452272d55a8480adc0c441358789"
+  integrity sha512-yQbXgO/OSZVD2IsiLlro+7Hf6Q18EJrKSEsdoMzKePKXct3gvD8oLcOQdIzGupr5Fj+EDe8gO/lxc1BzfMpxvA==
  dependencies:
-    fill-range "^7.0.1"
+    fill-range "^7.1.1"

 browserslist@^4.21.10, browserslist@^4.21.9:
  version "4.22.1"
@@ -1460,10 +1460,10 @@ cosmiconfig@^8.1.3:
    parse-json "^5.2.0"
    path-type "^4.0.0"

-cross-spawn@^7.0.2:
-  version "7.0.3"
-  resolved "https://registry.yarnpkg.com/cross-spawn/-/cross-spawn-7.0.3.tgz#f73a85b9d5d41d045551c177e2882d4ac85728a6"
-  integrity sha512-iRDPJKUPVEND7dHPO8rkbOnPpyDygcDFtWjpeWNCgy8WP2rXcxXL8TskReQl6OrB2G7+UJrags1q15Fudc7G6w==
+cross-spawn@^7.0.2, cross-spawn@^7.0.5:
+  version "7.0.6"
+  resolved "https://registry.yarnpkg.com/cross-spawn/-/cross-spawn-7.0.6.tgz#8a58fe78f00dcd70c370451759dfbfaf03e8ee9f"
+  integrity sha512-uV2QOWP2nWzsy2aMp8aRibhi9dlzF5Hgh5SHaB9OiTGEyDTiJJyx0uy51QXdyWbtAHNua4XJzUKca3OzKUd3vA==
  dependencies:
    path-key "^3.1.0"
    shebang-command "^2.0.0"
@@ -1750,10 +1750,10 @@ file-entry-cache@^6.0.1:
  dependencies:
    flat-cache "^3.0.4"

-fill-range@^7.0.1:
-  version "7.0.1"
-  resolved "https://registry.yarnpkg.com/fill-range/-/fill-range-7.0.1.tgz#1919a6a7c75fe38b2c7c77e5198535da9acdda40"
-  integrity sha512-qOo9F+dMUmC2Lcb4BbVvnKJxTPjCm+RRpe4gDuGrzkL7mEVl/djYSu2OdQ2Pa302N4oqkSg9ir6jaLWJ2USVpQ==
+fill-range@^7.1.1:
+  version "7.1.1"
+  resolved "https://registry.yarnpkg.com/fill-range/-/fill-range-7.1.1.tgz#44265d3cac07e3ea7dc247516380643754a05292"
+  integrity sha512-YsGpe3WHLK8ZYi4tWDg2Jy3ebRz2rXowDxnld4bkQB00cc/1Zw9AWnC0i9ztDJitivtQvaI9KaLyKrc+hBW0yg==
  dependencies:
    to-regex-range "^5.0.1"

@@ -2483,10 +2483,10 @@ rimraf@^3.0.2:
  dependencies:
    glob "^7.1.3"

-rollup@^3.27.1:
-  version "3.29.4"
-  resolved "https://registry.yarnpkg.com/rollup/-/rollup-3.29.4.tgz#4d70c0f9834146df8705bfb69a9a19c9e1109981"
-  integrity sha512-oWzmBZwvYrU0iJHtDmhsm662rC15FRXmcjCk1xD771dFDx5jJ02ufAQQTn0etB2emNk4J9EZg/yWKpsn9BWGRw==
+rollup@^3.27.1, rollup@^3.29.5:
+  version "3.29.5"
+  resolved "https://registry.yarnpkg.com/rollup/-/rollup-3.29.5.tgz#8a2e477a758b520fb78daf04bca4c522c1da8a54"
+  integrity sha512-GVsDdsbJzzy4S/v3dqWPJ7EfvZJfCHiDqe80IyrF59LYuP+e6U1LJoUqeuqRbwAWoMNoXivMNeNAOf5E22VA1w==
  optionalDependencies:
    fsevents "~2.3.2"

@@ -2770,10 +2770,10 @@ vite-plugin-svgr@^4.1.0:
    "@svgr/core" "^8.1.0"
    "@svgr/plugin-jsx" "^8.1.0"

-vite@^4.4.5:
-  version "4.5.0"
-  resolved "https://registry.yarnpkg.com/vite/-/vite-4.5.0.tgz#ec406295b4167ac3bc23e26f9c8ff559287cff26"
-  integrity sha512-ulr8rNLA6rkyFAlVWw2q5YJ91v098AFQ2R0PRFwPzREXOUJQPtFUG0t+/ZikhaOCDqFoDhN6/v8Sq0o4araFAw==
+vite@^4.5.2:
+  version "4.5.14"
+  resolved "https://registry.yarnpkg.com/vite/-/vite-4.5.14.tgz#2e652bc1d898265d987d6543ce866ecd65fa4086"
+  integrity sha512-+v57oAaoYNnO3hIu5Z/tJRZjq5aHM2zDve9YZ8HngVHbhk66RStobhb1sqPMIPEleV6cNKYK4eGrAbE9Ulbl2g==
  dependencies:
    esbuild "^0.18.10"
    postcss "^8.4.27"
@@ -8,6 +8,7 @@ import weakref
 from concurrent.futures import ThreadPoolExecutor
 from functools import lru_cache
 from typing import (
+    TYPE_CHECKING,
    Any,
    AsyncIterator,
    Dict,
@@ -21,7 +22,7 @@ from typing import (
 from urllib.parse import urljoin

 import httpx
-from httpx._types import AuthTypes, CertTypes, CookieTypes, HeaderTypes, VerifyTypes
+from httpx._types import AuthTypes, CertTypes, CookieTypes, HeaderTypes
 from langchain_core.callbacks import (
    AsyncCallbackManagerForChainRun,
    CallbackManagerForChainRun,
@@ -49,6 +50,10 @@ from langserve.server_sent_events import aconnect_sse, connect_sse

 logger = logging.getLogger(__name__)

+if TYPE_CHECKING:
+    # For type checking httpx types
+    import ssl
+

 def _is_json_serializable(obj: Any) -> bool:
    """Return True if the object is json serializable."""
@@ -120,6 +125,12 @@ def _log_error_message_once(error_message: str) -> None:
    logger.error(error_message)


+@lru_cache(maxsize=1_000)  # Will accommodate up to 1_000 different error messages
+def _log_info_message_once(error_message: str) -> None:
+    """Log an error message once."""
+    logger.info(error_message)
+
+
 def _sanitize_request(request: httpx.Request) -> httpx.Request:
    """Remove sensitive headers from the request."""
    accept_headers = {
@@ -275,10 +286,11 @@ class RemoteRunnable(Runnable[Input, Output]):
        auth: Optional[AuthTypes] = None,
        headers: Optional[HeaderTypes] = None,
        cookies: Optional[CookieTypes] = None,
-        verify: VerifyTypes = True,
+        verify: ssl.SSLContext | str | bool = True,
        cert: Optional[CertTypes] = None,
        client_kwargs: Optional[Dict[str, Any]] = None,
        use_server_callback_events: bool = True,
+        serializer: Optional[Serializer] = None,
    ) -> None:
        """Initialize the client.

@@ -294,6 +306,8 @@ class RemoteRunnable(Runnable[Input, Output]):
                and async httpx clients
            use_server_callback_events: Whether to invoke callbacks on any
                callback events returned by the server.
+            serializer: The serializer to use for serializing and deserializing
+                data. If not provided, a default serializer will be used.
        """
        _client_kwargs = client_kwargs or {}
        # Enforce trailing slash
@@ -321,7 +335,7 @@ class RemoteRunnable(Runnable[Input, Output]):

        # Register cleanup handler once RemoteRunnable is garbage collected
        weakref.finalize(self, _close_clients, self.sync_client, self.async_client)
-        self._lc_serializer = WellKnownLCSerializer()
+        self._lc_serializer = serializer or WellKnownLCSerializer()
        self._use_server_callback_events = use_server_callback_events

    def _invoke(
@@ -752,7 +766,7 @@ class RemoteRunnable(Runnable[Input, Output]):
        input: Any,
        config: Optional[RunnableConfig] = None,
        *,
-        version: Literal["v1"],
+        version: Literal["v1", "v2", None] = None,
        include_names: Optional[Sequence[str]] = None,
        include_types: Optional[Sequence[str]] = None,
        include_tags: Optional[Sequence[str]] = None,
@@ -775,7 +789,8 @@ class RemoteRunnable(Runnable[Input, Output]):
            input: The input to the runnable
            config: The config to use for the runnable
            version: The version of the astream_events to use.
-                     Currently only "v1" is supported.
+                Currently, this input is IGNORED on the client.
+                The server will return whatever format it's configured with.
            include_names: The names of the events to include
            include_types: The types of the events to include
            include_tags: The tags of the events to include
@@ -783,13 +798,18 @@ class RemoteRunnable(Runnable[Input, Output]):
            exclude_types: The types of the events to exclude
            exclude_tags: The tags of the events to exclude
        """
-        if version != "v1":
-            raise ValueError(f"Unsupported version: {version}. Use 'v1'")
-
        # Create a stream handler that will emit Log objects
        config = ensure_config(config)
        callback_manager = get_async_callback_manager_for_config(config)

