llama-cpp-python 0.2.15__tar.gz → 0.2.16__tar.gz

llama_cpp_python-0.2.16/.git/FETCH_HEAD

@@ -0,0 +1 @@
+b7e60b66f47950e385980a1329af9dfb14da6906		'b7e60b66f47950e385980a1329af9dfb14da6906' of https://github.com/abetlen/llama-cpp-python

llama_cpp_python-0.2.16/.git/HEAD

@@ -0,0 +1 @@
+b7e60b66f47950e385980a1329af9dfb14da6906

{llama_cpp_python-0.2.15 → llama_cpp_python-0.2.16}/.git/config

@@ -9,7 +9,7 @@
 [gc]
 	auto = 0
 [http "https://github.com/"]
-	extraheader = AUTHORIZATION: basic eC1hY2Nlc3MtdG9rZW46Z2hzXzVCV2FnZFFjcjVieUJXTjZWTU5kcDhRd05QZVE5ZTFhTkp6Wg==
+	extraheader = AUTHORIZATION: basic eC1hY2Nlc3MtdG9rZW46Z2hzXzJBc3h5aUVKQkZ1Q3M5bjVaWU1ZTk9za3hoSzh0VDFMeVdwRw==
 [submodule "vendor/llama.cpp"]
 	active = true
 	url = https://github.com/ggerganov/llama.cpp.git

llama_cpp_python-0.2.16/.git/logs/HEAD

@@ -0,0 +1 @@
+0000000000000000000000000000000000000000 b7e60b66f47950e385980a1329af9dfb14da6906 runner <runner@fv-az711-229.kxtiaivj4gxuxgxjt4etq45iac.phxx.internal.cloudapp.net> 1699615337 +0000	checkout: moving from master to refs/tags/v0.2.16

llama_cpp_python-0.2.16/.git/modules/vendor/llama.cpp/HEAD

@@ -0,0 +1 @@
+a75fa576abba9d37f463580c379e4bbf1e1ad03c

{llama_cpp_python-0.2.15 → llama_cpp_python-0.2.16}/.git/modules/vendor/llama.cpp/config

@@ -13,7 +13,7 @@
 [gc]
 	auto = 0
 [http "https://github.com/"]
-	extraheader = AUTHORIZATION: basic eC1hY2Nlc3MtdG9rZW46Z2hzXzVCV2FnZFFjcjVieUJXTjZWTU5kcDhRd05QZVE5ZTFhTkp6Wg==
+	extraheader = AUTHORIZATION: basic eC1hY2Nlc3MtdG9rZW46Z2hzXzJBc3h5aUVKQkZ1Q3M5bjVaWU1ZTk9za3hoSzh0VDFMeVdwRw==
 [url "https://github.com/"]
 	insteadOf = git@github.com:
 	insteadOf = org-6826477@github.com:

llama_cpp_python-0.2.16/.git/modules/vendor/llama.cpp/logs/HEAD

@@ -0,0 +1,2 @@
+0000000000000000000000000000000000000000 a75fa576abba9d37f463580c379e4bbf1e1ad03c runner <runner@fv-az711-229.kxtiaivj4gxuxgxjt4etq45iac.phxx.internal.cloudapp.net> 1699615338 +0000	clone: from https://github.com/ggerganov/llama.cpp.git
+a75fa576abba9d37f463580c379e4bbf1e1ad03c a75fa576abba9d37f463580c379e4bbf1e1ad03c runner <runner@fv-az711-229.kxtiaivj4gxuxgxjt4etq45iac.phxx.internal.cloudapp.net> 1699615338 +0000	checkout: moving from master to a75fa576abba9d37f463580c379e4bbf1e1ad03c

llama_cpp_python-0.2.16/.git/modules/vendor/llama.cpp/logs/refs/heads/master

@@ -0,0 +1 @@
+0000000000000000000000000000000000000000 a75fa576abba9d37f463580c379e4bbf1e1ad03c runner <runner@fv-az711-229.kxtiaivj4gxuxgxjt4etq45iac.phxx.internal.cloudapp.net> 1699615338 +0000	clone: from https://github.com/ggerganov/llama.cpp.git

llama_cpp_python-0.2.16/.git/modules/vendor/llama.cpp/logs/refs/remotes/origin/HEAD

