\n",
@@ -249,28 +254,28 @@
"
\n",
" \n",
" | 0 | \n",
- " sample_letter_708 | \n",
- " Having worked in the tech industry for 7 years... | \n",
+ " sample_letter_507 | \n",
+ " I am writing to apply for the System Administr... | \n",
"
\n",
" \n",
" | 1 | \n",
- " sample_letter_311 | \n",
- " Dear Hiring Manager,\\n\\nI am writing to expres... | \n",
+ " sample_letter_649 | \n",
+ " I am excited to apply for the AI Engineer posi... | \n",
"
\n",
" \n",
" | 2 | \n",
- " sample_letter_253 | \n",
- " I am writing to apply for the Generative AI En... | \n",
+ " sample_letter_480 | \n",
+ " Dear Hiring Manager,\\n\\nI am writing to expres... | \n",
"
\n",
" \n",
" | 3 | \n",
- " sample_letter_611 | \n",
+ " sample_letter_605 | \n",
" Dear Hiring Manager,\\n\\nI am writing to expres... | \n",
"
\n",
" \n",
" | 4 | \n",
- " sample_letter_394 | \n",
- " Dear Hiring Manager,\\n\\nI am writing to expres... | \n",
+ " sample_letter_746 | \n",
+ " I am writing to express my interest in the Dat... | \n",
"
\n",
" \n",
"\n",
@@ -285,95 +290,100 @@
"execution_count": 8
},
{
- "metadata": {},
"cell_type": "markdown",
- "source": "# Initializing a Connector to the OpenAI API",
- "id": "f13c02d1366be5df"
+ "id": "f13c02d1366be5df",
+ "metadata": {},
+ "source": "# Initializing a Connector to the OpenAI API"
},
{
"cell_type": "code",
+ "id": "c7e7e469ae9840ea",
+ "metadata": {
+ "collapsed": false,
+ "ExecuteTime": {
+ "end_time": "2025-03-01T16:03:31.285820Z",
+ "start_time": "2025-03-01T16:03:31.284192Z"
+ }
+ },
"source": [
"openai_key = os.getenv(\"OPENAI_API_KEY\")\n",
"\n",
"# Check if the API key is set and available\n",
"assert openai_key != \"\", \"Please set the OPENAI_API_KEY environment variable\""
],
- "metadata": {
- "collapsed": false,
- "ExecuteTime": {
- "end_time": "2024-07-19T15:18:20.310220Z",
- "start_time": "2024-07-19T15:18:20.307153Z"
- }
- },
- "id": "c7e7e469ae9840ea",
"outputs": [],
"execution_count": 9
},
{
"cell_type": "code",
- "source": "connector = OpenAIConnector(openai_key)",
+ "id": "47b55c370e9b849a",
"metadata": {
"collapsed": false,
"ExecuteTime": {
- "end_time": "2024-07-19T15:18:20.355977Z",
- "start_time": "2024-07-19T15:18:20.314041Z"
+ "end_time": "2025-03-01T16:03:31.354081Z",
+ "start_time": "2025-03-01T16:03:31.325298Z"
}
},
- "id": "47b55c370e9b849a",
+ "source": [
+ "connector = OpenAIConnector(openai_key)"
+ ],
"outputs": [],
"execution_count": 10
},
{
- "metadata": {},
"cell_type": "markdown",
- "source": "# Embedding the Letters",
- "id": "64a31f966f4bce00"
+ "id": "64a31f966f4bce00",
+ "metadata": {},
+ "source": "# Embedding the Letters"
},
{
"cell_type": "code",
- "source": [
- "letters_with_embeddings_df = application_letters_df.copy()\n",
- "letters_with_embeddings_df['embedding'] = connector.embed(documents=application_letters_df['text'], \n",
- " model=EmbeddingModels.OPENAPI_EMS)"
- ],
+ "id": "68a6d6e054a998b0",
"metadata": {
"collapsed": false,
"ExecuteTime": {
- "end_time": "2024-07-19T15:18:25.397806Z",
- "start_time": "2024-07-19T15:18:20.357020Z"
+ "end_time": "2025-03-01T16:03:35.887699Z",
+ "start_time": "2025-03-01T16:03:31.376295Z"
}
},
- "id": "68a6d6e054a998b0",
+ "source": [