+        if version is not None:
+            _log_info_message_once(
+                "Versioning of the astream_events API is not supported on the client "
+                "side currently. The server will return events in whatever format "
+                "it was configured with in add_routes or APIHandler. "
+                "To stop seeing this message, remove the `version` argument."
+            )
+
        events = []

        run_manager = await callback_manager.on_chain_start(
@@ -48,7 +48,12 @@
    "postcss": "^8.4.31",
    "tailwindcss": "^3.3.3",
    "typescript": "^5.0.2",
-    "vite": "^4.4.5",
+    "vite": "^4.5.2",
    "vite-plugin-svgr": "^4.1.0"
+  },
+  "resolutions": {
+    "braces": "^3.0.3",
+    "cross-spawn": "^7.0.5",
+    "rollup": "^3.29.5"
  }
 }
@@ -1338,12 +1338,12 @@ brace-expansion@^1.1.7:
    balanced-match "^1.0.0"
    concat-map "0.0.1"

-braces@^3.0.2, braces@~3.0.2:
-  version "3.0.2"
-  resolved "https://registry.yarnpkg.com/braces/-/braces-3.0.2.tgz#3454e1a462ee8d599e236df336cd9ea4f8afe107"
-  integrity sha512-b8um+L1RzM3WDSzvhm6gIz1yfTbBt6YTlcEKAvsmqCZZFw46z626lVj9j1yEPW33H5H+lBQpZMP1k8l+78Ha0A==
+braces@^3.0.2, braces@^3.0.3, braces@~3.0.2:
+  version "3.0.3"
+  resolved "https://registry.yarnpkg.com/braces/-/braces-3.0.3.tgz#490332f40919452272d55a8480adc0c441358789"
+  integrity sha512-yQbXgO/OSZVD2IsiLlro+7Hf6Q18EJrKSEsdoMzKePKXct3gvD8oLcOQdIzGupr5Fj+EDe8gO/lxc1BzfMpxvA==
  dependencies:
-    fill-range "^7.0.1"
+    fill-range "^7.1.1"

 browserslist@^4.21.10, browserslist@^4.21.9:
  version "4.22.1"
@@ -1482,10 +1482,10 @@ cosmiconfig@^8.1.3:
    parse-json "^5.2.0"
    path-type "^4.0.0"

-cross-spawn@^7.0.2:
-  version "7.0.3"
-  resolved "https://registry.yarnpkg.com/cross-spawn/-/cross-spawn-7.0.3.tgz#f73a85b9d5d41d045551c177e2882d4ac85728a6"
-  integrity sha512-iRDPJKUPVEND7dHPO8rkbOnPpyDygcDFtWjpeWNCgy8WP2rXcxXL8TskReQl6OrB2G7+UJrags1q15Fudc7G6w==
+cross-spawn@^7.0.2, cross-spawn@^7.0.5:
+  version "7.0.6"
+  resolved "https://registry.yarnpkg.com/cross-spawn/-/cross-spawn-7.0.6.tgz#8a58fe78f00dcd70c370451759dfbfaf03e8ee9f"
+  integrity sha512-uV2QOWP2nWzsy2aMp8aRibhi9dlzF5Hgh5SHaB9OiTGEyDTiJJyx0uy51QXdyWbtAHNua4XJzUKca3OzKUd3vA==
  dependencies:
    path-key "^3.1.0"
    shebang-command "^2.0.0"
@@ -1777,10 +1777,10 @@ file-entry-cache@^6.0.1:
  dependencies:
    flat-cache "^3.0.4"

-fill-range@^7.0.1:
-  version "7.0.1"
-  resolved "https://registry.yarnpkg.com/fill-range/-/fill-range-7.0.1.tgz#1919a6a7c75fe38b2c7c77e5198535da9acdda40"
-  integrity sha512-qOo9F+dMUmC2Lcb4BbVvnKJxTPjCm+RRpe4gDuGrzkL7mEVl/djYSu2OdQ2Pa302N4oqkSg9ir6jaLWJ2USVpQ==
+fill-range@^7.1.1:
+  version "7.1.1"
+  resolved "https://registry.yarnpkg.com/fill-range/-/fill-range-7.1.1.tgz#44265d3cac07e3ea7dc247516380643754a05292"
+  integrity sha512-YsGpe3WHLK8ZYi4tWDg2Jy3ebRz2rXowDxnld4bkQB00cc/1Zw9AWnC0i9ztDJitivtQvaI9KaLyKrc+hBW0yg==
  dependencies:
    to-regex-range "^5.0.1"

@@ -2503,10 +2503,10 @@ rimraf@^3.0.2:
  dependencies:
    glob "^7.1.3"

-rollup@^3.27.1:
-  version "3.29.4"
-  resolved "https://registry.yarnpkg.com/rollup/-/rollup-3.29.4.tgz#4d70c0f9834146df8705bfb69a9a19c9e1109981"
-  integrity sha512-oWzmBZwvYrU0iJHtDmhsm662rC15FRXmcjCk1xD771dFDx5jJ02ufAQQTn0etB2emNk4J9EZg/yWKpsn9BWGRw==
+rollup@^3.27.1, rollup@^3.29.5:
+  version "3.29.5"
+  resolved "https://registry.yarnpkg.com/rollup/-/rollup-3.29.5.tgz#8a2e477a758b520fb78daf04bca4c522c1da8a54"
+  integrity sha512-GVsDdsbJzzy4S/v3dqWPJ7EfvZJfCHiDqe80IyrF59LYuP+e6U1LJoUqeuqRbwAWoMNoXivMNeNAOf5E22VA1w==
  optionalDependencies:
    fsevents "~2.3.2"

@@ -2790,10 +2790,10 @@ vite-plugin-svgr@^4.1.0:
    "@svgr/core" "^8.1.0"
    "@svgr/plugin-jsx" "^8.1.0"

-vite@^4.4.5:
-  version "4.5.0"
-  resolved "https://registry.yarnpkg.com/vite/-/vite-4.5.0.tgz#ec406295b4167ac3bc23e26f9c8ff559287cff26"
-  integrity sha512-ulr8rNLA6rkyFAlVWw2q5YJ91v098AFQ2R0PRFwPzREXOUJQPtFUG0t+/ZikhaOCDqFoDhN6/v8Sq0o4araFAw==
+vite@^4.5.2:
+  version "4.5.14"
+  resolved "https://registry.yarnpkg.com/vite/-/vite-4.5.14.tgz#2e652bc1d898265d987d6543ce866ecd65fa4086"
+  integrity sha512-+v57oAaoYNnO3hIu5Z/tJRZjq5aHM2zDve9YZ8HngVHbhk66RStobhb1sqPMIPEleV6cNKYK4eGrAbE9Ulbl2g==
  dependencies:
    esbuild "^0.18.10"
    postcss "^8.4.27"
@@ -157,40 +157,50 @@ def _decode_event_data(value: Any) -> Any:


 class Serializer(abc.ABC):
-    @abc.abstractmethod
    def dumpd(self, obj: Any) -> Any:
        """Convert the given object to a JSON serializable object."""
-
-    @abc.abstractmethod
-    def dumps(self, obj: Any) -> bytes:
-        """Dump the given object as a JSON string."""
-
-    @abc.abstractmethod
-    def loads(self, s: bytes) -> Any:
-        """Load the given JSON string."""
-
-    @abc.abstractmethod
-    def loadd(self, obj: Any) -> Any:
-        """Load the given object."""
-
-
-class WellKnownLCSerializer(Serializer):
-    def dumpd(self, obj: Any) -> Any:
-        """Convert the given object to a JSON serializable object."""
-        return orjson.loads(orjson.dumps(obj, default=default))
-
-    def dumps(self, obj: Any) -> bytes:
-        """Dump the given object as a JSON string."""
-        return orjson.dumps(obj, default=default)
-
-    def loadd(self, obj: Any) -> Any:
-        """Load the given object."""
-        return _decode_lc_objects(obj)
+        return orjson.loads(self.dumps(obj))

    def loads(self, s: bytes) -> Any:
        """Load the given JSON string."""
        return self.loadd(orjson.loads(s))