@@ -0,0 +1 @@
+0000000000000000000000000000000000000000 a75fa576abba9d37f463580c379e4bbf1e1ad03c runner <runner@fv-az711-229.kxtiaivj4gxuxgxjt4etq45iac.phxx.internal.cloudapp.net> 1699615338 +0000	clone: from https://github.com/ggerganov/llama.cpp.git

llama_cpp_python-0.2.16/.git/modules/vendor/llama.cpp/packed-refs

@@ -0,0 +1,2 @@
+# pack-refs with: peeled fully-peeled sorted 
+a75fa576abba9d37f463580c379e4bbf1e1ad03c refs/remotes/origin/master

llama_cpp_python-0.2.16/.git/modules/vendor/llama.cpp/refs/heads/master

@@ -0,0 +1 @@
+a75fa576abba9d37f463580c379e4bbf1e1ad03c

llama_cpp_python-0.2.16/.git/modules/vendor/llama.cpp/shallow

@@ -0,0 +1 @@
+a75fa576abba9d37f463580c379e4bbf1e1ad03c

llama_cpp_python-0.2.16/.git/objects/b7/e60b66f47950e385980a1329af9dfb14da6906

@@ -0,0 +1,4 @@
+x
��Q�0��)��miwKb�r��,JB����%���If�Қ�T�9>բ
+ܣ%F�(6`p!1��&YQ
+N��}3�M�.ƞ}3R����%�\�t$��&!
+����x,C�	:��.p��7��,�|Ik����h=�1 ����%�n�|���u1_1�FW

llama_cpp_python-0.2.16/.git/refs/tags/v0.2.16

@@ -0,0 +1 @@
+b7e60b66f47950e385980a1329af9dfb14da6906

llama_cpp_python-0.2.16/.git/shallow

@@ -0,0 +1 @@
+b7e60b66f47950e385980a1329af9dfb14da6906

{llama_cpp_python-0.2.15 → llama_cpp_python-0.2.16}/.github/workflows/build-and-release.yaml

@@ -33,6 +33,9 @@ jobs:
 
       - name: Build wheels
         run: python -m cibuildwheel --output-dir wheelhouse
+        env:
+          # disable repair
+          CIBW_REPAIR_WHEEL_COMMAND: ""
 
       - uses: actions/upload-artifact@v3
         with:

{llama_cpp_python-0.2.15 → llama_cpp_python-0.2.16}/CHANGELOG.md

@@ -7,6 +7,19 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.2.16]
+
+- Update llama.cpp to ggerganov/llama.cp@a75fa576abba9d37f463580c379e4bbf1e1ad03c
+- Add `set_seed` to `Llama` class by @abetlen in fd41ed3a908761d286102a019a34c2938a15118d
+- Fix server doc arguments by @kjunggithub in #892
+- Fix response_format handler in llava chat handler by @abetlen in b62c44983921197ed10a7d29dc4ba920e9979380
+- Fix default max_tokens, chat completion is now unlimited (to context length) and completion is 16 tokens to match OpenAI defaults by @abetlen in e7962d2c733cbbeec5a37392c81f64185a9a39e8
+- Fix json_schema_to_gbnf helper so that it takes a json schema string as input instead by @abetlen in faeae181b1e868643c0dc28fcf039f077baf0829
+- Add support for $ref and $def in json_schema_to_gbnf to handle more complex function schemas by @abetlen in 770df344369c0630df1be14be9f9e301e7c56d24
+- Update functionary chat handler for new OpenAI api by abetlen in 1b376c62b775b401653facf25a519d116aafe99a
+- Fix add default stop sequence to chatml chat format by @abetlen in b84d76a844149216d511cfd8cdb9827148a1853c
+- Fix sampling bug when logits_all=False by @abetlen in 6f0b0b1b840af846938ed74d0e8170a91c40e617
+
 ## [0.2.15]
 
 - Update llama.cpp to ggerganov/llama.cpp@0a7c980b6f94a049cb804573df2d8092a34df8e4

