{
 "cells": [
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# How to count tokens with tiktoken\n",
    "\n",
    "[`tiktoken`](https://github.com/openai/tiktoken/blob/main/README.md) is a fast open-source tokenizer by OpenAI.\n",
    "\n",
    "Given a text string (e.g., `\"tiktoken is great!\"`) and an encoding (e.g., `\"gpt2\"`), a tokenizer can split the text string into a list of tokens (e.g., `[\"t\", \"ik\", \"token\", \" is\", \" great\", \"!\"]`).\n",
    "\n",
    "Splitting text strings into tokens is useful because models like GPT-3 see text in the form of tokens. Knowing how many tokens are in a text string can tell you (a) whether the string is too long for a text model to process and (b) how much an OpenAI API call costs (as usage is priced by token). Different models use different encodings.\n",
    "\n",
    "`tiktoken` supports three encodings used by OpenAI models:\n",
    "\n",
    "| Encoding name           | OpenAI models                                       |\n",
    "|-------------------------|-----------------------------------------------------|\n",
    "| `gpt2` (or `r50k_base`) | Most GPT-3 models                                   |\n",
    "| `p50k_base`             | Code models, `text-davinci-002`, `text-davinci-003` |\n",
    "| `cl100k_base`           | `text-embedding-ada-002`                            |\n",
    "\n",
    "`p50k_base` overlaps substantially with `gpt2`, and for non-code applications, they will usually give the same tokens.\n",
    "\n",
    "## Tokenizer libraries and languages\n",
    "\n",
    "For `gpt2` encodings, tokenizers are available in many languages.\n",
    "- Python: [tiktoken](https://github.com/openai/tiktoken/blob/main/README.md) (or alternatively [GPT2TokenizerFast](https://huggingface.co/docs/transformers/model_doc/gpt2#transformers.GPT2TokenizerFast))\n",
    "- JavaScript: [gpt-3-encoder](https://www.npmjs.com/package/gpt-3-encoder)\n",
    "- .NET / C#: [GPT Tokenizer](https://github.com/dluc/openai-tools)\n",
    "- Java: [gpt2-tokenizer-java](https://github.com/hyunwoongko/gpt2-tokenizer-java)\n",
    "- PHP: [GPT-3-Encoder-PHP](https://github.com/CodeRevolutionPlugins/GPT-3-Encoder-PHP)\n",
    "\n",
    "(OpenAI makes no endorsements or guarantees of third-party libraries.)\n",
    "\n",
    "For `p50k_base` and `cl100k_base` encodings, `tiktoken` is the only tokenizer available as of January 2023.\n",
    "- Python: [tiktoken](https://github.com/openai/tiktoken/blob/main/README.md)\n",
    "\n",
    "## How strings are typically tokenized\n",
    "\n",
    "In English, tokens commonly range in length from one character to one word (e.g., `\"t\"` or `\" great\"`), though in some languages tokens can be shorter than one character or longer than one word. Spaces are usually grouped with the starts of words (e.g., `\" is\"` instead of `\"is \"` or `\" \"`+`\"is\"`). You can quickly check how a string is tokenized at the [OpenAI Tokenizer](https://beta.openai.com/tokenizer)."
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 0. Install `tiktoken`\n",
    "\n",
    "In your terminal, install `tiktoken` with `pip`:\n",
    "\n",
    "```bash\n",
    "pip install tiktoken\n",
    "```"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 1. Import `tiktoken`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from typing import Iterable, Sequence, Optional\n",
    "\n",
    "import tiktoken\n"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 2. Load an encoding\n",
    "\n",
    "Use `tiktoken.get_encoding()` to load an encoding by name.\n",
    "\n",
    "The first time this runs, it will require an internet connection to download. Later runs won't need an internet connection."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "encoding = tiktoken.get_encoding(\"cl100k_base\")\n"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 3. Turn text into tokens with `encoding.encode()`\n",
    "\n"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The `.encode()` method converts a text string into a list of token integers."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "encoding.encode(\"tiktoken is great!\")\n"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Count tokens by counting the length of the list returned by `.encode()`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def num_tokens_from_string(string: str, encoding_name: str) -> int:\n",
    "    \"\"\"Returns the number of tokens in a text string.\"\"\"\n",
    "    encoding = tiktoken.get_encoding(encoding_name)\n",
    "    num_tokens = len(encoding.encode(string))\n",
    "    return num_tokens\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "num_tokens_from_string(\"tiktoken is great!\", \"gpt2\")\n"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 4. Turn tokens into text with `encoding.decode()`"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "`.decode()` converts a list of token integers to a string."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "encoding.decode([83, 1134, 30001, 318, 1049, 0])\n"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Warning: although `.decode()` can be applied to single tokens, beware that it can be lossy for tokens that aren't on utf-8 boundaries."