+ "letters_with_embeddings_df = application_letters_df.copy()\n",
+ "letters_with_embeddings_df[\"embedding\"] = connector.embed(\n",
+ " documents=application_letters_df[\"text\"], model=EmbeddingModels.OPENAPI_EMS\n",
+ ")"
+ ],
"outputs": [],
"execution_count": 11
},
{
+ "cell_type": "code",
+ "id": "8d4478a411acf706",
"metadata": {
"ExecuteTime": {
- "end_time": "2024-07-19T15:18:25.408392Z",
- "start_time": "2024-07-19T15:18:25.398908Z"
+ "end_time": "2025-03-01T16:03:35.898332Z",
+ "start_time": "2025-03-01T16:03:35.893536Z"
}
},
- "cell_type": "code",
- "source": "letters_with_embeddings_df.head()",
- "id": "8d4478a411acf706",
+ "source": [
+ "letters_with_embeddings_df.head()"
+ ],
"outputs": [
{
"data": {
"text/plain": [
" id text \\\n",
- "0 sample_letter_708 Having worked in the tech industry for 7 years... \n",
- "1 sample_letter_311 Dear Hiring Manager,\\n\\nI am writing to expres... \n",
- "2 sample_letter_253 I am writing to apply for the Generative AI En... \n",
- "3 sample_letter_611 Dear Hiring Manager,\\n\\nI am writing to expres... \n",
- "4 sample_letter_394 Dear Hiring Manager,\\n\\nI am writing to expres... \n",
+ "0 sample_letter_507 I am writing to apply for the System Administr... \n",
+ "1 sample_letter_649 I am excited to apply for the AI Engineer posi... \n",
+ "2 sample_letter_480 Dear Hiring Manager,\\n\\nI am writing to expres... \n",
+ "3 sample_letter_605 Dear Hiring Manager,\\n\\nI am writing to expres... \n",
+ "4 sample_letter_746 I am writing to express my interest in the Dat... \n",
"\n",
" embedding \n",
- "0 [-0.015994248911738396, 0.020503530278801918, ... \n",
- "1 [0.035636693239212036, -0.001379814581014216, ... \n",
- "2 [0.017323147505521774, -0.044040385633707047, ... \n",
- "3 [0.049760978668928146, -0.015271708369255066, ... \n",
- "4 [0.034355904906988144, 0.02534237876534462, 0.... "
+ "0 [-0.017879672348499298, 0.01556997001171112, 0... \n",
+ "1 [-0.016682444140315056, -0.0227852500975132, -... \n",
+ "2 [0.04394077882170677, 0.005209765397012234, 0.... \n",
+ "3 [0.04028189927339554, 0.020218798890709877, 0.... \n",
+ "4 [0.016521798446774483, -0.006224688142538071, ... "
],
"text/html": [
"
\n",
@@ -402,33 +412,33 @@
"
\n",
" \n",
" | 0 | \n",
- " sample_letter_708 | \n",
- " Having worked in the tech industry for 7 years... | \n",
- " [-0.015994248911738396, 0.020503530278801918, ... | \n",
+ " sample_letter_507 | \n",
+ " I am writing to apply for the System Administr... | \n",
+ " [-0.017879672348499298, 0.01556997001171112, 0... | \n",
"
\n",
" \n",
" | 1 | \n",
- " sample_letter_311 | \n",
- " Dear Hiring Manager,\\n\\nI am writing to expres... | \n",
- " [0.035636693239212036, -0.001379814581014216, ... | \n",
+ " sample_letter_649 | \n",
+ " I am excited to apply for the AI Engineer posi... | \n",
+ " [-0.016682444140315056, -0.0227852500975132, -... | \n",
"
\n",
" \n",
" | 2 | \n",
- " sample_letter_253 | \n",
- " I am writing to apply for the Generative AI En... | \n",
- " [0.017323147505521774, -0.044040385633707047, ... | \n",
+ " sample_letter_480 | \n",
+ " Dear Hiring Manager,\\n\\nI am writing to expres... | \n",
+ " [0.04394077882170677, 0.005209765397012234, 0.... | \n",