{llama_cpp_python-0.2.15 → llama_cpp_python-0.2.16}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: llama_cpp_python
-Version: 0.2.15
+Version: 0.2.16
 Summary: Python bindings for the llama.cpp library
 Author-Email: Andrei Betlen <abetlen@gmail.com>
 License: MIT

{llama_cpp_python-0.2.15 → llama_cpp_python-0.2.16}/docs/server.md

@@ -34,6 +34,35 @@ NOTE: All server options are also available as environment variables. For exampl
 
 ## Guides
 
+### Code Completion
+
+`llama-cpp-python` supports code completion via GitHub Copilot.
+
+*NOTE*: Without GPU acceleration this is unlikely to be fast enough to be usable.
+
+You'll first need to download one of the available code completion models in GGUF format:
+
+- [replit-code-v1_5-GGUF](https://huggingface.co/abetlen/replit-code-v1_5-3b-GGUF)
+
+Then you'll need to run the OpenAI compatible web server with a increased context size substantially for GitHub Copilot requests:
+
+```bash
+python3 -m llama_cpp.server --model <model_path> --n_ctx 16192
+```
+
+Then just update your settings in `.vscode/settings.json` to point to your code completion server:
+
+```json
+{
+    // ...
+    "github.copilot.advanced": {
+        "debug.testOverrideProxyUrl": "http://<host>:<port>",
+        "debug.overrideProxyUrl": "http://<host>:<port>"
+    }
+    // ...
+}
+```
+
 ### Function Calling
 
 `llama-cpp-python` supports structured function calling based on a JSON schema.
@@ -45,7 +74,7 @@ You'll first need to download one of the available function calling models in GG
 Then when you run the server you'll need to also specify the `functionary-7b-v1` chat_format
 
 ```bash
-python3 -m llama_cpp.server --model <model_path> --chat-format functionary
+python3 -m llama_cpp.server --model <model_path> --chat_format functionary
 ```
 
 ### Multimodal Models
@@ -57,11 +86,12 @@ You'll first need to download one of the available multi-modal models in GGUF fo
 
 - [llava-v1.5-7b](https://huggingface.co/mys/ggml_llava-v1.5-7b)
 - [llava-v1.5-13b](https://huggingface.co/mys/ggml_llava-v1.5-13b)
+- [bakllava-1-7b](https://huggingface.co/mys/ggml_bakllava-1)
 
 Then when you run the server you'll need to also specify the path to the clip model used for image embedding and the `llava-1-5` chat_format
 
 ```bash
-python3 -m llama_cpp.server --model <model_path> --clip-model-path <clip_model_path> --chat-format llava-1-5
+python3 -m llama_cpp.server --model <model_path> --clip_model_path <clip_model_path> --chat_format llava-1-5
 ```
 
