langchain-ai/langchain-pinecone
1
0
Fork 0
mirror of https://github.com/langchain-ai/langchain-pinecone.git synced 2026-07-16 09:24:24 -04:00
Code Issues 11 Packages Projects Releases 10 Wiki Activity

langchain-pinecone 0.2.0 doesn't support Python 3.13 #1

New Issue
Closed
opened 2026-02-16 07:15:55 -05:00 by yindo · 7 comments
yindo commented 2026-02-16 07:15:55 -05:00
Owner
Copy Link
Copy Source

Originally created by @guidev on GitHub (Nov 16, 2024).

Checked other resources

  • I added a very descriptive title to this issue.
  • I searched the 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 LangChain rather than my code.
  • The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).

Example Code

--

Error Message and Stack Trace (if applicable)

No response

Description

The current langchain-pinecone package (v0.2.0) depends on pinecone-client version ^5.0.0. However, the latest release in the 5.0.x series is 5.0.1, which was last updated on August 1, 2024, and does not support Python 3.13.

The most recent version of pinecone on PyPI is 5.4.0, released on November 13, 2024, and it includes support for Python 3.13.

Updating the dependency in langchain-pinecone to use pinecone version ^5.4.0 or newer would enable compatibility with Python 3.13 and ensure access to the latest features and improvements in the pinecone sdk.

https://pypi.org/project/pinecone/
https://pypi.org/project/pinecone-client/

System Info

System Information

OS: Darwin
OS Version: Darwin Kernel Version 24.1.0: Thu Oct 10 21:05:14 PDT 2024; root:xnu-11215.41.3~2/RELEASE_ARM64_T8103
Python Version: 3.12.0 (v3.12.0:0fb18b02c8, Oct 2 2023, 09:45:56) [Clang 13.0.0 (clang-1300.0.29.30)]

Package Information

langchain_core: 0.3.19
langchain: 0.3.7
langchain_community: 0.3.7
langsmith: 0.1.143
langchain_experimental: 0.3.3
langchain_openai: 0.2.8
langchain_pinecone: 0.2.0
langchain_text_splitters: 0.3.2

Optional packages not installed

langgraph
langserve

Other Dependencies

aiohttp: 3.9.5
async-timeout: Installed. No version info available.
dataclasses-json: 0.6.7
httpx: 0.27.2
httpx-sse: 0.4.0
jsonpatch: 1.33
numpy: 1.26.4
openai: 1.54.4
orjson: 3.10.11
packaging: 24.2
pinecone-client: 5.0.1
pydantic: 2.9.2
pydantic-settings: 2.6.1
PyYAML: 6.0.2
requests: 2.32.3
requests-toolbelt: 1.0.0
SQLAlchemy: 2.0.35
tenacity: 9.0.0
tiktoken: 0.8.0
typing-extensions: 4.12.2

Originally created by @guidev on GitHub (Nov 16, 2024). ### Checked other resources - [X] I added a very descriptive title to this issue. - [X] I searched the LangChain documentation with the integrated search. - [X] I used the GitHub search to find a similar question and didn't find it. - [X] I am sure that this is a bug in LangChain rather than my code. - [X] The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package). ### Example Code -- ### Error Message and Stack Trace (if applicable) _No response_ ### Description The current `langchain-pinecone` package (`v0.2.0`) depends on pinecone-client version `^5.0.0`. However, the latest release in the `5.0.x` series is `5.0.1`, which was last updated on **August 1, 2024**, and does not support Python 3.13. The most recent version of `pinecone` on PyPI is `5.4.0`, released on **November 13, 2024**, and it includes support for Python 3.13. Updating the dependency in `langchain-pinecone` to use `pinecone` version `^5.4.0` or newer would enable compatibility with Python 3.13 and ensure access to the latest features and improvements in the pinecone sdk. https://pypi.org/project/pinecone/ https://pypi.org/project/pinecone-client/ ### System Info System Information ------------------ > OS: Darwin > OS Version: Darwin Kernel Version 24.1.0: Thu Oct 10 21:05:14 PDT 2024; root:xnu-11215.41.3~2/RELEASE_ARM64_T8103 > Python Version: 3.12.0 (v3.12.0:0fb18b02c8, Oct 2 2023, 09:45:56) [Clang 13.0.0 (clang-1300.0.29.30)] Package Information ------------------- > langchain_core: 0.3.19 > langchain: 0.3.7 > langchain_community: 0.3.7 > langsmith: 0.1.143 > langchain_experimental: 0.3.3 > langchain_openai: 0.2.8 > langchain_pinecone: 0.2.0 > langchain_text_splitters: 0.3.2 Optional packages not installed ------------------------------- > langgraph > langserve Other Dependencies ------------------ > aiohttp: 3.9.5 > async-timeout: Installed. No version info available. > dataclasses-json: 0.6.7 > httpx: 0.27.2 > httpx-sse: 0.4.0 > jsonpatch: 1.33 > numpy: 1.26.4 > openai: 1.54.4 > orjson: 3.10.11 > packaging: 24.2 > pinecone-client: 5.0.1 > pydantic: 2.9.2 > pydantic-settings: 2.6.1 > PyYAML: 6.0.2 > requests: 2.32.3 > requests-toolbelt: 1.0.0 > SQLAlchemy: 2.0.35 > tenacity: 9.0.0 > tiktoken: 0.8.0 > typing-extensions: 4.12.2
yindo closed this issue 2026-02-16 07:15:55 -05:00
yindo commented 2026-02-16 07:15:56 -05:00
Author
Owner
Copy Link
Copy Source