+    @abc.abstractmethod
+    def dumps(self, obj: Any) -> bytes:
+        """Dump the given object to a JSON byte string."""
+
+    @abc.abstractmethod
+    def loadd(self, s: bytes) -> Any:
+        """Given a python object, load it into a well known object.
+
+        The obj represents content that was json loaded from a string, but
+        not yet validated or converted into a well known object.
+        """
+
+
+class WellKnownLCSerializer(Serializer):
+    """A pre-defined serializer for well known LangChain objects.
+
+    This is the default serialized used by LangServe for serializing and
+    de-serializing well known LangChain objects.
+
+    If you need to extend the serialization capabilities for your own application,
+    feel free to create a new instance of the Serializer class and implement
+    the abstract methods dumps and loadd.
+    """
+
+    def dumps(self, obj: Any) -> bytes:
+        """Dump the given object to a JSON byte string."""
+        return orjson.dumps(obj, default=default)
+
+    def loadd(self, obj: Any) -> Any:
+        """Given a python object, load it into a well known object.
+
+        The obj represents content that was json loaded from a string, but
+        not yet validated or converted into a well known object.
+        """
+        return _decode_lc_objects(obj)
+

 def _project_top_level(model: BaseModel) -> Dict[str, Any]:
    """Project the top level of the model as dict."""
@@ -26,6 +26,7 @@ from langserve.api_handler import (
    TokenFeedbackConfig,
    _is_hosted,
 )
+from langserve.serialization import Serializer

 try:
    from fastapi import APIRouter, Depends, FastAPI, Request, Response
@@ -262,6 +263,8 @@ def add_routes(
    enabled_endpoints: Optional[Sequence[EndpointName]] = None,
    dependencies: Optional[Sequence[Depends]] = None,
    playground_type: Literal["default", "chat"] = "default",
+    astream_events_version: Literal["v1", "v2"] = "v2",
+    serializer: Optional[Serializer] = None,
 ) -> None:
    """Register the routes on the given FastAPI app or APIRouter.

@@ -380,14 +383,18 @@ def add_routes(
            - chat: UX is optimized for chat-like interactions. Please review
              the README in langserve for more details about constraints (e.g.,
              which message types are supported etc.)
+        astream_events_version: version of the stream events endpoint to use.
+            By default "v2".
+        serializer: The serializer to use for serializing the output. If not provided,
+            the default serializer will be used.
    """  # noqa: E501
    if not isinstance(runnable, Runnable):
        raise TypeError(
            f"Expected a Runnable, got {type(runnable)}. "
-            f"The second argument to add_routes should be a Runnable instance."
-            f"add_route(app, runnable, ...) is the correct usage."
-            f"Please make sure that you are using a runnable which is an instance of "
-            f"langchain_core.runnables.Runnable."
+            "The second argument to add_routes should be a Runnable instance."
+            "add_route(app, runnable, ...) is the correct usage."
+            "Please make sure that you are using a runnable which is an instance of "
+            "langchain_core.runnables.Runnable."
        )

    endpoint_configuration = _EndpointConfiguration(
@@ -443,7 +450,10 @@ def add_routes(
        per_req_config_modifier=per_req_config_modifier,
        stream_log_name_allow_list=stream_log_name_allow_list,
        playground_type=playground_type,
+        astream_events_version=astream_events_version,
+        serializer=serializer,
    )
+
    namespace = path or ""

    route_tags = [path.strip("/")] if path else None
@@ -1,8 +1,9 @@
 """Adapted from https://github.com/florimondmanca/httpx-sse"""
 from contextlib import asynccontextmanager, contextmanager
-from typing import Any, AsyncIterator, Iterator, List, Optional, TypedDict
+from typing import Any, AsyncIterator, Iterator, List, Optional

 import httpx
+from typing_extensions import TypedDict


 class ServerSentEvent(TypedDict):
@@ -396,27 +396,29 @@ class StreamEventsParameters(BaseModel):
 # status code and a message.


-class OnChainStart(BaseModel):
-    """On Chain Start Callback Event."""
+class BaseCallback(BaseModel):
+    """Base class for all callback events."""

-    serialized: Dict[str, Any]
-    inputs: Any
    run_id: UUID
    parent_run_id: Optional[UUID] = None
    tags: Optional[List[str]] = None
    metadata: Optional[Dict[str, Any]] = None
-    kwargs: Any = None
+
+
+class OnChainStart(BaseCallback):
+    """On Chain Start Callback Event."""
+
+    serialized: Optional[Dict[str, Any]] = None
+    inputs: Any
+    kwargs: Optional[Dict[str, Any]] = None
    type: Literal["on_chain_start"] = "on_chain_start"


-class OnChainEnd(BaseModel):
+class OnChainEnd(BaseCallback):
    """On Chain End Callback Event."""

    outputs: Any
-    run_id: UUID
-    parent_run_id: Optional[UUID] = None
-    tags: Optional[List[str]] = None
-    kwargs: Any = None
+    kwargs: Optional[Dict[str, Any]] = None
    type: Literal["on_chain_end"] = "on_chain_end"


@@ -428,38 +430,35 @@ class Error(BaseModel):
    type: Literal["error"] = "error"


-class OnChainError(BaseModel):
+class OnChainError(BaseCallback):
    """On Chain Error Callback Event."""

    error: Error
-    run_id: UUID
-    parent_run_id: Optional[UUID] = None
-    tags: Optional[List[str]] = None
-    kwargs: Any = None
+    kwargs: Optional[Dict[str, Any]] = None
    type: Literal["on_chain_error"] = "on_chain_error"


-class OnToolStart(BaseModel):
+class OnToolStart(BaseCallback):
    """On Tool Start Callback Event."""

-    serialized: Dict[str, Any]
+    serialized: Optional[Dict[str, Any]] = None
    input_str: str
    run_id: UUID
    parent_run_id: Optional[UUID] = None
    tags: Optional[List[str]] = None
    metadata: Optional[Dict[str, Any]] = None
-    kwargs: Any = None
+    kwargs: Optional[Dict[str, Any]] = None
    type: Literal["on_tool_start"] = "on_tool_start"


-class OnToolEnd(BaseModel):
+class OnToolEnd(BaseCallback):
    """On Tool End Callback Event."""

    output: str
    run_id: UUID
    parent_run_id: Optional[UUID] = None
    tags: Optional[List[str]] = None
-    kwargs: Any = None
+    kwargs: Optional[Dict[str, Any]] = None
    type: Literal["on_tool_end"] = "on_tool_end"


@@ -467,36 +466,29 @@ class OnToolError(BaseModel):
    """On Tool Error Callback Event."""

    error: Error
-    run_id: UUID
-    parent_run_id: Optional[UUID] = None
-    tags: Optional[List[str]] = None
-    kwargs: Any = None
+    kwargs: Optional[Dict[str, Any]] = None
    type: Literal["on_tool_error"] = "on_tool_error"


-class OnChatModelStart(BaseModel):
+class OnChatModelStart(BaseCallback):
    """On Chat Model Start Callback Event."""

-    serialized: Dict[str, Any]
+    serialized: Optional[Dict[str, Any]] = None
    messages: List[List[BaseMessage]]
-    run_id: UUID
-    parent_run_id: Optional[UUID] = None
-    tags: Optional[List[str]] = None
-    metadata: Optional[Dict[str, Any]] = None
-    kwargs: Any = None
+    kwargs: Optional[Dict[str, Any]] = None
    type: Literal["on_chat_model_start"] = "on_chat_model_start"


-class OnLLMStart(BaseModel):
+class OnLLMStart(BaseCallback):
    """On LLM Start Callback Event."""

-    serialized: Dict[str, Any]
+    serialized: Optional[Dict[str, Any]] = None
    prompts: List[str]
    run_id: UUID
    parent_run_id: Optional[UUID] = None
    tags: Optional[List[str]] = None
    metadata: Optional[Dict[str, Any]] = None
-    kwargs: Any = None
+    kwargs: Optional[Dict[str, Any]] = None
    type: Literal["on_llm_start"] = "on_llm_start"


@@ -515,49 +507,39 @@ class LLMResult(BaseModel):
    """List of metadata info for model call for each input."""