 Then you can just use the OpenAI API as normal

llama_cpp_python-0.2.16/examples/notebooks/Functions.ipynb

@@ -0,0 +1,400 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "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"
+     ]
+    }
+   ],
+   "source": [
+    "import openai\n",
+    "import json\n",
+    "\n",
+    "\n",
+    "client = openai.OpenAI(\n",
+    "    api_key = \"sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx\", # can be anything\n",
+    "    base_url = \"http://100.64.159.73:8000/v1\"\n",
+    ")\n",
+    "\n",
+    "# Example dummy function hard coded to return the same weather\n",
+    "# In production, this could be your backend API or an external API\n",
+    "def get_current_weather(location, unit=\"fahrenheit\"):\n",
+    "    \"\"\"Get the current weather in a given location\"\"\"\n",
+    "    if \"tokyo\" in location.lower():\n",
+    "        return json.dumps({\"location\": \"Tokyo\", \"temperature\": \"10\", \"unit\": \"celsius\"})\n",
+    "    elif \"san francisco\" in location.lower():\n",
+    "        return json.dumps({\"location\": \"San Francisco\", \"temperature\": \"72\", \"unit\": \"fahrenheit\"})\n",
+    "    elif \"paris\" in location.lower():\n",
+    "        return json.dumps({\"location\": \"Paris\", \"temperature\": \"22\", \"unit\": \"celsius\"})\n",
+    "    else:\n",
+    "        return json.dumps({\"location\": location, \"temperature\": \"unknown\"})\n",
+    "\n",
+    "def run_conversation():\n",
+    "    # Step 1: send the conversation and available functions to the model\n",
+    "    messages = [{\"role\": \"user\", \"content\": \"What's the weather like in San Francisco, Tokyo, and Paris?\"}]\n",
+    "    tools = [\n",
+    "        {\n",
+    "            \"type\": \"function\",\n",
+    "            \"function\": {\n",
+    "                \"name\": \"get_current_weather\",\n",
+    "                \"description\": \"Get the current weather in a given location\",\n",
+    "                \"parameters\": {\n",
+    "                    \"type\": \"object\",\n",
+    "                    \"properties\": {\n",
+    "                        \"location\": {\n",
+    "                            \"type\": \"string\",\n",
+    "                            \"description\": \"The city and state, e.g. San Francisco, CA\",\n",
+    "                        },\n",
+    "                        \"unit\": {\"type\": \"string\", \"enum\": [\"celsius\", \"fahrenheit\"]},\n",
+    "                    },\n",
+    "                    \"required\": [\"location\"],\n",
+    "                },\n",
+    "            },\n",
+    "        }\n",
+    "    ]\n",
+    "    response = client.chat.completions.create(\n",
+    "        model=\"gpt-3.5-turbo-1106\",\n",
+    "        messages=messages,\n",
+    "        tools=tools,\n",
+    "        tool_choice=\"auto\",  # auto is default, but we'll be explicit\n",
+    "    )\n",
+    "    response_message = response.choices[0].message\n",
+    "    tool_calls = response_message.tool_calls\n",
+    "    # Step 2: check if the model wanted to call a function\n",
+    "    if tool_calls:\n",
+    "        # Step 3: call the function\n",
+    "        # Note: the JSON response may not always be valid; be sure to handle errors\n",
+    "        available_functions = {\n",
+    "            \"get_current_weather\": get_current_weather,\n",
+    "        }  # only one function in this example, but you can have multiple\n",
+    "        messages.append(response_message)  # extend conversation with assistant's reply\n",
+    "        # Step 4: send the info for each function call and function response to the model\n",
+    "        for tool_call in tool_calls:\n",
+    "            function_name = tool_call.function.name\n",
+    "            function_to_call = available_functions[function_name]\n",
+    "            function_args = json.loads(tool_call.function.arguments)\n",
+    "            function_response = function_to_call(\n",
+    "                location=function_args.get(\"location\"),\n",
+    "                unit=function_args.get(\"unit\"),\n",
+    "            )\n",
+    "            messages.append(\n",
+    "                {\n",
+    "                    \"tool_call_id\": tool_call.id,\n",
+    "                    \"role\": \"tool\",\n",
+    "                    \"name\": function_name,\n",
+    "                    \"content\": function_response,\n",
+    "                }\n",
+    "            )  # extend conversation with function response\n",
+    "        second_response = client.chat.completions.create(\n",
+    "            model=\"gpt-3.5-turbo-1106\",\n",