"
\n",
" \n",
" | 3 | \n",
- " sample_letter_611 | \n",
+ " sample_letter_605 | \n",
" Dear Hiring Manager,\\n\\nI am writing to expres... | \n",
- " [0.049760978668928146, -0.015271708369255066, ... | \n",
+ " [0.04028189927339554, 0.020218798890709877, 0.... | \n",
"
\n",
" \n",
" | 4 | \n",
- " sample_letter_394 | \n",
- " Dear Hiring Manager,\\n\\nI am writing to expres... | \n",
- " [0.034355904906988144, 0.02534237876534462, 0.... | \n",
+ " sample_letter_746 | \n",
+ " I am writing to express my interest in the Dat... | \n",
+ " [0.016521798446774483, -0.006224688142538071, ... | \n",
"
\n",
" \n",
"\n",
@@ -443,34 +453,38 @@
"execution_count": 12
},
{
- "metadata": {},
"cell_type": "markdown",
- "source": "# Finding the Most Relevant Letters to the Job Ad",
- "id": "c7e02957fc102026"
+ "id": "c7e02957fc102026",
+ "metadata": {},
+ "source": "# Finding the Most Relevant Letters to the Job Ad"
},
{
+ "cell_type": "code",
+ "id": "ce90f301a75a57d",
"metadata": {
"ExecuteTime": {
- "end_time": "2024-07-19T15:18:25.489564Z",
- "start_time": "2024-07-19T15:18:25.409503Z"
+ "end_time": "2025-03-01T16:03:35.957725Z",
+ "start_time": "2025-03-01T16:03:35.953966Z"
}
},
- "cell_type": "code",
- "source": "ranker = Ranker()",
- "id": "ce90f301a75a57d",
+ "source": [
+ "ranker = Ranker()"
+ ],
"outputs": [],
"execution_count": 13
},
{
+ "cell_type": "code",
+ "id": "20a8939323bfaf40",
"metadata": {
"ExecuteTime": {
- "end_time": "2024-07-19T15:18:27.193297Z",
- "start_time": "2024-07-19T15:18:25.495872Z"
+ "end_time": "2025-03-01T16:03:36.786030Z",
+ "start_time": "2025-03-01T16:03:35.995579Z"
}
},
- "cell_type": "code",
- "source": "ranker.make_collection(documents_with_embeddings=letters_with_embeddings_df)",
- "id": "20a8939323bfaf40",
+ "source": [
+ "ranker.make_collection(documents_with_embeddings=letters_with_embeddings_df)"
+ ],
"outputs": [
{
"name": "stdout",
@@ -483,19 +497,19 @@
"execution_count": 14
},
{
+ "cell_type": "code",
+ "id": "f1ecce59c3f826e0",
"metadata": {
"ExecuteTime": {
- "end_time": "2024-07-19T15:18:27.198446Z",
- "start_time": "2024-07-19T15:18:27.194346Z"
+ "end_time": "2025-03-01T16:03:36.800549Z",
+ "start_time": "2025-03-01T16:03:36.798838Z"
}
},
- "cell_type": "code",
"source": [
"sample_job_ad = doc_loader.load_document(path=SAMPLE_JOB_AD)\n",
"\n",
"pprint(sample_job_ad)"
],
- "id": "f1ecce59c3f826e0",
"outputs": [
{
"data": {
@@ -511,37 +525,40 @@
"execution_count": 15
},
{
+ "cell_type": "code",
+ "id": "2d61db3285bf245c",
"metadata": {
"ExecuteTime": {
- "end_time": "2024-07-19T15:18:27.516960Z",
- "start_time": "2024-07-19T15:18:27.199817Z"
+ "end_time": "2025-03-01T16:03:37.297177Z",
+ "start_time": "2025-03-01T16:03:36.840933Z"
}
},
- "cell_type": "code",
"source": [
- "sample_job_ad_embedded = connector.embed(documents=[sample_job_ad], \n",
- " model=EmbeddingModels.OPENAPI_EMS)"
+ "sample_job_ad_embedded = connector.embed(\n",
+ " documents=[sample_job_ad], model=EmbeddingModels.OPENAPI_EMS\n",
+ ")"
],
- "id": "2d61db3285bf245c",
"outputs": [],
"execution_count": 16
},
{
+ "cell_type": "code",
+ "id": "f40e0f2ddb7a7504",
"metadata": {
"ExecuteTime": {
- "end_time": "2024-07-19T15:18:27.522163Z",