-class OnLLMEnd(BaseModel):
+class OnLLMEnd(BaseCallback):
    """On LLM End Callback Event."""

    response: LLMResult
-    run_id: UUID
-    parent_run_id: Optional[UUID] = None
-    tags: Optional[List[str]] = None
-    kwargs: Any = None
+    kwargs: Optional[Dict[str, Any]] = None
    type: Literal["on_llm_end"] = "on_llm_end"


-class OnRetrieverStart(BaseModel):
+class OnRetrieverStart(BaseCallback):
    """On Retriever Start Callback Event."""

-    serialized: Dict[str, Any]
+    serialized: Optional[Dict[str, Any]] = None
    query: str
-    run_id: UUID
-    parent_run_id: Optional[UUID] = None
-    tags: Optional[List[str]] = None
-    metadata: Optional[Dict[str, Any]] = None
-    kwargs: Any = None
+    kwargs: Optional[Dict[str, Any]] = None
    type: Literal["on_retriever_start"] = "on_retriever_start"


-class OnRetrieverError(BaseModel):
+class OnRetrieverError(BaseCallback):
    """On Retriever Error Callback Event."""

    error: Error
    run_id: UUID
    parent_run_id: Optional[UUID] = None
    tags: Optional[List[str]] = None
-    kwargs: Any = None
+    kwargs: Optional[Dict[str, Any]] = None
    type: Literal["on_retriever_error"] = "on_retriever_error"


-class OnRetrieverEnd(BaseModel):
+class OnRetrieverEnd(BaseCallback):
    """On Retriever End Callback Event."""

    documents: Sequence[Document]
-    run_id: UUID
-    parent_run_id: Optional[UUID] = None
-    tags: Optional[List[str]] = None
-    kwargs: Any = None
+    kwargs: Optional[Dict[str, Any]] = None
    type: Literal["on_retriever_end"] = "on_retriever_end"


@@ -826,13 +826,13 @@ tests = ["asttokens (>=2.1.0)", "coverage", "coverage-enable-subprocess", "ipyth

 [[package]]
 name = "fastapi"
-version = "0.114.1"
+version = "0.114.2"
 description = "FastAPI framework, high performance, easy to learn, fast to code, ready for production"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "fastapi-0.114.1-py3-none-any.whl", hash = "sha256:5d4746f6e4b7dff0b4f6b6c6d5445645285f662fe75886e99af7ee2d6b58bb3e"},
-    {file = "fastapi-0.114.1.tar.gz", hash = "sha256:1d7bbbeabbaae0acb0c22f0ab0b040f642d3093ca3645f8c876b6f91391861d8"},
+    {file = "fastapi-0.114.2-py3-none-any.whl", hash = "sha256:44474a22913057b1acb973ab90f4b671ba5200482e7622816d79105dcece1ac5"},
+    {file = "fastapi-0.114.2.tar.gz", hash = "sha256:0adb148b62edb09e8c6eeefa3ea934e8f276dabc038c5a82989ea6346050c3da"},
 ]

 [package.dependencies]
@@ -1062,15 +1062,18 @@ zstd = ["zstandard (>=0.18.0)"]

 [[package]]
 name = "idna"
-version = "3.8"
+version = "3.9"
 description = "Internationalized Domain Names in Applications (IDNA)"
 optional = false
 python-versions = ">=3.6"
 files = [
-    {file = "idna-3.8-py3-none-any.whl", hash = "sha256:050b4e5baadcd44d760cedbd2b8e639f2ff89bbc7a5730fcc662954303377aac"},
-    {file = "idna-3.8.tar.gz", hash = "sha256:d838c2c0ed6fced7693d5e8ab8e734d5f8fda53a039c0164afb0b82e771e3603"},
+    {file = "idna-3.9-py3-none-any.whl", hash = "sha256:69297d5da0cc9281c77efffb4e730254dd45943f45bbfb461de5991713989b1e"},
+    {file = "idna-3.9.tar.gz", hash = "sha256:e5c5dafde284f26e9e0f28f6ea2d6400abd5ca099864a67f576f3981c6476124"},
 ]

+[package.extras]
+all = ["flake8 (>=7.1.1)", "mypy (>=1.11.2)", "pytest (>=8.3.2)", "ruff (>=0.6.2)"]
+
 [[package]]
 name = "importlib-metadata"
 version = "8.5.0"
@@ -1564,41 +1567,44 @@ test = ["hatch", "ipykernel", "openapi-core (>=0.18.0,<0.19.0)", "openapi-spec-v

 [[package]]
 name = "langchain-core"
-version = "0.3.0.dev5"
+version = "0.3.0"
 description = "Building applications with LLMs through composability"
 optional = false
 python-versions = "<4.0,>=3.9"
 files = [
-    {file = "langchain_core-0.3.0.dev5-py3-none-any.whl", hash = "sha256:8de38ea9dd15f9705d20ee44af7160216052467d47893d5473e0e878861685be"},
-    {file = "langchain_core-0.3.0.dev5.tar.gz", hash = "sha256:d0986b3e2810522d90eb09d048ee4a92b079a334b313f4b7429624b4a062adff"},
+    {file = "langchain_core-0.3.0-py3-none-any.whl", hash = "sha256:bee6dae2366d037ef0c5b87401fed14b5497cad26f97724e8c9ca7bc9239e847"},
+    {file = "langchain_core-0.3.0.tar.gz", hash = "sha256:1249149ea3ba24c9c761011483c14091573a5eb1a773aa0db9c8ad155dd4a69d"},
 ]

 [package.dependencies]
 jsonpatch = ">=1.33,<2.0"
 langsmith = ">=0.1.117,<0.2.0"
 packaging = ">=23.2,<25"
-pydantic = ">=2.7.4,<3.0.0"
+pydantic = [
+    {version = ">=2.5.2,<3.0.0", markers = "python_full_version < \"3.12.4\""},
+    {version = ">=2.7.4,<3.0.0", markers = "python_full_version >= \"3.12.4\""},
+]
 PyYAML = ">=5.3"
 tenacity = ">=8.1.0,<8.4.0 || >8.4.0,<9.0.0"
 typing-extensions = ">=4.7"

 [[package]]
 name = "langsmith"
-version = "0.1.117"
+version = "0.1.120"
 description = "Client library to connect to the LangSmith LLM Tracing and Evaluation Platform."
 optional = false
 python-versions = "<4.0,>=3.8.1"
 files = [
-    {file = "langsmith-0.1.117-py3-none-any.whl", hash = "sha256:e936ee9bcf8293b0496df7ba462a3702179fbe51f9dc28744b0fbec0dbf206ae"},
-    {file = "langsmith-0.1.117.tar.gz", hash = "sha256:a1b532f49968b9339bcaff9118d141846d52ed3d803f342902e7448edf1d662b"},
+    {file = "langsmith-0.1.120-py3-none-any.whl", hash = "sha256:54d2785e301646c0988e0a69ebe4d976488c87b41928b358cb153b6ddd8db62b"},
+    {file = "langsmith-0.1.120.tar.gz", hash = "sha256:25499ca187b41bd89d784b272b97a8d76f60e0e21bdf20336e8a2aa6a9b23ac9"},
 ]

 [package.dependencies]
 httpx = ">=0.23.0,<1"
 orjson = ">=3.9.14,<4.0.0"
 pydantic = [
-    {version = ">=2.7.4,<3.0.0", markers = "python_full_version >= \"3.12.4\""},
    {version = ">=1,<3", markers = "python_full_version < \"3.12.4\""},
+    {version = ">=2.7.4,<3.0.0", markers = "python_full_version >= \"3.12.4\""},
 ]
 requests = ">=2,<3"

@@ -2117,13 +2123,13 @@ ptyprocess = ">=0.5"

 [[package]]
 name = "platformdirs"
-version = "4.3.2"
+version = "4.3.3"
 description = "A small Python package for determining appropriate platform-specific dirs, e.g. a `user data dir`."
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "platformdirs-4.3.2-py3-none-any.whl", hash = "sha256:eb1c8582560b34ed4ba105009a4badf7f6f85768b30126f351328507b2beb617"},
-    {file = "platformdirs-4.3.2.tar.gz", hash = "sha256:9e5e27a08aa095dd127b9f2e764d74254f482fef22b0970773bfba79d091ab8c"},
+    {file = "platformdirs-4.3.3-py3-none-any.whl", hash = "sha256:50a5450e2e84f44539718293cbb1da0a0885c9d14adf21b77bae4e66fc99d9b5"},
+    {file = "platformdirs-4.3.3.tar.gz", hash = "sha256:d4e0b7d8ec176b341fb03cb11ca12d0276faa8c485f9cd218f613840463fc2c0"},
 ]

