Commit Graph

3 Commits

Author SHA1 Message Date
Bagatur
a0c2281540
infra: update mypy 1.10, ruff 0.5 (#23721)
```python
"""python scripts/update_mypy_ruff.py"""
import glob
import tomllib
from pathlib import Path

import toml
import subprocess
import re

ROOT_DIR = Path(__file__).parents[1]


def main():
    for path in glob.glob(str(ROOT_DIR / "libs/**/pyproject.toml"), recursive=True):
        print(path)
        with open(path, "rb") as f:
            pyproject = tomllib.load(f)
        try:
            pyproject["tool"]["poetry"]["group"]["typing"]["dependencies"]["mypy"] = (
                "^1.10"
            )
            pyproject["tool"]["poetry"]["group"]["lint"]["dependencies"]["ruff"] = (
                "^0.5"
            )
        except KeyError:
            continue
        with open(path, "w") as f:
            toml.dump(pyproject, f)
        cwd = "/".join(path.split("/")[:-1])
        completed = subprocess.run(
            "poetry lock --no-update; poetry install --with typing; poetry run mypy . --no-color",
            cwd=cwd,
            shell=True,
            capture_output=True,
            text=True,
        )
        logs = completed.stdout.split("\n")

        to_ignore = {}
        for l in logs:
            if re.match("^(.*)\:(\d+)\: error:.*\[(.*)\]", l):
                path, line_no, error_type = re.match(
                    "^(.*)\:(\d+)\: error:.*\[(.*)\]", l
                ).groups()
                if (path, line_no) in to_ignore:
                    to_ignore[(path, line_no)].append(error_type)
                else:
                    to_ignore[(path, line_no)] = [error_type]
        print(len(to_ignore))
        for (error_path, line_no), error_types in to_ignore.items():
            all_errors = ", ".join(error_types)
            full_path = f"{cwd}/{error_path}"
            try:
                with open(full_path, "r") as f:
                    file_lines = f.readlines()
            except FileNotFoundError:
                continue
            file_lines[int(line_no) - 1] = (
                file_lines[int(line_no) - 1][:-1] + f"  # type: ignore[{all_errors}]\n"
            )
            with open(full_path, "w") as f:
                f.write("".join(file_lines))

        subprocess.run(
            "poetry run ruff format .; poetry run ruff --select I --fix .",
            cwd=cwd,
            shell=True,
            capture_output=True,
            text=True,
        )


if __name__ == "__main__":
    main()

```
2024-07-03 10:33:27 -07:00
tianzedavid
5a8909440b
docs: remove repetitive words (#21058)
remove repetitive words

Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
2024-05-01 01:10:42 +00:00
Jan Chorowski
b8b42ccbc5
community[minor]: Pathway vectorstore(#14859)
- **Description:** Integration with pathway.com data processing pipeline
acting as an always updated vectorstore
  - **Issue:** not applicable
- **Dependencies:** optional dependency on
[`pathway`](https://pypi.org/project/pathway/)
  - **Twitter handle:** pathway_com

The PR provides and integration with `pathway` to provide an easy to use
always updated vector store:

```python
import pathway as pw
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.text_splitter import CharacterTextSplitter
from langchain.vectorstores import PathwayVectorClient, PathwayVectorServer

data_sources = []
data_sources.append(
    pw.io.gdrive.read(object_id="17H4YpBOAKQzEJ93xmC2z170l0bP2npMy", service_user_credentials_file="credentials.json", with_metadata=True))

text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
embeddings_model = OpenAIEmbeddings(openai_api_key=os.environ["OPENAI_API_KEY"])
vector_server = PathwayVectorServer(
    *data_sources,
    embedder=embeddings_model,
    splitter=text_splitter,
)
vector_server.run_server(host="127.0.0.1", port="8765", threaded=True, with_cache=False)
client = PathwayVectorClient(
    host="127.0.0.1",
    port="8765",
)
query = "What is Pathway?"
docs = client.similarity_search(query)
```

The `PathwayVectorServer` builds a data processing pipeline which
continusly scans documents in a given source connector (google drive,
s3, ...) and builds a vector store. The `PathwayVectorClient` implements
LangChain's `VectorStore` interface and connects to the server to
retrieve documents.

---------

Co-authored-by: Mateusz Lewandowski <lewymati@users.noreply.github.com>
Co-authored-by: mlewandowski <mlewandowski@MacBook-Pro-mlewandowski.local>
Co-authored-by: Berke <berkecanrizai1@gmail.com>
Co-authored-by: Adrian Kosowski <adrian@pathway.com>
Co-authored-by: mlewandowski <mlewandowski@macbook-pro-mlewandowski.home>
Co-authored-by: berkecanrizai <63911408+berkecanrizai@users.noreply.github.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: mlewandowski <mlewandowski@MBPmlewandowski.ht.home>
Co-authored-by: Szymon Dudycz <szymond@pathway.com>
Co-authored-by: Szymon Dudycz <szymon.dudycz@gmail.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
2024-03-29 10:50:39 -07:00