Websocket implementation

[moghadas76]

Checked other resources

• I added a very descriptive title to this issue.
• I searched the LangGraph/LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.
• I am sure that this is a bug in LangGraph/LangChain rather than my code.
• I am sure this is better as an issue rather than a GitHub discussion, since this is a LangGraph bug and not a design question.

Example Code

def stream(
        self, path: str, method: str, *, json: Optional[dict] = None
    ) -> Iterator[StreamPart]:
        """Stream the results of a request using SSE."""
        headers, content = encode_json(json)
        with httpx_sse.connect_sse(
            self.client, method, path, headers=headers, content=content
        ) as sse:
            try:
                sse.response.raise_for_status()
            except httpx.HTTPStatusError as e:
                body = sse.response.read().decode()
                if sys.version_info >= (3, 11):
                    e.add_note(body)
                else:
                    logger.error(f"Error from langgraph-api: {body}", exc_info=e)
                raise e
            for event in sse.iter_sse():
                yield StreamPart(
                    event.event, orjson.loads(event.data) if event.data else None
                )

Error Message and Stack Trace (if applicable)

I want support websocket as well

Description

I want support websocket as well

System Info

scikit-image==0.22.0
scikit-learn==1.3.2
scipy==1.10.1
seaborn==0.13.0
Send2Trash==1.8.2
sentry-sdk==1.36.0
setproctitle==1.3.3
shap==0.46.0
shellingham==1.5.4
six @ file:///home/conda/feedstock_root/build_artifacts/six_1620240208055/work
slicer==0.0.8
smmap==5.0.1
sniffio==1.3.0
soupsieve==2.5
SQLAlchemy==2.0.23
sqlparse==0.4.4
stack-data==0.6.3
starlette==0.37.2
statsmodels==0.14.0
sympy @ file:///work/ci_py311_2/sympy_1679339311852/work
tables==3.9.1
tabulate==0.9.0
tenacity==8.2.3
tensorboard==2.17.0
tensorboard-data-server==0.7.1
tensorflow-estimator==2.15.0
tensorflow-io-gcs-filesystem==0.34.0
termcolor==2.3.0
terminado==0.18.1
threadpoolctl==3.2.0
tifffile==2023.9.26
time-machine==2.14.1
timm==0.9.7
tinycss2==1.2.1
tokenizers==0.19.1
tomlkit==0.12.3
toolz==0.12.1
torch==2.3.0
torch-summary==1.4.5
torch_cluster==1.6.3+pt23cu121
torch_geometric==2.4.0
torch_scatter==2.1.2+pt23cu121
torch_sparse==0.6.18+pt23cu121
torch_spline_conv==1.2.2+pt23cu121
torchaudio==2.3.0
torchinfo==1.8.0
torchmetrics==1.3.0.post0
torchsummary==1.5.1
torchvision==0.18.0
tornado @ file:///croot/tornado_1696936946304/work
tqdm==4.66.1
traitlets==5.9.0
transformers==4.44.2
triton==2.3.0
typed-argument-parser==1.7.2
typer==0.12.3
types-python-dateutil==2.9.0.20240316
typing-inspect==0.9.0
typing_extensions==4.8.0
tzdata==2023.3
ujson==5.10.0
uri-template==1.3.0
urllib3==2.2.2
uvicorn==0.25.0
uvloop==0.19.0
wandb==0.17.6
watchfiles==0.22.0
wcwidth @ file:///home/conda/feedstock_root/build_artifacts/wcwidth_1704731205417/work
webcolors==1.13
webencodings==0.5.1
websocket-client==1.7.0
websockets==12.0
Werkzeug==3.0.0
wrapt==1.14.1
xgboost==2.0.3
xxhash==3.4.1
yarl==1.9.4

[vbarda]

@moghadas76 we don't currently plan to support websockets in LangGraph Cloud. could you say more about your use case / why you need websocket support?