 [package.extras]
@@ -2254,8 +2260,8 @@ files = [
 annotated-types = ">=0.6.0"
 pydantic-core = "2.23.3"
 typing-extensions = [
-    {version = ">=4.12.2", markers = "python_version >= \"3.13\""},
    {version = ">=4.6.1", markers = "python_version < \"3.13\""},
+    {version = ">=4.12.2", markers = "python_version >= \"3.13\""},
 ]

 [package.extras]
@@ -2377,23 +2383,6 @@ files = [
 [package.extras]
 windows-terminal = ["colorama (>=0.4.6)"]

-[[package]]
-name = "pyproject-toml"
-version = "0.0.10"
-description = "Project intend to implement PEP 517, 518, 621, 631 and so on."
-optional = false
-python-versions = "*"
-files = [
-    {file = "pyproject-toml-0.0.10.tar.gz", hash = "sha256:f0ce0e9934ecb00c0e529b4a1c380edd3034c4be65516769c5f080bdb23dfcb3"},
-    {file = "pyproject_toml-0.0.10-py3-none-any.whl", hash = "sha256:257a7070617e1a0bcfd8f790817b30bd9193876023a9b9e7a6b4fc976acf4c3e"},
-]
-
-[package.dependencies]
-jsonschema = "*"
-setuptools = ">=42"
-toml = "*"
-wheel = "*"
-
 [[package]]
 name = "pytest"
 version = "7.4.4"
@@ -2988,26 +2977,6 @@ nativelib = ["pyobjc-framework-Cocoa", "pywin32"]
 objc = ["pyobjc-framework-Cocoa"]
 win32 = ["pywin32"]

-[[package]]
-name = "setuptools"
-version = "74.1.2"
-description = "Easily download, build, install, upgrade, and uninstall Python packages"
-optional = false
-python-versions = ">=3.8"
-files = [
-    {file = "setuptools-74.1.2-py3-none-any.whl", hash = "sha256:5f4c08aa4d3ebcb57a50c33b1b07e94315d7fc7230f7115e47fc99776c8ce308"},
-    {file = "setuptools-74.1.2.tar.gz", hash = "sha256:95b40ed940a1c67eb70fc099094bd6e99c6ee7c23aa2306f4d2697ba7916f9c6"},
-]
-
-[package.extras]
-check = ["pytest-checkdocs (>=2.4)", "pytest-ruff (>=0.2.1)", "ruff (>=0.5.2)"]
-core = ["importlib-metadata (>=6)", "importlib-resources (>=5.10.2)", "jaraco.text (>=3.7)", "more-itertools (>=8.8)", "packaging (>=24)", "platformdirs (>=2.6.2)", "tomli (>=2.0.1)", "wheel (>=0.43.0)"]
-cover = ["pytest-cov"]
-doc = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "pygments-github-lexers (==0.0.5)", "pyproject-hooks (!=1.1)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-favicon", "sphinx-inline-tabs", "sphinx-lint", "sphinx-notfound-page (>=1,<2)", "sphinx-reredirects", "sphinxcontrib-towncrier", "towncrier (<24.7)"]
-enabler = ["pytest-enabler (>=2.2)"]
-test = ["build[virtualenv] (>=1.0.3)", "filelock (>=3.4.0)", "ini2toml[lite] (>=0.14)", "jaraco.develop (>=7.21)", "jaraco.envs (>=2.2)", "jaraco.path (>=3.2.0)", "jaraco.test", "packaging (>=23.2)", "pip (>=19.1)", "pyproject-hooks (!=1.1)", "pytest (>=6,!=8.1.*)", "pytest-home (>=0.5)", "pytest-perf", "pytest-subprocess", "pytest-timeout", "pytest-xdist (>=3)", "tomli-w (>=1.0.0)", "virtualenv (>=13.0.0)", "wheel (>=0.44.0)"]
-type = ["importlib-metadata (>=7.0.2)", "jaraco.develop (>=7.21)", "mypy (==1.11.*)", "pytest-mypy"]
-
 [[package]]
 name = "six"
 version = "1.16.0"
@@ -3149,17 +3118,6 @@ webencodings = ">=0.4"
 doc = ["sphinx", "sphinx_rtd_theme"]
 test = ["pytest", "ruff"]

-[[package]]
-name = "toml"
-version = "0.10.2"
-description = "Python Library for Tom's Obvious, Minimal Language"
-optional = false
-python-versions = ">=2.6, !=3.0.*, !=3.1.*, !=3.2.*"
-files = [
-    {file = "toml-0.10.2-py2.py3-none-any.whl", hash = "sha256:806143ae5bfb6a3c6e736a764057db0e6a0e05e338b5630894a5f779cabb4f9b"},
-    {file = "toml-0.10.2.tar.gz", hash = "sha256:b3bda1d108d5dd99f4a20d24d9c348e91c4db7ab1b749200bded2f839ccbe68f"},
-]
-
 [[package]]
 name = "tomli"
 version = "2.0.1"
@@ -3264,13 +3222,13 @@ dev = ["flake8", "flake8-annotations", "flake8-bandit", "flake8-bugbear", "flake

 [[package]]
 name = "urllib3"
-version = "2.2.2"
+version = "2.2.3"
 description = "HTTP library with thread-safe connection pooling, file post, and more."
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "urllib3-2.2.2-py3-none-any.whl", hash = "sha256:a448b2f64d686155468037e1ace9f2d2199776e17f0a46610480d311f73e3472"},
-    {file = "urllib3-2.2.2.tar.gz", hash = "sha256:dd505485549a7a552833da5e6063639d0d177c04f23bc3864e41e5dc5f612168"},
+    {file = "urllib3-2.2.3-py3-none-any.whl", hash = "sha256:ca899ca043dcb1bafa3e262d73aa25c465bfb49e0bd9dd5d59f1d0acba2f8fac"},
+    {file = "urllib3-2.2.3.tar.gz", hash = "sha256:e7d814a81dad81e6caf2ec9fdedb284ecc9c73076b62654547cc64ccdcae26e9"},
 ]

 [package.extras]
@@ -3634,20 +3592,6 @@ files = [
    {file = "websockets-13.0.1.tar.gz", hash = "sha256:4d6ece65099411cfd9a48d13701d7438d9c34f479046b34c50ff60bb8834e43e"},
 ]

-[[package]]
-name = "wheel"
-version = "0.44.0"
-description = "A built-package format for Python"
-optional = false
-python-versions = ">=3.8"
-files = [
-    {file = "wheel-0.44.0-py3-none-any.whl", hash = "sha256:2376a90c98cc337d18623527a97c31797bd02bad0033d41547043a1cbfbe448f"},
-    {file = "wheel-0.44.0.tar.gz", hash = "sha256:a29c3f2817e95ab89aa4660681ad547c0e9547f20e75b0562fe7723c9a2a9d49"},
-]
-
-[package.extras]
-test = ["pytest (>=6.0.0)", "setuptools (>=65)"]
-
 [[package]]
 name = "y-py"
 version = "0.6.2"
@@ -3857,13 +3801,13 @@ test = ["mypy", "pre-commit", "pytest", "pytest-asyncio", "websockets (>=10.0)"]

 [[package]]
 name = "zipp"
-version = "3.20.1"
+version = "3.20.2"
 description = "Backport of pathlib-compatible object wrapper for zip files"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "zipp-3.20.1-py3-none-any.whl", hash = "sha256:9960cd8967c8f85a56f920d5d507274e74f9ff813a0ab8889a5b5be2daf44064"},
-    {file = "zipp-3.20.1.tar.gz", hash = "sha256:c22b14cc4763c5a5b04134207736c107db42e9d3ef2d9779d465f5f1bcba572b"},
+    {file = "zipp-3.20.2-py3-none-any.whl", hash = "sha256:a817ac80d6cf4b23bf7f2828b7cabf326f15a001bea8b1f9b49631780ba28350"},
+    {file = "zipp-3.20.2.tar.gz", hash = "sha256:bc9eb26f4506fda01b81bcde0ca78103b6e62f991b381fec825435c836edbc29"},
 ]

 [package.extras]
@@ -3882,4 +3826,4 @@ server = ["fastapi", "sse-starlette"]
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.9"
-content-hash = "bee76de01384e265c807d785959226cdf9c788b4d5dfc3772dcce5d70a8f6121"
+content-hash = "8bb5ca68199c071d2d95d1bec5d4cf3e36a0e0535853b2370cfb594ba0808c0d"
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "langserve"
-version = "0.3.0dev2"
+version = "0.3.2"
 description = ""
 readme = "README.md"
 authors = ["LangChain"]
@@ -11,12 +11,11 @@ include = ["langserve/playground/dist/**/*", "langserve/chat_playground/dist/**/