@keenranger commented on GitHub (Nov 19, 2024):

Not only does the pinecone-client version not support Python 3.13, but aiohttp==3.9.5 doesn’t either. (aiohttp starts to support Python 3.13 since 3.10.6). It seems like more adjustments will be necessary.

@keenranger commented on GitHub (Nov 19, 2024): Not only does the `pinecone-client` version not support Python 3.13, but [aiohttp==3.9.5](https://pypi.org/project/aiohttp/3.9.5/) doesn’t either. (`aiohttp` starts to support Python 3.13 since [3.10.6](https://pypi.org/project/aiohttp/3.10.6/)). It seems like more adjustments will be necessary.
yindo commented 2026-02-16 07:15:56 -05:00
Author
Owner
Copy Link
Copy Source

@Jacky3003 commented on GitHub (Nov 19, 2024):

To Add, the following code snippet from the tests doesn't work with aiohttp==3.11.2 which is the latest version:

from langchain_pinecone import PineconeEmbeddings

API_KEY = "some-api-key"
MODEL_NAME = "multilingual-e5-large"

e = PineconeEmbeddings(
    pinecone_api_key=API_KEY,  # type: ignore[call-arg]
    model=MODEL_NAME,
)

The following output is seen below:

langchain_pinecone/embeddings.py:97: in validate_environment
    self._async_client = aiohttp.ClientSession(
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _

self = <aiohttp.client.ClientSession object at 0x75328c34bf10>, base_url = None

    def __init__(
        self,
        base_url: Optional[StrOrURL] = None,
        *,
        connector: Optional[BaseConnector] = None,
        loop: Optional[asyncio.AbstractEventLoop] = None,
        cookies: Optional[LooseCookies] = None,
        headers: Optional[LooseHeaders] = None,
        proxy: Optional[StrOrURL] = None,
        proxy_auth: Optional[BasicAuth] = None,
        skip_auto_headers: Optional[Iterable[str]] = None,
        auth: Optional[BasicAuth] = None,
        json_serialize: JSONEncoder = json.dumps,
        request_class: Type[ClientRequest] = ClientRequest,
        response_class: Type[ClientResponse] = ClientResponse,
        ws_response_class: Type[ClientWebSocketResponse] = ClientWebSocketResponse,
        version: HttpVersion = http.HttpVersion11,
        cookie_jar: Optional[AbstractCookieJar] = None,
        connector_owner: bool = True,
        raise_for_status: Union[
            bool, Callable[[ClientResponse], Awaitable[None]]
        ] = False,
        read_timeout: Union[float, _SENTINEL] = sentinel,
        conn_timeout: Optional[float] = None,
        timeout: Union[object, ClientTimeout] = sentinel,
        auto_decompress: bool = True,
        trust_env: bool = False,
        requote_redirect_url: bool = True,
        trace_configs: Optional[List[TraceConfig]] = None,
        read_bufsize: int = 2**16,
        max_line_size: int = 8190,
        max_field_size: int = 8190,
        fallback_charset_resolver: _CharsetResolver = lambda r, b: "utf-8",
    ) -> None:
        # We initialise _connector to None immediately, as it's referenced in __del__()
        # and could cause issues if an exception occurs during initialisation.
        self._connector: Optional[BaseConnector] = None
    
        if loop is None:
            if connector is not None:
                loop = connector._loop
    
>       loop = loop or asyncio.get_running_loop()
E       RuntimeError: no running event loop

/home/vscode/langchain-py-env/lib/python3.11/site-packages/aiohttp/client.py:310: RuntimeError

