Merge tag 'v0.2.17' into main

abetlen · abetlen · commit ca30d898e96f · 2023-11-14T15:32:12.000-05:00
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -7,6 +7,11 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.2.17]
+
+- Update llama.cpp to ggerganov/llama.cpp@df9d1293defe783f42bc83af732d3c670552c541
+- Hotfix: Set `CUDA_ARCHITECTURES=OFF` for `llava_shared` target on Windows by @abetlen in 4388f3341413110217b98c4f097ac5c590bdf40b
+
 ## [0.2.16]
 
 - Update llama.cpp to ggerganov/llama.cp@a75fa576abba9d37f463580c379e4bbf1e1ad03c
diff --git a/CMakeLists.txt b/CMakeLists.txt
@@ -6,6 +6,8 @@ option(LLAMA_BUILD "Build llama.cpp shared library and install alongside python
 
 if (LLAMA_BUILD)
     set(BUILD_SHARED_LIBS "On")
+
+    # Building llama
     if (APPLE AND NOT CMAKE_SYSTEM_PROCESSOR MATCHES "arm64")
         # Need to disable these llama.cpp flags on Apple x86_64,
         # otherwise users may encounter invalid instruction errors
@@ -41,8 +43,14 @@ if (LLAMA_BUILD)
         FILES $<TARGET_RUNTIME_DLLS:llama>
         DESTINATION ${CMAKE_CURRENT_SOURCE_DIR}/llama_cpp
     )
+
+    # Building llava
     add_subdirectory(vendor/llama.cpp/examples/llava)
     set_target_properties(llava_shared PROPERTIES OUTPUT_NAME "llava")
+    # Set CUDA_ARCHITECTURES to OFF on windows
+    if (WIN32)
+        set_target_properties(llava_shared PROPERTIES CUDA_ARCHITECTURES OFF)
+    endif()
     install(
         TARGETS llava_shared
         LIBRARY DESTINATION ${SKBUILD_PLATLIB_DIR}/llama_cpp
diff --git a/examples/notebooks/Functions.ipynb b/examples/notebooks/Functions.ipynb
@@ -1,15 +1,41 @@
 {
  "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Functions\n",
+    "\n",
+    "The OpenAI compatbile web server in `llama-cpp-python` supports function calling.\n",
+    "\n",
+    "Function calling allows API clients to specify a schema that gives the model a format it should respond in.\n",
+    "Function calling in `llama-cpp-python` works by combining models pretrained for function calling such as [`functionary`](https://huggingface.co/abetlen/functionary-7b-v1-GGUF) with constrained sampling to produce a response that is compatible with the schema.\n",
+    "\n",
+    "Note however that this improves but does not guarantee that the response will be compatible with the schema.\n",
+    "\n",
+    "## Requirements\n",
+    "\n",
+    "Before we begin you will need the following:\n",
+    "\n",
+    "- A running `llama-cpp-python` server with a function calling compatible model. [See here](https://llama-cpp-python.readthedocs.io/en/latest/server/#function-calling)\n",
+    "- The OpenAI Python Client `pip install openai`\n",
+    "- (Optional) The Instructor Python Library `pip install instructor`\n",
+    "\n",
+    "## Function Calling with OpenAI Python Client\n",
+    "\n",
+    "We'll start with a basic demo that only uses the OpenAI Python Client."
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": 29,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "ChatCompletion(id='chatcmpl-b6dcbb47-1120-4761-8cd9-83542c97647b', choices=[Choice(finish_reason='stop', index=0, message=ChatCompletionMessage(content=\"The current temperature in San Francisco is 72 degrees Fahrenheit. It's a sunny day with clear skies, making it perfect for outdoor activities.\\n \", role='assistant', function_call=None, tool_calls=None))], created=1699602158, model='gpt-3.5-turbo-1106', object='chat.completion', system_fingerprint=None, usage=CompletionUsage(completion_tokens=38, prompt_tokens=135, total_tokens=173))\n"
+      "ChatCompletion(id='chatcmpl-a2d9eb9f-7354-472f-b6ad-4d7a807729a3', choices=[Choice(finish_reason='stop', index=0, message=ChatCompletionMessage(content='The current weather in San Francisco is **72°F** (22°C).\\n ', role='assistant', function_call=None, tool_calls=None))], created=1699638365, model='gpt-3.5-turbo-1106', object='chat.completion', system_fingerprint=None, usage=CompletionUsage(completion_tokens=22, prompt_tokens=136, total_tokens=158))\n"
      ]
     }
    ],
@@ -20,7 +46,7 @@
     "\n",
     "client = openai.OpenAI(\n",