 [tool.poetry.dependencies]
 python = "^3.9"
-httpx = ">=0.23.0" # May be able to decrease this version
+httpx = ">=0.23.0,<1.0"
 fastapi = {version = ">=0.90.1,<1", optional = true}
 sse-starlette = {version = "^1.3.0", optional = true}
-langchain-core = "0.3.0dev5"
-orjson = ">=2"
-pyproject-toml = "^0.0.10"
+langchain-core = "^0.3"
+orjson = ">=2,<4"
 pydantic = "^2.7"

 [tool.poetry.group.dev.dependencies]
@@ -189,9 +189,3 @@ def test_encoding_of_well_known_types(obj: Any, expected: str) -> None:
    """
    lc_serializer = WellKnownLCSerializer()
    assert lc_serializer.dumpd(obj) == expected
-
-
-@pytest.mark.xfail(reason="0.3")
-def test_fail_03() -> None:
-    """This test will fail on purposes. It contains a TODO list for 0.3 release."""
-    assert "CHatGeneration_Deserialized correct" == "UNcomment test above"
@@ -56,6 +56,7 @@ from langchain_core.tracers import RunLog, RunLogPatch
 from langsmith import schemas as ls_schemas
 from langsmith.client import Client
 from langsmith.schemas import FeedbackIngestToken
+from orjson import orjson
 from pydantic import BaseModel, Field, __version__
 from pytest import MonkeyPatch
 from pytest_mock import MockerFixture
@@ -122,6 +123,19 @@ def _replace_run_id_in_stream_resp(streamed_resp: str) -> str:
    return streamed_resp.replace(uuid, "<REPLACED>")


+def _null_run_id_and_metadata_recursively(decoded_response: Any) -> None:
+    """Recursively traverse the object and delete any keys called run_id"""
+    if isinstance(decoded_response, dict):
+        for key, value in decoded_response.items():
+            if key in {"run_id", "__langserve_version"}:
+                decoded_response[key] = None
+            else:
+                _null_run_id_and_metadata_recursively(value)
+    elif isinstance(decoded_response, list):
+        for item in decoded_response:
+            _null_run_id_and_metadata_recursively(item)
+
+
@pytest.fixture(scope="module")
 def event_loop():
    """Create an instance of the default event loop for each test case."""
@@ -231,13 +245,17 @@ async def get_async_test_client(

@asynccontextmanager
 async def get_async_remote_runnable(
-    server: FastAPI, *, path: Optional[str] = None, raise_app_exceptions: bool = True
+    server: FastAPI,
+    *,
+    path: Optional[str] = None,
+    raise_app_exceptions: bool = True,
+    **kwargs: Any,
 ) -> RemoteRunnable:
    """Get an async client."""
    url = "http://localhost:9999"
    if path:
        url += path
-    remote_runnable_client = RemoteRunnable(url=url)
+    remote_runnable_client = RemoteRunnable(url=url, **kwargs)

    async with get_async_test_client(
        server, path=path, raise_app_exceptions=raise_app_exceptions
@@ -523,6 +541,15 @@ def test_invoke(sync_remote_runnable: RemoteRunnable) -> None:
    assert remote_runnable_run.child_runs[0].name == "add_one_or_passthrough"


+def test_batch_tracer_with_single_input(sync_remote_runnable: RemoteRunnable) -> None:
+    """Test passing a single tracer to batch."""
+    tracer = FakeTracer()
+    assert sync_remote_runnable.batch([1], config={"callbacks": [tracer]}) == [2]
+    assert len(tracer.runs) == 1
+    assert len(tracer.runs[0].child_runs) == 1
+    assert tracer.runs[0].child_runs[0].name == "add_one_or_passthrough"
+
+
 def test_batch(sync_remote_runnable: RemoteRunnable) -> None:
    """Test sync batch."""
    assert sync_remote_runnable.batch([]) == []
@@ -536,17 +563,9 @@ def test_batch(sync_remote_runnable: RemoteRunnable) -> None:
    tracer = FakeTracer()
    assert sync_remote_runnable.batch([1, 2], config={"callbacks": [tracer]}) == [2, 3]
    assert len(tracer.runs) == 2
-    # Light test to verify that we're picking up information about the server side
-    # function being invoked via a callback.
-    assert tracer.runs[0].child_runs[0].name == "RunnableLambda"
-    assert (
-        tracer.runs[0].child_runs[0].extra["kwargs"]["name"] == "add_one_or_passthrough"
-    )

-    assert tracer.runs[1].child_runs[0].name == "RunnableLambda"
-    assert (
-        tracer.runs[1].child_runs[0].extra["kwargs"]["name"] == "add_one_or_passthrough"
-    )
+    assert tracer.runs[0].child_runs[0].name == "add_one_or_passthrough"
+    assert tracer.runs[1].child_runs[0].name == "add_one_or_passthrough"

    # Verify that each tracer gets its own run
    tracer1 = FakeTracer()
@@ -558,17 +577,8 @@ def test_batch(sync_remote_runnable: RemoteRunnable) -> None:
    assert len(tracer2.runs) == 1
    # Light test to verify that we're picking up information about the server side
    # function being invoked via a callback.
-    assert tracer1.runs[0].child_runs[0].name == "RunnableLambda"
-    assert (
-        tracer1.runs[0].child_runs[0].extra["kwargs"]["name"]
-        == "add_one_or_passthrough"
-    )
-
-    assert tracer2.runs[0].child_runs[0].name == "RunnableLambda"
-    assert (
-        tracer2.runs[0].child_runs[0].extra["kwargs"]["name"]
-        == "add_one_or_passthrough"
-    )
+    assert tracer1.runs[0].child_runs[0].name == "add_one_or_passthrough"
+    assert tracer2.runs[0].child_runs[0].name == "add_one_or_passthrough"


 async def test_ainvoke(async_remote_runnable: RemoteRunnable) -> None:
@@ -601,10 +611,7 @@ async def test_ainvoke(async_remote_runnable: RemoteRunnable) -> None:
    elif sys.version_info < (3, 11):
        assert len(tracer.runs) == 1, "Failed for python < 3.11"
        remote_runnable = tracer.runs[0]
-        assert (
-            remote_runnable.child_runs[0].extra["kwargs"]["name"]
-            == "add_one_or_passthrough"
-        )
+        assert remote_runnable.name == "RemoteRunnable"
    else:
        raise AssertionError(f"Unsupported python version {sys.version_info}")

@@ -624,17 +631,9 @@ async def test_abatch(async_remote_runnable: RemoteRunnable) -> None:
        [1, 2], config={"callbacks": [tracer]}
    ) == [2, 3]
    assert len(tracer.runs) == 2
-    # Light test to verify that we're picking up information about the server side
-    # function being invoked via a callback.
-    assert tracer.runs[0].child_runs[0].name == "RunnableLambda"
-    assert (
-        tracer.runs[0].child_runs[0].extra["kwargs"]["name"] == "add_one_or_passthrough"
-    )

-    assert tracer.runs[1].child_runs[0].name == "RunnableLambda"
-    assert (
-        tracer.runs[1].child_runs[0].extra["kwargs"]["name"] == "add_one_or_passthrough"
-    )
+    assert tracer.runs[0].child_runs[0].name == "add_one_or_passthrough"
+    assert tracer.runs[1].child_runs[0].name == "add_one_or_passthrough"

    # Verify that each tracer gets its own run
    tracer1 = FakeTracer()
@@ -644,19 +643,9 @@ async def test_abatch(async_remote_runnable: RemoteRunnable) -> None:
    ) == [2, 3]
    assert len(tracer1.runs) == 1
    assert len(tracer2.runs) == 1
-    # Light test to verify that we're picking up information about the server side
-    # function being invoked via a callback.
-    assert tracer1.runs[0].child_runs[0].name == "RunnableLambda"
-    assert (
-        tracer1.runs[0].child_runs[0].extra["kwargs"]["name"]
-        == "add_one_or_passthrough"
-    )

-    assert tracer2.runs[0].child_runs[0].name == "RunnableLambda"
-    assert (
-        tracer2.runs[0].child_runs[0].extra["kwargs"]["name"]
-        == "add_one_or_passthrough"
-    )
+    assert tracer1.runs[0].child_runs[0].name == "add_one_or_passthrough"
+    assert tracer2.runs[0].child_runs[0].name == "add_one_or_passthrough"


 async def test_astream(async_remote_runnable: RemoteRunnable) -> None:
@@ -1128,6 +1117,156 @@ async def test_config_keys_validation(mocker: MockerFixture) -> None:
        assert config_seen["metadata"]["__langserve_endpoint"] == "invoke"