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "For single tokens, `.decode_single_token_bytes()` safely converts a single integer token to the bytes it represents."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "[encoding.decode_single_token_bytes(token) for token in [83, 1134, 30001, 318, 1049, 0]]\n"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "(The `b` in front of the strings indicates that the strings are byte strings.)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 5. Comparing encodings\n",
    "\n",
    "Different encodings can vary in how they split words, group spaces, and handle non-English characters. Using the methods above, we can compare different encodings on a few example strings."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "outputs": [],
   "source": [
    "def compare_encodings(example_string: str) -> None:\n",
    "    \"\"\"Prints a comparison of three string encodings.\"\"\"\n",
    "    # print the example string\n",
    "    print(f'\\nExample string: \"{example_string}\"')\n",
    "    # for each encoding, print the # of tokens, the token integers, and the token bytes\n",
    "    for encoding_name in [\"gpt2\", \"p50k_base\", \"cl100k_base\"]:\n",
    "        encoding = tiktoken.get_encoding(encoding_name)\n",
    "        token_integers = encoding.encode(example_string)\n",
    "        num_tokens = len(token_integers)\n",
    "        token_bytes = [encoding.decode_single_token_bytes(token) for token in token_integers]\n",
    "        print()\n",
    "        print(f\"{encoding_name}: {num_tokens} tokens\")\n",
    "        print(f\"token integers: {token_integers}\")\n",
    "        print(f\"token bytes: {token_bytes}\")#%% md\n",
    "# How to count tokens with tiktoken\n",
    "\n",
    "[`tiktoken`](https://github.com/openai/tiktoken/blob/main/README.md) is a fast open-source tokenizer by OpenAI.\n",
    "\n",
    "Given a text string (e.g., `\"tiktoken is great!\"`) and an encoding (e.g., `\"gpt2\"`), a tokenizer can split the text string into a list of tokens (e.g., `[\"t\", \"ik\", \"token\", \" is\", \" great\", \"!\"]`).\n",
    "\n",
    "Splitting text strings into tokens is useful because models like GPT-3 see text in the form of tokens. Knowing how many tokens are in a text string can tell you (a) whether the string is too long for a text model to process and (b) how much an OpenAI API call costs (as usage is priced by token). Different models use different encodings.\n",
    "\n",
    "`tiktoken` supports three encodings used by OpenAI models:\n",
    "\n",
    "| Encoding name           | OpenAI models                                       |\n",
    "|-------------------------|-----------------------------------------------------|\n",
    "| `gpt2` (or `r50k_base`) | Most GPT-3 models                                   |\n",
    "| `p50k_base`             | Code models, `text-davinci-002`, `text-davinci-003` |\n",
    "| `cl100k_base`           | `text-embedding-ada-002`                            |\n",
    "\n",
    "`p50k_base` overlaps substantially with `gpt2`, and for non-code applications, they will usually give the same tokens.\n",
    "\n",
    "## Tokenizer libraries and languages\n",
    "\n",
    "For `gpt2` encodings, tokenizers are available in many languages.\n",
    "- Python: [tiktoken](https://github.com/openai/tiktoken/blob/main/README.md) (or alternatively [GPT2TokenizerFast](https://huggingface.co/docs/transformers/model_doc/gpt2#transformers.GPT2TokenizerFast))\n",
    "- JavaScript: [gpt-3-encoder](https://www.npmjs.com/package/gpt-3-encoder)\n",
    "- .NET / C#: [GPT Tokenizer](https://github.com/dluc/openai-tools)\n",
    "- Java: [gpt2-tokenizer-java](https://github.com/hyunwoongko/gpt2-tokenizer-java)\n",
    "- PHP: [GPT-3-Encoder-PHP](https://github.com/CodeRevolutionPlugins/GPT-3-Encoder-PHP)\n",
    "\n",
    "(OpenAI makes no endorsements or guarantees of third-party libraries.)\n",