     "    api_key = \"sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx\", # can be anything\n",
-    "    base_url = \"http://100.64.159.73:8000/v1\"\n",
+    "    base_url = \"http://100.64.159.73:8000/v1\" # NOTE: Replace with IP address and port of your llama-cpp-python server\n",
     ")\n",
     "\n",
     "# Example dummy function hard coded to return the same weather\n",
@@ -100,9 +126,32 @@
     "print(run_conversation())"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Function Calling with Instructor\n",
+    "\n",
+    "The above example is a bit verbose and requires you to manually verify the schema.\n",
+    "\n",
+    "For our next examples we'll use the `instructor` library to simplify the process and accomplish a number of different tasks with function calling.\n",
+    "\n",
+    "You'll first need to install the [`instructor`](https://github.com/jxnl/instructor/).\n",
+    "\n",
+    "You can do so by running the following command in your terminal:\n",
+    "\n",
+    "```bash\n",
+    "pip install instructor\n",
+    "```\n",
+    "\n",
+    "Below we'll go through a few basic examples taken directly from the [instructor cookbook](https://jxnl.github.io/instructor/)\n",
+    "\n",
+    "## Basic Usage"
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": 30,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [
     {
@@ -139,11 +188,28 @@
     "print(user)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Text Classification\n",
+    "\n",
+    "### Single-Label Classification"
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": 31,
+   "execution_count": 7,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "class_label=<Labels.SPAM: 'spam'>\n"
+     ]
+    }
+   ],
    "source": [
     "import enum\n",
     "\n",
@@ -172,19 +238,27 @@
     "    )  # type: ignore\n",
     "\n",
     "prediction = classify(\"Hello there I'm a Nigerian prince and I want to give you money\")\n",
-    "assert prediction.class_label == Labels.SPAM"
+    "assert prediction.class_label == Labels.SPAM\n",
+    "print(prediction)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Multi-Label Classification"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 32,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "class_labels=[<MultiLabels.BILLING: 'billing'>, <MultiLabels.TECH_ISSUE: 'tech_issue'>]\n"
+      "class_labels=[<MultiLabels.TECH_ISSUE: 'tech_issue'>, <MultiLabels.BILLING: 'billing'>]\n"
      ]
     }
    ],
@@ -223,16 +297,27 @@
     "print(prediction)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Self-Critique"
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": 33,
+   "execution_count": 13,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "question='What is the meaning of life?' answer='The meaning of life, according to the Devil, is to live a life of sin and debauchery.'\n"
+      "question='What is the meaning of life?' answer='According to the Devil, the meaning of life is to live a life of sin and debauchery.'\n",
+      "1 validation error for QuestionAnswerNoEvil\n",
+      "answer\n",
+      "  Assertion failed, The statement promotes sin and debauchery, which can be considered objectionable. [type=assertion_error, input_value='According to the Devil, ... of sin and debauchery.', input_type=str]\n",
+      "    For further information visit https://errors.pydantic.dev/2.3/v/assertion_error\n"
      ]
     }
    ],
@@ -294,6 +379,13 @@
     "    print(e)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Answering Questions with Validated Citations"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 42,
@@ -366,13 +458,6 @@
     "qa = ask_ai(question, context)\n",
     "print(qa)"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
diff --git a/llama_cpp/__init__.py b/llama_cpp/__init__.py
@@ -1,4 +1,4 @@
 from .llama_cpp import *
 from .llama import *
 
-__version__ = "0.2.16"
+__version__ = "0.2.17"
diff --git a/vendor/llama.cpp b/vendor/llama.cpp
@@ -1 +1 @@
-Subproject commit a75fa576abba9d37f463580c379e4bbf1e1ad03c
+Subproject commit df9d1293defe783f42bc83af732d3c670552c541