+async def test_include_callback_events(mocker: MockerFixture) -> None:
+    """This test should not use a RemoteRunnable.
+
+    Check if callback events are being sent back from the server.
+
+    Do so using the raw client.
+    """
+
+    async def add_one(x: int) -> int:
+        """Add one to simulate a valid function"""
+        return x + 1
+
+    server_runnable = RunnableLambda(func=add_one)
+
+    app = FastAPI()
+    add_routes(app, server_runnable, input_type=int, include_callback_events=True)
+    async with AsyncClient(
+        base_url="http://localhost:9999", transport=httpx.ASGITransport(app=app)
+    ) as async_client:
+        response = await async_client.post("/invoke", json={"input": 1})
+        # Config should be ignored but default debug information
+        # will still be added
+        assert response.status_code == 200
+        decoded_response = response.json()
+        # Remove any run_id from the response recursively
+        _null_run_id_and_metadata_recursively(decoded_response)
+        assert decoded_response == {
+            "callback_events": [
+                {
+                    "inputs": 1,
+                    "kwargs": {"name": "add_one", "run_type": None},
+                    "metadata": {
+                        "__langserve_endpoint": "invoke",
+                        "__langserve_version": None,
+                        "__useragent": "python-httpx/0.27.2",
+                    },
+                    "parent_run_id": None,
+                    "serialized": None,
+                    "run_id": None,
+                    "tags": [],
+                    "type": "on_chain_start",
+                },
+                {
+                    "kwargs": {},
+                    "outputs": 2,
+                    "metadata": None,
+                    "parent_run_id": None,
+                    "tags": [],
+                    "run_id": None,
+                    "type": "on_chain_end",
+                },
+            ],
+            "metadata": {
+                "feedback_tokens": [],
+                "run_id": None,
+            },
+            "output": 2,
+        }
+
+
+async def test_include_callback_events_batch() -> None:
+    """This test should not use a RemoteRunnable.
+
+    Check if callback events are being sent back from the server.
+
+    Do so using the raw client.
+    """
+
+    async def add_one(x: int) -> int:
+        """Add one to simulate a valid function"""
+        return x + 1
+
+    server_runnable = RunnableLambda(func=add_one)
+
+    app = FastAPI()
+    add_routes(app, server_runnable, input_type=int, include_callback_events=True)
+    async with AsyncClient(
+        base_url="http://localhost:9999", transport=httpx.ASGITransport(app=app)
+    ) as async_client:
+        response = await async_client.post("/batch", json={"inputs": [1, 2]})
+        # Config should be ignored but default debug information
+        # will still be added
+        assert response.status_code == 200
+        decoded_response = response.json()
+        # Remove any run_id from the response recursively
+        _null_run_id_and_metadata_recursively(decoded_response)
+        del decoded_response["metadata"]["run_ids"]
+        assert decoded_response == {
+            "callback_events": [
+                [
+                    {
+                        "inputs": 1,
+                        "kwargs": {"name": "add_one", "run_type": None},
+                        "metadata": {
+                            "__langserve_endpoint": "batch",
+                            "__langserve_version": None,
+                            "__useragent": "python-httpx/0.27.2",
+                        },
+                        "parent_run_id": None,
+                        "run_id": None,
+                        "serialized": None,
+                        "tags": [],
+                        "type": "on_chain_start",
+                    },
+                    {
+                        "kwargs": {},
+                        "outputs": 2,
+                        "parent_run_id": None,
+                        "metadata": None,
+                        "run_id": None,
+                        "tags": [],
+                        "type": "on_chain_end",
+                    },
+                ],
+                [
+                    {
+                        "inputs": 2,
+                        "kwargs": {"name": "add_one", "run_type": None},
+                        "metadata": {
+                            "__langserve_endpoint": "batch",
+                            "__langserve_version": None,
+                            "__useragent": "python-httpx/0.27.2",
+                        },
+                        "parent_run_id": None,
+                        "run_id": None,
+                        "serialized": None,
+                        "tags": [],
+                        "type": "on_chain_start",
+                    },
+                    {
+                        "kwargs": {},
+                        "outputs": 3,
+                        "parent_run_id": None,
+                        "metadata": None,
+                        "run_id": None,
+                        "tags": [],
+                        "type": "on_chain_end",
+                    },
+                ],
+            ],
+            "metadata": {
+                "responses": [
+                    {"feedback_tokens": [], "run_id": None},
+                    {"feedback_tokens": [], "run_id": None},
+                ],
+            },
+            "output": [2, 3],
+        }
+
+
 async def test_input_validation(mocker: MockerFixture) -> None:
    """Test client side and server side exceptions."""

@@ -2146,6 +2285,49 @@ async def test_uuid_serialization() -> None:
        )


+async def test_custom_serialization() -> None:
+    """Test updating the config based on the raw request object."""
+    from langserve.serialization import Serializer
+
+    class CustomObject:
+        def __init__(self, x: int) -> None:
+            self.x = x
+
+        def __eq__(self, other) -> bool:
+            return self.x == other.x
+
+    class CustomSerializer(Serializer):
+        def dumps(self, obj: Any) -> bytes:
+            """Dump the given object as a JSON string."""
+            if isinstance(obj, CustomObject):
+                return orjson.dumps({"x": obj.x})
+            else:
+                return orjson.dumps(obj)
+
+        def loadd(self, obj: Any) -> Any:
+            """Load the given object."""
+            if isinstance(obj, bytes):
+                obj = obj.decode("utf-8")
+            if obj.get("x"):
+                return CustomObject(x=obj["x"])
+            return obj
+
+    def foo(x: int) -> Any:
+        """Add one to simulate a valid function."""
+        return CustomObject(x=5)
+
+    app = FastAPI()
+    server_runnable = RunnableLambda(foo)
+    add_routes(app, server_runnable, serializer=CustomSerializer())
+
+    async with get_async_remote_runnable(
+        app, raise_app_exceptions=True, serializer=CustomSerializer()
+    ) as runnable:
+        result = await runnable.ainvoke(5)
+        assert isinstance(result, CustomObject)
+        assert result == CustomObject(x=5)
+
+
 async def test_endpoint_configurations() -> None:
    """Test enabling/disabling endpoints."""
    app = FastAPI()
@@ -2306,7 +2488,7 @@ async def test_astream_events_simple(async_remote_runnable: RemoteRunnable) -> N
        # test client side error
        with pytest.raises(httpx.HTTPStatusError) as cb:
            # Invalid input type (expected string but got int)
-            async for _ in runnable.astream_events("foo", version="v1"):
+            async for _ in runnable.astream_events("foo", version="v2"):
                pass

        # Verify that this is a 422 error
@@ -2315,7 +2497,7 @@ async def test_astream_events_simple(async_remote_runnable: RemoteRunnable) -> N
        with pytest.raises(httpx.HTTPStatusError) as cb:
            # Invalid input type (expected string but got int)
            # include names should not be a list of lists
-            async for _ in runnable.astream_events(1, include_names=[[]], version="v1"):
+            async for _ in runnable.astream_events(1, include_names=[[]], version="v2"):
                pass

        # Verify that this is a 422 error
@@ -2324,7 +2506,7 @@ async def test_astream_events_simple(async_remote_runnable: RemoteRunnable) -> N
        # Test good requests
        events = []

-        async for event in runnable.astream_events(1, version="v1"):
+        async for event in runnable.astream_events(1, version="v2"):
            events.append(event)

        # validate events
@@ -2337,6 +2519,7 @@ async def test_astream_events_simple(async_remote_runnable: RemoteRunnable) -> N
                assert not k.startswith("__")
            assert "metadata" in event
            del event["metadata"]
+            event["parent_ids"] = []

        assert events == [
            {
@@ -2416,6 +2599,7 @@ def _clean_up_events(events: List[Dict[str, Any]]) -> None:
            assert not k.startswith("__")
        assert "metadata" in event
        del event["metadata"]
+        event["parent_ids"] = []


 async def test_astream_events_with_serialization(
@@ -2488,7 +2672,7 @@ async def test_astream_events_with_serialization(
        app, raise_app_exceptions=False, path="/doc_types"
    ) as runnable:
        # Test good requests
-        events = [event async for event in runnable.astream_events("foo", version="v1")]
+        events = [event async for event in runnable.astream_events("foo", version="v2")]
        _clean_up_events(events)

        assert events == [
@@ -2578,7 +2762,7 @@ async def test_astream_events_with_serialization(
        app, raise_app_exceptions=False, path="/get_pets"
    ) as runnable:
        # Test good requests
-        events = [event async for event in runnable.astream_events("foo", version="v1")]
+        events = [event async for event in runnable.astream_events("foo", version="v2")]
        _clean_up_events(events)
        assert events == [
            {
@@ -2613,7 +2797,7 @@ async def test_astream_events_with_serialization(
    ) as runnable:
        # Test good requests
        with pytest.raises(httpx.HTTPStatusError) as cb:
-            async for event in runnable.astream_events("foo", version="v1"):
+            async for event in runnable.astream_events("foo", version="v2"):
                pass
        assert cb.value.response.status_code == 500