+    "            messages=messages,\n",
+    "        )  # get a new response from the model where it can see the function response\n",
+    "        return second_response\n",
+    "print(run_conversation())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "name='Jason' age=25\n"
+     ]
+    }
+   ],
+   "source": [
+    "import instructor\n",
+    "from pydantic import BaseModel\n",
+    "\n",
+    "# Enables `response_model`\n",
+    "client = instructor.patch(client=client)\n",
+    "\n",
+    "class UserDetail(BaseModel):\n",
+    "    name: str\n",
+    "    age: int\n",
+    "\n",
+    "user = client.chat.completions.create(\n",
+    "    model=\"gpt-3.5-turbo\",\n",
+    "    response_model=UserDetail,\n",
+    "    messages=[\n",
+    "        {\"role\": \"user\", \"content\": \"Extract Jason is 25 years old\"},\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "assert isinstance(user, UserDetail)\n",
+    "assert user.name == \"Jason\"\n",
+    "assert user.age == 25\n",
+    "\n",
+    "print(user)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import enum\n",
+    "\n",
+    "class Labels(str, enum.Enum):\n",
+    "    \"\"\"Enumeration for single-label text classification.\"\"\"\n",
+    "    SPAM = \"spam\"\n",
+    "    NOT_SPAM = \"not_spam\"\n",
+    "\n",
+    "class SinglePrediction(BaseModel):\n",
+    "    \"\"\"\n",
+    "    Class for a single class label prediction.\n",
+    "    \"\"\"\n",
+    "    class_label: Labels\n",
+    "\n",
+    "def classify(data: str) -> SinglePrediction:\n",
+    "    \"\"\"Perform single-label classification on the input text.\"\"\"\n",
+    "    return client.chat.completions.create(\n",
+    "        model=\"gpt-3.5-turbo-0613\",\n",
+    "        response_model=SinglePrediction,\n",
+    "        messages=[\n",
+    "            {\n",
+    "                \"role\": \"user\",\n",
+    "                \"content\": f\"Classify the following text: {data}\",\n",
+    "            },\n",
+    "        ],\n",
+    "    )  # 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"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "class_labels=[<MultiLabels.BILLING: 'billing'>, <MultiLabels.TECH_ISSUE: 'tech_issue'>]\n"
+     ]
+    }
+   ],
+   "source": [
+    "from typing import List\n",
+    "\n",
+    "# Define Enum class for multiple labels\n",
+    "class MultiLabels(str, enum.Enum):\n",
+    "    TECH_ISSUE = \"tech_issue\"\n",
+    "    BILLING = \"billing\"\n",
+    "    GENERAL_QUERY = \"general_query\"\n",
+    "\n",
+    "# Define the multi-class prediction model\n",
+    "class MultiClassPrediction(BaseModel):\n",
+    "    \"\"\"\n",
+    "    Class for a multi-class label prediction.\n",
+    "    \"\"\"\n",
+    "    class_labels: List[MultiLabels]\n",
+    "\n",
+    "def multi_classify(data: str) -> MultiClassPrediction:\n",
+    "    \"\"\"Perform multi-label classification on the input text.\"\"\"\n",
+    "    return client.chat.completions.create(\n",
+    "        model=\"gpt-3.5-turbo-0613\",\n",
+    "        response_model=MultiClassPrediction,\n",
+    "        messages=[\n",
+    "            {\n",
+    "                \"role\": \"user\",\n",
+    "                \"content\": f\"Classify the following support ticket: {data}\",\n",
+    "            },\n",
+    "        ],\n",
+    "    )  # type: ignore\n",
+    "\n",
+    "# Test multi-label classification\n",
+    "ticket = \"My account is locked and I can't access my billing info.\"\n",
+    "prediction = multi_classify(ticket)\n",
+    "print(prediction)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "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"
+     ]
+    }
+   ],
+   "source": [
+    "from typing_extensions import Annotated\n",
+    "from pydantic import BaseModel, BeforeValidator\n",
+    "\n",
+    "from instructor import llm_validator\n",
+    "\n",
+    "\n",
+    "question = \"What is the meaning of life?\"\n",
+    "context = \"The according to the devil the meaning of live is to live a life of sin and debauchery.\"\n",
+    "\n",
+    "class QuestionAnswer(BaseModel):\n",
+    "    question: str\n",
+    "    answer: str\n",
+    "\n",
+    "qa: QuestionAnswer = client.chat.completions.create(\n",
+    "    model=\"gpt-3.5-turbo\",\n",
+    "    response_model=QuestionAnswer,\n",
+    "    messages=[\n",
+    "        {\n",
+    "            \"role\": \"system\",\n",
+    "            \"content\": \"You are a system that answers questions based on the context. answer exactly what the question asks using the context.\",\n",
+    "        },\n",
+    "        {\n",
+    "            \"role\": \"user\",\n",
