Merge branch 'main' into upstash-chat-store-integration

CHANGELOG.md

@@ -1,5 +1,47 @@
 # ChangeLog
 
+## [2024-09-26]
+
+### `llama-index-core` [0.11.14]
+
+- Enhance insert Method in BaseIndex to Support Customizable Transformations (#16206)
+- Ensure ChatMemoryBuffer's chat history never begins with a TOOL message (#16214)
+- safe prompt helper string formatting (#16219)
+- [Feature Request] Support max concurrent workflow_instance.run() executions (#16215)
+- Workflows + Human In The Loop Dedicated Support (#16220)
+
+### `llama-index-graph-stores-neptune` [0.2.2]
+
+- fix NoneType object error when passing in provided client (#16174)
+
+### `llama-index-llms-ollama` [0.3.3]
+
+- fix ollama chat missing `keep_alive` (#16182)
+
+### `llama-index-llms-vertex` [0.3.6]
+
+- Fix vertex init function (#16216)
+
+### `llama-index-multi-modal-llms-mistral` [0.1.0]
+
+- Add support for Mistral Multi modal LLM (#16191)
+
+### `llama-index-readers-jira` [0.3.0]
+
+- Add pagination support for Jira Reader (#16226)
+
+### `llama-index-vector-stores-azurecosmosmongo` [0.2.1]
+
+- Azure Cosmos DB Filtered Vector Search (#16175)
+
+### `llama-index-vector-stores-azurecosmosnosql` [1.1.0]
+
+- Azure Cosmos DB Filtered Vector Search (#16175)
+
+### `llama-index-vector-stores-deeplake` [0.2.1]
+
+- Add missing JWT dependency (#16236)
+
 ## [2024-09-24]
 
 ### `llama-index-core` [0.11.13]

docs/docs/CHANGELOG.md

@@ -1,5 +1,47 @@
 # ChangeLog
 
+## [2024-09-26]
+
+### `llama-index-core` [0.11.14]
+
+- Enhance insert Method in BaseIndex to Support Customizable Transformations (#16206)
+- Ensure ChatMemoryBuffer's chat history never begins with a TOOL message (#16214)
+- safe prompt helper string formatting (#16219)
+- [Feature Request] Support max concurrent workflow_instance.run() executions (#16215)
+- Workflows + Human In The Loop Dedicated Support (#16220)
+
+### `llama-index-graph-stores-neptune` [0.2.2]
+
+- fix NoneType object error when passing in provided client (#16174)
+
+### `llama-index-llms-ollama` [0.3.3]
+
+- fix ollama chat missing `keep_alive` (#16182)
+
+### `llama-index-llms-vertex` [0.3.6]
+
+- Fix vertex init function (#16216)
+
+### `llama-index-multi-modal-llms-mistral` [0.1.0]
+
+- Add support for Mistral Multi modal LLM (#16191)
+
+### `llama-index-readers-jira` [0.3.0]
+
+- Add pagination support for Jira Reader (#16226)
+
+### `llama-index-vector-stores-azurecosmosmongo` [0.2.1]
+
+- Azure Cosmos DB Filtered Vector Search (#16175)
+
+### `llama-index-vector-stores-azurecosmosnosql` [1.1.0]
+
+- Azure Cosmos DB Filtered Vector Search (#16175)
+
+### `llama-index-vector-stores-deeplake` [0.2.1]
+
+- Add missing JWT dependency (#16236)
+
 ## [2024-09-24]
 
 ### `llama-index-core` [0.11.13]

docs/docs/api_reference/multi_modal_llms/mistralai.md

@@ -0,0 +1,4 @@
+::: llama_index.multi_modal_llms.mistralai
+    options:
+      members:
+        - MistralMultiModal

docs/docs/examples/data_connectors/WebPageDemo.ipynb

@@ -1,7 +1,6 @@
 {
  "cells": [
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "5747e926",
    "metadata": {},
@@ -599,13 +598,136 @@
     "    scrape_format=\"markdown\",  # The scrape result format, either `markdown`(default) or `text`\n",
     ")"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f81ccdb7",
+   "metadata": {},
+   "source": [
+    "# Using ZyteWebReader"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "aee6d871",
+   "metadata": {},
+   "source": [
+    "ZyteWebReader allows a user to access the content of webpage in different modes (\"article\", \"html-text\", \"html\"). \n",
+    "It enables user to change setting such as browser rendering and JS as the content of many sites would require setting these options to access relevant content. All supported options can be found here: https://docs.zyte.com/zyte-api/usage/reference.html\n",
+    "\n",
+    "To install dependencies:\n",
+    "```shell\n",
+    "pip install zyte-api\n",
+    "```\n",
+    "\n",
+    "To get access to your ZYTE API key please visit: https://www.zyte.com/zyte-api/"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f49f22bf",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.readers.web import ZyteWebReader\n",
+    "\n",
+    "# Required to run it in notebook\n",
+    "# import nest_asyncio\n",
+    "# nest_asyncio.apply()\n",
+    "\n",
+    "zyte_dw_params = {\n",
+    "    \"browserHtml\": True,  # Enable browser rendering\n",
+    "    \"javascript\": True,  # Enable JavaScript\n",
+    "}\n",
+    "\n",
+    "# Initiate ZyteWebReader with your Zyte API key\n",
+    "zyte_reader = ZyteWebReader(\n",
+    "    api_key=\"Your Zyte API Key\",\n",
+    "    download_kwargs=zyte_dw_params,\n",
+    ")\n",
+    "\n",
+    "# Load documents from URLs as markdown\n",
+    "documents = zyte_reader.load_data(\n",
+    "    urls=[\"https://www.zyte.com/blog/system-integrators-extract-big-data/\"],\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "74b5d21f-7f53-4412-8f11-bbc84d85a1b5",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "7150"
+      ]
+     },
+     "execution_count": null,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(documents[0].text)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "006254a3-5af8-4a0d-8bf0-b16b9e3dce5c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "zyte_reader = ZyteWebReader(\n",
+    "    api_key=\"Your API Key\",\n",
+    "    mode=\"html-text\",\n",
+    "    download_kwargs=zyte_dw_params,\n",
+    ")\n",
+    "\n",
+    "# Load documents from URLs as markdown\n",
+    "documents = zyte_reader.load_data(\n",
+    "    urls=[\"https://www.zyte.com/blog/system-integrators-extract-big-data/\"],\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3bfb8e5d-7690-4a55-9052-365cbf2c9ce8",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "19554"
+      ]
+     },
+     "execution_count": null,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(documents[0].text)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f642faae-198e-4fad-9742-c590991c8810",
+   "metadata": {},
+   "source": [
+    "In default mode (\"article\") only the article text is extracted while in the \"html-text\" full text is extracted from the webpage, there the length of the text is significantly longer. "
+   ]
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "forked-llama",
    "language": "python",
-   "name": "python3"
+   "name": "forked-llama"
   },
   "language_info": {
    "codemirror_mode": {