    "\n",
    "For `p50k_base` and `cl100k_base` encodings, `tiktoken` is the only tokenizer available as of January 2023.\n",
    "- Python: [tiktoken](https://github.com/openai/tiktoken/blob/main/README.md)\n",
    "\n",
    "## How strings are typically tokenized\n",
    "\n",
    "In English, tokens commonly range in length from one character to one word (e.g., `\"t\"` or `\" great\"`), though in some languages tokens can be shorter than one character or longer than one word. Spaces are usually grouped with the starts of words (e.g., `\" is\"` instead of `\"is \"` or `\" \"`+`\"is\"`). You can quickly check how a string is tokenized at the [OpenAI Tokenizer](https://beta.openai.com/tokenizer)."
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "## 0. Install `tiktoken`\n",
    "\n",
    "In your terminal, install `tiktoken` with `pip`:\n",
    "\n",
    "```bash\n",
    "pip install tiktoken\n",
    "```"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "## 1. Import `tiktoken`"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "outputs": [],
   "source": [
    "from typing import Iterable, Sequence, Optional\n",
    "\n",
    "import tiktoken\n"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "## 2. Load an encoding\n",
    "\n",
    "Use `tiktoken.get_encoding()` to load an encoding by name.\n",
    "\n",
    "The first time this runs, it will require an internet connection to download. Later runs won't need an internet connection."
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "outputs": [],
   "source": [
    "encoding = tiktoken.get_encoding(\"cl100k_base\")\n"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "## 3. Turn text into tokens with `encoding.encode()`\n",
    "\n"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "The `.encode()` method converts a text string into a list of token integers."
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "outputs": [],
   "source": [
    "encoding.encode(\"tiktoken is great!\")\n"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "Count tokens by counting the length of the list returned by `.encode()`."
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "outputs": [],
   "source": [
    "def num_tokens_from_string(string: str, encoding_name: str) -> int:\n",
    "    \"\"\"Returns the number of tokens in a text string.\"\"\"\n",
    "    encoding = tiktoken.get_encoding(encoding_name)\n",
    "    num_tokens = len(encoding.encode(string))\n",
    "    return num_tokens\n"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "outputs": [],
   "source": [
    "num_tokens_from_string(\"tiktoken is great!\", \"gpt2\")\n"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "## 4. Turn tokens into text with `encoding.decode()`"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "`.decode()` converts a list of token integers to a string."
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "outputs": [],
   "source": [
    "encoding.decode([83, 1134, 30001, 318, 1049, 0])\n"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "Warning: although `.decode()` can be applied to single tokens, beware that it can be lossy for tokens that aren't on utf-8 boundaries."
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "For single tokens, `.decode_single_token_bytes()` safely converts a single integer token to the bytes it represents."
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "outputs": [],
   "source": [
    "[encoding.decode_single_token_bytes(token) for token in [83, 1134, 30001, 318, 1049, 0]]\n"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "(The `b` in front of the strings indicates that the strings are byte strings.)"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "## 5. Comparing encodings\n",
    "\n",
    "Different encodings can vary in how they split words, group spaces, and handle non-English characters. Using the methods above, we can compare different encodings on a few example strings."