+    "            \"content\": f\"using the context: {context}\\n\\nAnswer the following question: {question}\",\n",
+    "        },\n",
+    "    ],\n",
+    ")\n",
+    "print(qa)\n",
+    "\n",
+    "class QuestionAnswerNoEvil(BaseModel):\n",
+    "    question: str\n",
+    "    answer: Annotated[\n",
+    "        str,\n",
+    "        BeforeValidator(\n",
+    "            llm_validator(\"don't say objectionable things\", allow_override=True)\n",
+    "        ),\n",
+    "    ]\n",
+    "\n",
+    "try:\n",
+    "    qa: QuestionAnswerNoEvil = client.chat.completions.create(\n",
+    "        model=\"gpt-3.5-turbo\",\n",
+    "        response_model=QuestionAnswerNoEvil,\n",
+    "        messages=[\n",
+    "            {\n",
+    "                \"role\": \"system\",\n",
+    "                \"content\": \"You are a system that answers questions based on the context. answer exactly what the question asks using the context.\",\n",
+    "            },\n",
+    "            {\n",
+    "                \"role\": \"user\",\n",
+    "                \"content\": f\"using the context: {context}\\n\\nAnswer the following question: {question}\",\n",
+    "            },\n",
+    "        ],\n",
+    "    )\n",
+    "except Exception as e:\n",
+    "    print(e)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "question='What did the author do during college?' answer=[Fact(fact='The author, Jason Liu, studied Computational Mathematics and Physics in university.', substring_quote=['Computational Mathematics'])]\n"
+     ]
+    }
+   ],
+   "source": [
+    "import re\n",
+    "from typing import List\n",
+    "\n",
+    "from pydantic import Field, BaseModel, model_validator, FieldValidationInfo\n",
+    "\n",
+    "class Fact(BaseModel):\n",
+    "    fact: str = Field(...)\n",
+    "    substring_quote: List[str] = Field(...)\n",
+    "\n",
+    "    @model_validator(mode=\"after\")\n",
+    "    def validate_sources(self, info: FieldValidationInfo) -> \"Fact\":\n",
+    "        text_chunks = info.context.get(\"text_chunk\", None)\n",
+    "        spans = list(self.get_spans(text_chunks))\n",
+    "        self.substring_quote = [text_chunks[span[0] : span[1]] for span in spans]\n",
+    "        return self\n",
+    "\n",
+    "    def get_spans(self, context):\n",
+    "        for quote in self.substring_quote:\n",
+    "            yield from self._get_span(quote, context)\n",
+    "\n",
+    "    def _get_span(self, quote, context):\n",
+    "        for match in re.finditer(re.escape(quote), context):\n",
+    "            yield match.span()\n",
+    "\n",
+    "class QuestionAnswer(BaseModel):\n",
+    "    question: str = Field(...)\n",
+    "    answer: List[Fact] = Field(...)\n",
+    "\n",
+    "    @model_validator(mode=\"after\")\n",
+    "    def validate_sources(self) -> \"QuestionAnswer\":\n",
+    "        self.answer = [fact for fact in self.answer if len(fact.substring_quote) > 0]\n",
+    "        return self\n",
+    "\n",
+    "\n",
+    "def ask_ai(question: str, context: str) -> QuestionAnswer:\n",
+    "    return client.chat.completions.create(\n",
+    "        model=\"gpt-3.5-turbo-0613\",\n",
+    "        temperature=0.0,\n",
+    "        response_model=QuestionAnswer,\n",
+    "        messages=[\n",
+    "            {\"role\": \"system\", \"content\": \"You are a world class algorithm to answer questions with correct and exact citations.\"},\n",
+    "            {\"role\": \"user\", \"content\": f\"{context}\"},\n",
+    "            {\"role\": \"user\", \"content\": f\"Question: {question}\"}\n",
+    "        ],\n",
+    "        validation_context={\"text_chunk\": context},\n",
+    "    )\n",
+    "\n",
+    "question = \"What did the author do during college?\"\n",
+    "context = \"\"\"\n",
+    "My name is Jason Liu, and I grew up in Toronto Canada but I was born in China.\n",
+    "I went to an arts high school but in university I studied Computational Mathematics and physics.\n",
+    "As part of coop I worked at many companies including Stitchfix, Facebook.\n",
+    "I also started the Data Science club at the University of Waterloo and I was the president of the club for 2 years.\n",
+    "\"\"\"\n",
+    "\n",
+    "qa = ask_ai(question, context)\n",
+    "print(qa)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "python-3.8.10",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.5+"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

{llama_cpp_python-0.2.15 → llama_cpp_python-0.2.16}/llama_cpp/__init__.py

@@ -1,4 +1,4 @@
 from .llama_cpp import *
 from .llama import *
 
-__version__ = "0.2.15"
+__version__ = "0.2.16"