Merge branch 'run-llama:main' into main

docs/pyproject.toml

@@ -44,7 +44,7 @@ idna = "3.7"
 ipykernel = "6.29.3"
 ipython = "8.22.2"
 jedi = "0.19.1"
-jinja2 = "3.1.4"
+jinja2 = "^3.1.5"
 jsonschema = "4.21.1"
 jsonschema-specifications = "2023.12.1"
 jupyter-client = "8.6.1"

llama-index-integrations/llms/llama-index-llms-bedrock-converse/llama_index/llms/bedrock_converse/utils.py

@@ -337,12 +337,7 @@ def converse_with_retry(
         {
             k: v
             for k, v in kwargs.items()
-            if (
-                k != "tools"
-                or k != "guardrail_identifier"
-                or k != "guardrail_version"
-                or k != "trace"
-            )
+            if k not in ["tools", "guardrail_identifier", "guardrail_version", "trace"]
         },
     )
 
@@ -395,12 +390,7 @@ async def converse_with_retry_async(
         {
             k: v
             for k, v in kwargs.items()
-            if (
-                k != "tools"
-                or k != "guardrail_identifier"
-                or k != "guardrail_version"
-                or k != "trace"
-            )
+            if k not in ["tools", "guardrail_identifier", "guardrail_version", "trace"]
         },
     )
 

llama-index-integrations/llms/llama-index-llms-bedrock-converse/pyproject.toml

@@ -27,7 +27,7 @@ exclude = ["**/BUILD"]
 license = "MIT"
 name = "llama-index-llms-bedrock-converse"
 readme = "README.md"
-version = "0.4.2"
+version = "0.4.3"
 
 [tool.poetry.dependencies]
 python = ">=3.9,<4.0"

llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/knowledge_base/base.py

@@ -5,7 +5,8 @@
 
 
 class KnowledgeBaseWebReader(BaseReader):
-    """Knowledge base reader.
+    """
+    Knowledge base reader.
 
     Crawls and reads articles from a knowledge base/help center with Playwright.
     Tested on Zendesk and Intercom CMS, may work on others.
@@ -36,6 +37,7 @@ def __init__(
         title_selector: Optional[str] = None,
         subtitle_selector: Optional[str] = None,
         body_selector: Optional[str] = None,
+        max_depth: int = 100,
     ) -> None:
         """Initialize with parameters."""
         self.root_url = root_url
@@ -44,6 +46,7 @@ def __init__(
         self.title_selector = title_selector
         self.subtitle_selector = subtitle_selector
         self.body_selector = body_selector
+        self.max_depth = max_depth
 
     def load_data(self) -> List[Document]:
         """Load data from the knowledge base."""
@@ -54,9 +57,7 @@ def load_data(self) -> List[Document]:
 
             # Crawl
             article_urls = self.get_article_urls(
-                browser,
-                self.root_url,
-                self.root_url,
+                browser, self.root_url, self.root_url, self.max_depth
             )
 
             # Scrape
@@ -82,7 +83,8 @@ def scrape_article(
         browser: Any,
         url: str,
     ) -> Dict[str, str]:
-        """Scrape a single article url.
+        """
+        Scrape a single article url.
 
         Args:
             browser (Any): a Playwright Chromium browser.
@@ -125,9 +127,10 @@ def scrape_article(
         return {"title": title, "subtitle": subtitle, "body": body, "url": url}
 
     def get_article_urls(
-        self, browser: Any, root_url: str, current_url: str
+        self, browser: Any, root_url: str, current_url: str, max_depth: int = 100
     ) -> List[str]:
-        """Recursively crawl through the knowledge base to find a list of articles.
+        """
+        Recursively crawl through the knowledge base to find a list of articles.
 
         Args:
             browser (Any): a Playwright Chromium browser.
@@ -158,7 +161,9 @@ def get_article_urls(
 
         for link in links:
             url = root_url + page.evaluate("(node) => node.getAttribute('href')", link)
-            article_urls.extend(self.get_article_urls(browser, root_url, url))
+            article_urls.extend(
+                self.get_article_urls(browser, root_url, url, max_depth)
+            )
 
         page.close()
 

llama-index-integrations/readers/llama-index-readers-web/pyproject.toml

@@ -45,7 +45,7 @@ license = "MIT"
 maintainers = ["HawkClaws", "Hironsan", "NA", "an-bluecat", "bborn", "jasonwcfan", "kravetsmic", "pandazki", "ruze00", "selamanse", "thejessezhang"]
 name = "llama-index-readers-web"
 readme = "README.md"
-version = "0.3.2"
+version = "0.3.3"
 
 [tool.poetry.dependencies]
 python = ">=3.9,<4.0"

llama-index-integrations/vector_stores/llama-index-vector-stores-opensearch/llama_index/vector_stores/opensearch/base.py

@@ -634,7 +634,7 @@ def _is_efficient_filtering_enabled(self) -> bool:
             ef_enabled = False
         else:
             self._os_version = self._get_opensearch_version()
-            major, minor, patch = self.os_version.split(".")
+            major, minor, patch = self._os_version.split(".")
             ef_enabled = int(major) >= 2 and int(minor) >= 9
         return ef_enabled
 

llama-index-integrations/vector_stores/llama-index-vector-stores-opensearch/pyproject.toml

@@ -27,7 +27,7 @@ exclude = ["**/BUILD"]
 license = "MIT"
 name = "llama-index-vector-stores-opensearch"
 readme = "README.md"
-version = "0.5.1"
+version = "0.5.2"
 
 [tool.poetry.dependencies]
 python = ">=3.9,<4.0"