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "outputs": [],
   "source": [
    "def compare_encodings(example_string: str) -> None:\n",
    "    \"\"\"Prints a comparison of three string encodings.\"\"\"\n",
    "    # print the example string\n",
    "    print(f'\\nExample string: \"{example_string}\"')\n",
    "    # for each encoding, print the # of tokens, the token integers, and the token bytes\n",
    "    for encoding_name in [\"gpt2\", \"p50k_base\", \"cl100k_base\"]:\n",
    "        encoding = tiktoken.get_encoding(encoding_name)\n",
    "        token_integers = encoding.encode(example_string)\n",
    "        num_tokens = len(token_integers)\n",
    "        token_bytes = [encoding.decode_single_token_bytes(token) for token in token_integers]\n",
    "        print()\n",
    "        print(f\"{encoding_name}: {num_tokens} tokens\")\n",
    "        print(f\"token integers: {token_integers}\")\n",
    "        print(f\"token bytes: {token_bytes}\")\n"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "outputs": [],
   "source": [
    "compare_encodings(\"antidisestablishmentarianism\")\n"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "outputs": [],
   "source": [
    "compare_encodings(\"2 + 2 = 4\")\n"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "outputs": [],
   "source": [
    "compare_encodings(\"お誕生日おめでとう\")\n"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "outputs": [],
   "source": [
    "long_prompt = str(list(range(3000)))\n",
    "num_tokens_from_string(long_prompt, 'cl100k_base')"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "outputs": [],
   "source": [
    "import openai\n",
    "EMBEDDING_MODEL = 'text-embedding-ada-002'\n",
    "EMBEDDING_CTX_LENGTH = 8191\n",
    "openai.Embedding.create(input=long_prompt, model=EMBEDDING_MODEL)\n",
    "\n"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "outputs": [],
   "source": [
    "def truncate_string_tokens(text: str, encoding_name: str = 'cl100k_base', max_tokens: int = EMBEDDING_CTX_LENGTH) -> list[int]:\n",
    "    \"\"\"Truncate a string to have `max_tokens` according to the given encoding.\"\"\"\n",
    "    encoding = tiktoken.get_encoding(encoding_name)\n",
    "    return encoding.encode(text)[:max_tokens]\n"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "outputs": [],
   "source": [
    "from itertools import islice\n",
    "\n",
    "# From: https://docs.python.org/3/library/itertools.html#itertools-recipes\n",
    "def batched(iterable, n):\n",
    "    \"\"\"Batch data into tuples of length n. The last batch may be shorter.\"\"\"\n",
    "    # batched('ABCDEFG', 3) --> ABC DEF G\n",
    "    if n < 1:\n",
    "        raise ValueError('n must be at least one')\n",
    "    it = iter(iterable)\n",
    "    while (batch := tuple(islice(it, n))):\n",
    "        yield batch\n",
    "\n",
    "\n",
    "def chunked_tokens(text: str, encoding_name: str = 'cl100k_base', chunk_ctx_length: int = EMBEDDING_CTX_LENGTH):\n",
    "    encoding = tiktoken.get_encoding(encoding_name)\n",
    "    tokens = encoding.encode(text)\n",
    "    chunks_iterator = batched(tokens, chunk_ctx_length)\n",
    "    yield from chunks_iterator\n"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "from tenacity import retry, wait_random_exponential, stop_after_attempt\n",
    "\n",
    "\n",
    "@retry(wait=wait_random_exponential(min=1, max=20), stop=stop_after_attempt(6))\n",
    "def get_embedding(tokens: Sequence[int], model=EMBEDDING_MODEL) -> list[float]:\n",
    "    return openai.Embedding.create(input=tokens, model=model)[\"data\"][0][\"embedding\"]\n",
    "\n",
    "\n",
    "def len_safe_get_embedding(text: str, model=EMBEDDING_MODEL, max_tokens: int = EMBEDDING_CTX_LENGTH, encoding_name: str = 'cl100k_base', reduction: Optional[str]='average'):\n",
    "    chunk_embeddings = []\n",
    "    for chunk in chunked_tokens(text, encoding_name=encoding_name, chunk_ctx_length=max_tokens):\n",
    "        chunk_embeddings.append(get_embedding(chunk, model=model))\n",
    "\n",
    "    if reduction is None:\n",