@@ -2641,7 +2825,7 @@ async def test_astream_events_with_prompt_model_parser_chain(
        events = [
            event
            async for event in runnable.astream_events(
-                {"question": "hello"}, version="v1"
+                {"question": "hello"}, version="v2"
            )
        ]
        _clean_up_events(events)
@@ -2850,25 +3034,16 @@ async def test_astream_events_with_prompt_model_parser_chain(
                        ]
                    },
                    "output": {
-                        "generations": [
-                            [
-                                {
-                                    "generation_info": None,
-                                    "message": {
-                                        "additional_kwargs": {},
-                                        "content": "Hello World!",
-                                        "name": None,
-                                        "response_metadata": {},
-                                        "type": "AIMessageChunk",
-                                    },
-                                    "text": "Hello World!",
-                                    "type": "ChatGenerationChunk",
-                                }
-                            ]
-                        ],
-                        "llm_output": None,
-                        "run": None,
-                        "type": "LLMResult",
+                        "additional_kwargs": {},
+                        "content": "Hello World!",
+                        "example": False,
+                        "invalid_tool_calls": [],
+                        "name": None,
+                        "response_metadata": {},
+                        "tool_call_chunks": [],
+                        "tool_calls": [],
+                        "type": "AIMessageChunk",
+                        "usage_metadata": None,
                    },
                },
                "event": "on_chat_model_end",
@@ -1,4 +1,4 @@
-from typing import Dict, List
+from typing import Any, Dict, List, Optional
 from uuid import UUID

 from langchain_core.tracers import BaseTracer
@@ -39,6 +39,34 @@ class FakeTracer(BaseTracer):
            }
        )

+    def _create_chain_run(
+        self,
+        serialized: Dict[str, Any],
+        inputs: Dict[str, Any],
+        run_id: UUID,
+        tags: Optional[List[str]] = None,
+        parent_run_id: Optional[UUID] = None,
+        metadata: Optional[Dict[str, Any]] = None,
+        run_type: Optional[str] = None,
+        name: Optional[str] = None,
+        **kwargs: Any,
+    ) -> Run:
+        if name is None:
+            # can't raise an exception from here, but can get a breakpoint
+            # import pdb; pdb.set_trace()
+            pass
+        return super()._create_chain_run(
+            serialized,
+            inputs,
+            run_id,
+            tags,
+            parent_run_id,
+            metadata,
+            run_type,
+            name,
+            **kwargs,
+        )
+
    def _persist_run(self, run: Run) -> None:
        """Persist a run."""
        self.runs.append(self._copy_run(run))
Author	SHA1	Message	Date
joaquin-borggio-lc	f0d86287ab	ci: drop python 3.8 (#825 )	2025-09-17 15:38:01 -04:00
joaquin-borggio-lc	168c9ff90e	chore: bump patch version (#823 ) bump patched version so i can release	2025-09-17 15:31:09 -04:00
joaquin-borggio-lc	a87125d0b8	chore: bump some package versions (#821 ) Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	2025-09-17 15:03:09 -04:00
Eugene Yurtsev	1de17fa799	Add new contributor to .clabot configuration (#822 )	2025-09-17 15:01:18 -04:00
ResearchAI	1a08f2740c	Update Chroma import to avoid deprecation warning. (#741 )	2025-07-09 17:19:18 -04:00
Yash Jivani	06c3c3691e	Update README.md Grammatical Errors (#733 )	2025-07-09 17:15:01 -04:00
Eugene Yurtsev	d20eab45f2	ci: add workflow dispatch to _release (#805 )	2024-12-26 21:37:14 -05:00
Eugene Yurtsev	321b7aa3b1	Release 0.3.1 (#801 )	2024-12-19 10:33:17 -05:00
Eugene Yurtsev	aa4aea4a81	lint (#803 )	2024-12-19 10:19:16 -05:00
Eugene Yurtsev	1aaec1189c	Update _lint.yml (#802 )	2024-12-18 22:10:43 -05:00
アリス	0d7601781d	update ssl verifying part to work with httpx 0.28.0 (#798 ) As the new httpx 0.28.0 removes VerifyTypes, we should update to follow their change See [issue](https://github.com/langchain-ai/langserve/issues/796) --------- Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	2024-12-18 22:08:58 -05:00
Eugene Yurtsev	0ad075fb67	Update .clabot (#800 )	2024-12-18 22:04:39 -05:00
Mingqi Hu	b007300b06	docs: Remove templates in readme (#792 ) docs: Remove templates in readme Issue: 404 when you click the [LangChain Templates](https://github.com/langchain-ai/langchain/blob/master/templates/README.md) in readme. As templates dir has been removed on latest langchain master. <img width="368" alt="image" src="https://github.com/user-attachments/assets/8dfa7e82-c6df-458c-ba42-2b9f0fd67d8d"> Fix: Just remove it to avoid 404 as example dirs is enough, look like (my local vs code) <img width="423" alt="image" src="https://github.com/user-attachments/assets/b65fc053-ed62-47e4-8404-fbfbcb4b17d5"> Signed-off-by: Mingqi <mingqi.hu@intel.com> Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	2024-11-22 10:21:02 -05:00
Eugene Yurtsev	9df7e88bb9	Update .clabot (#793 )	2024-11-22 10:20:11 -05:00
Eugene Yurtsev	c626cde08c	Update MIGRATION.md (#789 )	2024-11-18 11:06:37 -05:00
ccurme	c4a8925b00	docs: update local link in readme (#788 ) LangChain doc builds are currently [broken](https://vercel.com/langchain/langchain/ExxE3a6SSZVa7RSRUDB3mzHDpsvV?filter=errors). - LangChain docs page hosts LangServe readme: https://python.langchain.com/docs/langserve/; - The readme is [downloaded from github](https://github.com/langchain-ai/langchain/blob/22a8652eccd9023cd41ea0f6924575ce87c28756/docs/Makefile#L49) when docs are built; - A [script](https://github.com/langchain-ai/langchain/blob/master/docs/scripts/resolve_local_links.py) resolves local links in the readme to point to the LangServe github. This script assumes local links are prefixed with `./`	2024-11-18 11:05:19 -05:00
Eugene Yurtsev	80f949b62e	migration guide (#787 )	2024-11-16 22:36:31 -05:00
Eugene Yurtsev	c27923a7d1	Update README.md (#773 )	2024-09-18 13:33:52 -04:00
Eugene Yurtsev	f3b9c43106	Update README.md (#771 )	2024-09-16 13:22:26 -04:00
Eugene Yurtsev	6b1a0d97ef	Update README (#769 )	2024-09-16 11:56:41 -04:00
Eugene Yurtsev	dc04672537	examples: update clients (#768 )	2024-09-14 14:32:41 -04:00
Eugene Yurtsev	42b61a664b	v0.3 release (#767 )	2024-09-14 14:14:45 -04:00
Eugene Yurtsev	1e24edce08	Add ability to specify custom serializer (#764 ) Allow users to define a custom serializer	2024-09-14 14:06:08 -04:00
Eugene Yurtsev	c747e20c1e	Fix issue with callback events sent from server (#765 ) This properly propagates the name of the runs from the server to the client if one enables callbacks.	2024-09-14 13:46:10 -04:00
Eugene Yurtsev	8b4d8dff6c	propagate astream events from add_route (#763 ) Propagate the parameter to APIHandler	2024-09-12 17:02:35 -04:00
Eugene Yurtsev	2c957bdd78	mark include callback events as a beta api (#761 )	2024-09-12 14:58:33 -04:00
Eugene Yurtsev	36f945e494	improve error messages when models fail to hash (#762 )	2024-09-12 14:58:25 -04:00
Eugene Yurtsev	43683b3671	add ability to control version of astream events API (#760 ) add ability to control version of astream events API server side	2024-09-12 14:33:21 -04:00