This was specifically for the embeddings component, but could be part of the other components as well. See system information below:

System Information

OS: Linux
OS Version: langchain-ai/langchain#48~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Mon Oct 7 11:24:13 UTC 2
Python Version: 3.11.4 (main, Jun 7 2023, 18:32:58) [GCC 10.2.1 20210110]

Package Information

langchain_core: 0.3.12
langchain: 0.3.4
langchain_community: 0.3.3
langsmith: 0.1.132
langchain_pinecone: 0.2.0
langchain_standard_tests: 0.1.1
langchain_text_splitters: 0.3.0

Optional packages not installed

langgraph
langserve

Other Dependencies

aiohttp: 3.11.2
async-timeout: Installed. No version info available.
dataclasses-json: 0.6.7
httpx: 0.27.2
jsonpatch: 1.33
numpy: 1.26.4
orjson: 3.10.7
packaging: 24.1
pinecone-client: 5.0.0
pydantic: 2.9.2
pydantic-settings: 2.5.2
pytest: 7.4.4
PyYAML: 6.0.2
requests: 2.32.3
requests-toolbelt: 1.0.0
SQLAlchemy: 2.0.35
syrupy: 4.7.2
tenacity: 9.0.0
typing-extensions: 4.12.2

@Jacky3003 commented on GitHub (Nov 19, 2024): To Add, the following code snippet from the tests doesn't work with `aiohttp==3.11.2` which is the latest version: ```python from langchain_pinecone import PineconeEmbeddings API_KEY = "some-api-key" MODEL_NAME = "multilingual-e5-large" e = PineconeEmbeddings( pinecone_api_key=API_KEY, # type: ignore[call-arg] model=MODEL_NAME, ) ``` The following output is seen below: ``` langchain_pinecone/embeddings.py:97: in validate_environment self._async_client = aiohttp.ClientSession( _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ self = <aiohttp.client.ClientSession object at 0x75328c34bf10>, base_url = None def __init__( self, base_url: Optional[StrOrURL] = None, *, connector: Optional[BaseConnector] = None, loop: Optional[asyncio.AbstractEventLoop] = None, cookies: Optional[LooseCookies] = None, headers: Optional[LooseHeaders] = None, proxy: Optional[StrOrURL] = None, proxy_auth: Optional[BasicAuth] = None, skip_auto_headers: Optional[Iterable[str]] = None, auth: Optional[BasicAuth] = None, json_serialize: JSONEncoder = json.dumps, request_class: Type[ClientRequest] = ClientRequest, response_class: Type[ClientResponse] = ClientResponse, ws_response_class: Type[ClientWebSocketResponse] = ClientWebSocketResponse, version: HttpVersion = http.HttpVersion11, cookie_jar: Optional[AbstractCookieJar] = None, connector_owner: bool = True, raise_for_status: Union[ bool, Callable[[ClientResponse], Awaitable[None]] ] = False, read_timeout: Union[float, _SENTINEL] = sentinel, conn_timeout: Optional[float] = None, timeout: Union[object, ClientTimeout] = sentinel, auto_decompress: bool = True, trust_env: bool = False, requote_redirect_url: bool = True, trace_configs: Optional[List[TraceConfig]] = None, read_bufsize: int = 2**16, max_line_size: int = 8190, max_field_size: int = 8190, fallback_charset_resolver: _CharsetResolver = lambda r, b: "utf-8", ) -> None: # We initialise _connector to None immediately, as it's referenced in __del__() # and could cause issues if an exception occurs during initialisation. self._connector: Optional[BaseConnector] = None if loop is None: if connector is not None: loop = connector._loop > loop = loop or asyncio.get_running_loop() E RuntimeError: no running event loop /home/vscode/langchain-py-env/lib/python3.11/site-packages/aiohttp/client.py:310: RuntimeError ``` This was specifically for the embeddings component, but could be part of the other components as well. See system information below: System Information ------------------ > OS: Linux > OS Version: langchain-ai/langchain#48~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Mon Oct 7 11:24:13 UTC 2 > Python Version: 3.11.4 (main, Jun 7 2023, 18:32:58) [GCC 10.2.1 20210110] Package Information ------------------- > langchain_core: 0.3.12 > langchain: 0.3.4 > langchain_community: 0.3.3 > langsmith: 0.1.132 > langchain_pinecone: 0.2.0 > langchain_standard_tests: 0.1.1 > langchain_text_splitters: 0.3.0 Optional packages not installed ------------------------------- > langgraph > langserve Other Dependencies ------------------ > aiohttp: 3.11.2 > async-timeout: Installed. No version info available. > dataclasses-json: 0.6.7 > httpx: 0.27.2 > jsonpatch: 1.33 > numpy: 1.26.4 > orjson: 3.10.7 > packaging: 24.1 > pinecone-client: 5.0.0 > pydantic: 2.9.2 > pydantic-settings: 2.5.2 > pytest: 7.4.4 > PyYAML: 6.0.2 > requests: 2.32.3 > requests-toolbelt: 1.0.0 > SQLAlchemy: 2.0.35 > syrupy: 4.7.2 > tenacity: 9.0.0 > typing-extensions: 4.12.2
yindo commented 2026-02-16 07:15:56 -05:00
Author
Owner
Copy Link
Copy Source

