Merge branch 'langchain-ai:master' into master

.github/actions/poetry_setup/action.yml

@@ -31,20 +31,20 @@ runs:
       with:
         python-version: ${{ inputs.python-version }}
 
-    - uses: actions/cache@v3
-      id: cache-bin-poetry
-      name: Cache Poetry binary - Python ${{ inputs.python-version }}
-      env:
-        SEGMENT_DOWNLOAD_TIMEOUT_MIN: "1"
-      with:
-        path: |
-          /opt/pipx/venvs/poetry
-          /opt/pipx_bin/poetry
-        # This step caches the poetry installation, so make sure it's keyed on the poetry version as well.
-        key: bin-poetry-${{ runner.os }}-${{ runner.arch }}-py-${{ inputs.python-version }}-${{ inputs.poetry-version }}
+    # - uses: actions/cache@v3
+    #   id: cache-bin-poetry
+    #   name: Cache Poetry binary - Python ${{ inputs.python-version }}
+    #   env:
+    #     SEGMENT_DOWNLOAD_TIMEOUT_MIN: "1"
+    #   with:
+    #     path: |
+    #       /opt/pipx/venvs/poetry
+    #       /opt/pipx_bin/poetry
+    #     # This step caches the poetry installation, so make sure it's keyed on the poetry version as well.
+    #     key: bin-poetry-${{ runner.os }}-${{ runner.arch }}-py-${{ inputs.python-version }}-${{ inputs.poetry-version }}
 
     - name: Install poetry
-      if: steps.cache-bin-poetry.outputs.cache-hit != 'true'
+      # if: steps.cache-bin-poetry.outputs.cache-hit != 'true'
       shell: bash
       env:
         POETRY_VERSION: ${{ inputs.poetry-version }}

libs/langchain/langchain/document_loaders/async_html.py

@@ -1,7 +1,8 @@
 import asyncio
 import logging
 import warnings
-from typing import Any, Dict, Iterator, List, Optional, Union
+from concurrent.futures import ThreadPoolExecutor
+from typing import Any, Dict, Iterator, List, Optional, Union, cast
 
 import aiohttp
 import requests
@@ -129,9 +130,18 @@ def lazy_load(self) -> Iterator[Document]:
     def load(self) -> List[Document]:
         """Load text from the url(s) in web_path."""
 
-        results = asyncio.run(self.fetch_all(self.web_paths))
+        try:
+            # Raises RuntimeError if there is no current event loop.
+            asyncio.get_running_loop()
+            # If there is a current event loop, we need to run the async code
+            # in a separate loop, in a separate thread.
+            with ThreadPoolExecutor(max_workers=1) as executor:
+                future = executor.submit(asyncio.run, self.fetch_all(self.web_paths))
+                results = future.result()
+        except RuntimeError:
+            results = asyncio.run(self.fetch_all(self.web_paths))
         docs = []
-        for i, text in enumerate(results):
+        for i, text in enumerate(cast(List[str], results)):
             metadata = {"source": self.web_paths[i]}
             docs.append(Document(page_content=text, metadata=metadata))
 

libs/langchain/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "langchain"
-version = "0.0.281"
+version = "0.0.282"
 description = "Building applications with LLMs through composability"
 authors = []
 license = "MIT"