Merge branch 'main' into feat/ersatz-o1

run-llama · Sep 30, 2024 · 2929ec4 · 2929ec4
2 parents f6164db + a620a26
commit 2929ec4
Show file tree

Hide file tree

Showing 147 changed files with 4,682 additions and 987 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,5 +1,98 @@
 # 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]
+
+- add option for string node representation during retireval in property graphs (#16100)
+- improve markdown element node parser and structured prediction reliability (#16172)
+
+### `llama-index-graph-stores-neptune` [0.2.1]
+
+- Fixed issue where Neptune was adding additional labels (#16137)
+
+### `llama-index-llms-vertext` [0.3.5]
+
+- Pass safety_settings to send_message methods to fix settings not being sent to API (#16153)
+
+### `llama-index-readers-box` [0.2.3]
+
+- upgrading box sdk to >= 1.5.0 #16169
+
+### `llama-index-storage-chat-store-dynamodb` [0.2.0]
+
+- Async support for dynamodb (#16139)
+
+### `llama-index-storage-chat-store-redis` [0.3.1]
+
+- Async support for redis (#16139)
+
+### `llama-index-vector-stores-astra-db` [0.3.0]
+
+- Depend on AstraPy 1.5 and above for AstraDBVectorStore (#16164)
+
+## [2024-09-22]
+
+### `llama-index-core` [0.11.12]
+
+- Correct Pydantic warning(s) issed for llm base class (#16141)
+- globally safe format prompt variables in strings with JSON (#15734)
+- account for tools in prompt helper and response synthesizers (#16157)
+
+### `llama-index-readers-google` [0.4.1]
+
+- feat: add drive link to google drive reader metadata (#16156)
+
+### `llama-index-readers-microsoft-sharepoint` [0.3.2]
+
+- Add required_exts option to SharePoint reader (#16152)
+
+### `llama-index-vector-stores-milvus` [0.2.4]
+
+- Support user-defined schema in MilvusVectorStore (#16151)
+
 ## [2024-09-20]
 
 ### `llama-index-core` [0.11.11]

diff --git a/docs/docs/CHANGELOG.md b/docs/docs/CHANGELOG.md
@@ -1,5 +1,98 @@
 # 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]
+
+- add option for string node representation during retireval in property graphs (#16100)
+- improve markdown element node parser and structured prediction reliability (#16172)
+
+### `llama-index-graph-stores-neptune` [0.2.1]
+
+- Fixed issue where Neptune was adding additional labels (#16137)
+
+### `llama-index-llms-vertext` [0.3.5]
+
+- Pass safety_settings to send_message methods to fix settings not being sent to API (#16153)
+
+### `llama-index-readers-box` [0.2.3]
+
+- upgrading box sdk to >= 1.5.0 #16169
+
+### `llama-index-storage-chat-store-dynamodb` [0.2.0]
+
+- Async support for dynamodb (#16139)
+
+### `llama-index-storage-chat-store-redis` [0.3.1]
+
+- Async support for redis (#16139)
+
+### `llama-index-vector-stores-astra-db` [0.3.0]
+
+- Depend on AstraPy 1.5 and above for AstraDBVectorStore (#16164)
+
+## [2024-09-22]
+
+### `llama-index-core` [0.11.12]
+
+- Correct Pydantic warning(s) issed for llm base class (#16141)
+- globally safe format prompt variables in strings with JSON (#15734)
+- account for tools in prompt helper and response synthesizers (#16157)
+
+### `llama-index-readers-google` [0.4.1]
+
+- feat: add drive link to google drive reader metadata (#16156)
+
+### `llama-index-readers-microsoft-sharepoint` [0.3.2]
+
+- Add required_exts option to SharePoint reader (#16152)
+
+### `llama-index-vector-stores-milvus` [0.2.4]
+
+- Support user-defined schema in MilvusVectorStore (#16151)
+
 ## [2024-09-20]
 
 ### `llama-index-core` [0.11.11]

diff --git a/docs/docs/api_reference/multi_modal_llms/mistralai.md b/docs/docs/api_reference/multi_modal_llms/mistralai.md
@@ -0,0 +1,4 @@
+::: llama_index.multi_modal_llms.mistralai
+    options:
+      members:
+        - MistralMultiModal
diff --git a/docs/docs/examples/agent/nvidia_agent.ipynb b/docs/docs/examples/agent/nvidia_agent.ipynb
@@ -378,8 +378,7 @@
    "outputs": [],
    "source": [
     "response = agent.chat(\n",
-    "    \"Tell me both the risk factors and tailwinds for Uber? Do two parallel tool calls.\",\n",
-    "    allow_parallel_tool_calls=True,\n",
+    "    \"Tell me both the risk factors and tailwinds for Uber? Do two parallel tool calls.\"\n",
     ")\n",
     "print(str(response))"
    ]

diff --git a/docs/docs/examples/data_connectors/WebPageDemo.ipynb b/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": {

diff --git a/docs/docs/examples/embeddings/voyageai.ipynb b/docs/docs/examples/embeddings/voyageai.ipynb
@@ -59,7 +59,7 @@
    "source": [
     "# get API key and create embeddings\n",
     "\n",
-    "model_name = \"voyage-law-2\"  # Please check https://docs.voyageai.com/docs/embeddings for the available models\n",
+    "model_name = \"voyage-3\"  # Please check https://docs.voyageai.com/docs/embeddings for the available models\n",
     "voyage_api_key = os.environ.get(\"VOYAGE_API_KEY\", \"your-api-key\")\n",
     "\n",
     "embed_model = VoyageEmbedding(\n",