@Lwhieldon commented on GitHub (Mar 10, 2025):

Any updates on when langchain-pinecone will be compatible with python 313?

@Lwhieldon commented on GitHub (Mar 10, 2025): Any updates on when langchain-pinecone will be compatible with python 313?
yindo commented 2026-02-16 07:15:56 -05:00
Author
Owner
Copy Link
Copy Source

@OperKH commented on GitHub (Mar 12, 2025):

So, starting with langchain-pinecone==0.2.3 it supports python 3.13 langchain-ai/langchain#29737. But depends on numpy<2.0.0,>=1.26.4 and numpy==1.26.4 doesn't support python 3.13 and numpy==2.2.3 can't be installed 😔

@OperKH commented on GitHub (Mar 12, 2025): So, starting with `langchain-pinecone==0.2.3` it supports python 3.13 langchain-ai/langchain#29737. But depends on `numpy<2.0.0,>=1.26.4` and `numpy==1.26.4` doesn't support python 3.13 and `numpy==2.2.3` can't be installed 😔
yindo commented 2026-02-16 07:15:56 -05:00
Author
Owner
Copy Link
Copy Source

@spoletum commented on GitHub (Apr 1, 2025):

One must really love Python.

@spoletum commented on GitHub (Apr 1, 2025): One must really love Python.
yindo commented 2026-02-16 07:15:56 -05:00
Author
Owner
Copy Link
Copy Source

@dosubot[bot] commented on GitHub (Jul 1, 2025):

Hi, @guidev. I'm Dosu, and I'm helping the LangChain team manage their backlog. I'm marking this issue as stale.

Issue Summary:

  • Original issue: langchain-pinecone version 0.2.0 is incompatible with Python 3.13 due to pinecone-client dependency.
  • Suggested update: Move to pinecone version ^5.4.0 or newer for compatibility.
  • Additional concerns: aiohttp==3.9.5 and aiohttp==3.11.2 have compatibility issues with Python 3.13.
  • Dependency conflict: langchain-pinecone==0.2.3 supports Python 3.13 but conflicts with numpy.
  • Community engagement: Various users have reported issues and inquiries about compatibility updates.

Next Steps:

  • Please confirm if this issue is still relevant to the latest version of the LangChain repository by commenting here.
  • If no updates are provided, this issue will be automatically closed in 7 days.

Thank you for your understanding and contribution!

@dosubot[bot] commented on GitHub (Jul 1, 2025): Hi, @guidev. I'm [Dosu](https://dosu.dev), and I'm helping the LangChain team manage their backlog. I'm marking this issue as stale. **Issue Summary:** - Original issue: `langchain-pinecone` version 0.2.0 is incompatible with Python 3.13 due to `pinecone-client` dependency. - Suggested update: Move to `pinecone` version `^5.4.0` or newer for compatibility. - Additional concerns: `aiohttp==3.9.5` and `aiohttp==3.11.2` have compatibility issues with Python 3.13. - Dependency conflict: `langchain-pinecone==0.2.3` supports Python 3.13 but conflicts with `numpy`. - Community engagement: Various users have reported issues and inquiries about compatibility updates. **Next Steps:** - Please confirm if this issue is still relevant to the latest version of the LangChain repository by commenting here. - If no updates are provided, this issue will be automatically closed in 7 days. Thank you for your understanding and contribution!
yindo commented 2026-02-16 07:15:56 -05:00
Author
Owner
Copy Link
Copy Source

@hagen00 commented on GitHub (Oct 8, 2025):

I'm using python 3.13. Working fine for me.

@hagen00 commented on GitHub (Oct 8, 2025): I'm using python 3.13. Working fine for me.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
enhancement
enhancement
pull-request
Mirrored from GitHub Pull Request
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langchain-ai/langchain-pinecone#1
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?