    "        return chunk_embeddings\n",
    "    elif reduction == 'average':\n",
    "        return np.mean(chunk_embeddings, weights=[len(c) for c in chunk_embeddings])\n",
    "    else:\n",
    "        raise NotI\n",
    "\n",
    "\n",
    "\n"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "outputs": [],
   "source": [],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "compare_encodings(\"antidisestablishmentarianism\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "compare_encodings(\"2 + 2 = 4\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "compare_encodings(\"お誕生日おめでとう\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "outputs": [],
   "source": [
    "long_prompt = str(list(range(3000)))\n",
    "num_tokens_from_string(long_prompt, 'cl100k_base')"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "outputs": [],
   "source": [
    "import openai\n",
    "\n",
    "EMBEDDING_MODEL = 'text-embedding-ada-002'\n",
    "EMBEDDING_CTX_LENGTH = 8191\n",
    "\n",
    "openai.Embedding.create(input=long_prompt, model=EMBEDDING_MODEL)\n",
    "\n"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "outputs": [],
   "source": [
    "def truncate_string_tokens(text: str, encoding_name: str = 'cl100k_base', max_tokens: int = EMBEDDING_CTX_LENGTH) -> list[int]:\n",
    "    \"\"\"Truncate a string to have `max_tokens` according to the given encoding.\"\"\"\n",
    "    encoding = tiktoken.get_encoding(encoding_name)\n",
    "    return encoding.encode(text)[:max_tokens]\n"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "outputs": [],
   "source": [
    "from itertools import islice\n",
    "\n",
    "# From: https://docs.python.org/3/library/itertools.html#itertools-recipes\n",
    "def batched(iterable, n):\n",
    "    \"\"\"Batch data into tuples of length n. The last batch may be shorter.\"\"\"\n",
    "    # batched('ABCDEFG', 3) --> ABC DEF G\n",
    "    if n < 1:\n",
    "        raise ValueError('n must be at least one')\n",
    "    it = iter(iterable)\n",
    "    while (batch := tuple(islice(it, n))):\n",
    "        yield batch\n",
    "\n",
    "\n",
    "def chunked_tokens(text: str, encoding_name: str = 'cl100k_base', chunk_ctx_length: int = EMBEDDING_CTX_LENGTH):\n",
    "    encoding = tiktoken.get_encoding(encoding_name)\n",
    "    tokens = encoding.encode(text)\n",
    "    chunks_iterator = batched(tokens, chunk_ctx_length)\n",
    "    yield from chunks_iterator\n"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "from tenacity import retry, wait_random_exponential, stop_after_attempt\n",
    "\n",
    "\n",
    "@retry(wait=wait_random_exponential(min=1, max=20), stop=stop_after_attempt(6))\n",
    "def get_embedding(tokens: Sequence[int], model=EMBEDDING_MODEL) -> list[float]:\n",
    "    return openai.Embedding.create(input=tokens, model=model)[\"data\"][0][\"embedding\"]\n",
    "\n",
    "\n",
    "def len_safe_get_embedding(text: str, model=EMBEDDING_MODEL, max_tokens: int = EMBEDDING_CTX_LENGTH, encoding_name: str = 'cl100k_base', reduction: Optional[str] = None):\n",
    "    chunk_embeddings = []\n",
    "    for chunk in chunked_tokens(text, encoding_name=encoding_name, chunk_ctx_length=max_tokens):\n",
    "        chunk_embeddings.append(get_embedding(chunk, model=model))\n",
    "\n",
    "    if reduction is None:\n",
    "        return chunk_embeddings\n",
    "    elif reduction == 'average':\n",
    "        return np.average(chunk_embeddings, axis=0, weights=[len(c) for c in chunk_embeddings]).tolist()\n",
    "    else:\n",
    "        raise ValueError(f'reduction {reduction} not valid.')\n",
    "\n",
    "\n",
    "\n"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "outputs": [],
   "source": [],
   "metadata": {
    "collapsed": false
   }
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "openai",
   "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": "3.9.9"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "365536dcbde60510dc9073d6b991cd35db2d9bac356a11f5b64279a5e6708b97"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}