- "start_time": "2024-07-19T15:18:27.518012Z"
+ "end_time": "2025-03-01T16:03:37.301674Z",
+ "start_time": "2025-03-01T16:03:37.299478Z"
}
},
- "cell_type": "code",
- "source": "sample_job_ad_embedded",
- "id": "f40e0f2ddb7a7504",
+ "source": [
+ "sample_job_ad_embedded"
+ ],
"outputs": [
{
"data": {
"text/plain": [
"[array([-0.03499759, -0.01236026, 0.00740111, ..., 0.00064774,\n",
- " 0.02555379, -0.00236529])]"
+ " 0.02555379, -0.00236529], shape=(1536,))]"
]
},
"execution_count": 17,
@@ -552,26 +569,34 @@
"execution_count": 17
},
{
+ "cell_type": "code",
+ "id": "1ab0c0edd9e564bf",
"metadata": {
"ExecuteTime": {
- "end_time": "2024-07-19T15:18:27.608446Z",
- "start_time": "2024-07-19T15:18:27.523471Z"
+ "end_time": "2025-03-01T16:03:37.355254Z",
+ "start_time": "2025-03-01T16:03:37.345435Z"
}
},
- "cell_type": "code",
"source": [
- "most_relevant_letters = ranker.find_similar(sample_job_ad_embedded[0], top_k=3, min_similarity=0.1)\n",
+ "most_relevant_letters = ranker.find_similar(\n",
+ " sample_job_ad_embedded[0], top_k=3, min_similarity=0.1\n",
+ ")\n",
"\n",
"most_relevant_letters"
],
- "id": "1ab0c0edd9e564bf",
"outputs": [
{
"data": {
"text/plain": [
- "[ScoredPoint(id=478, version=0, score=0.36129672473127655, payload={'text': 'I am applying for the System Administrator position at Adobe. My extensive experience with Red Hat, CentOS, and Puppet, as well as my proficiency in Ruby, makes me a strong candidate for this role. I am excited about the opportunity to bring my unique skill set to your team.'}, vector=None, shard_key=None, order_value=None),\n",
- " ScoredPoint(id=644, version=0, score=0.35730961122204624, payload={'text': 'I am very interested in the Senior Support Engineer position at Innovative Tech. I have over 4 years of experience in IT support, and I am confident that I can bring a high level of expertise to your team. In my current role at ABC Inc, I have been responsible for managing a team of support specialists and dealing with complex technical issues. I am highly skilled in troubleshooting, networking, and both Linux and Windows systems. I hold a BSc in Information Technology and I am always eager to learn and improve my skills. I believe that my experience and dedication would make me a valuable addition to your company. Thank you for considering my application.'}, vector=None, shard_key=None, order_value=None),\n",
- " ScoredPoint(id=159, version=0, score=0.35427863518996816, payload={'text': \"Dear Hiring Manager,\\n\\nI am writing to express my interest in the Intermediate Applied Scientist position at ABC Environmental Solutions. With my strong background in environmental science and experience in applied consulting, I believe I am well-suited for this role.\\n\\nIn my current position as an Applied Scientist at DEF Environmental Solutions, I have successfully conducted environmental impact assessments and provided regulatory support. I have also gained proficiency in data analysis using tools such as Microsoft Office Suite and Arc GIS. Additionally, my fieldwork experience has allowed me to develop strong problem-solving skills and the ability to thrive under new challenges.\\n\\nI hold a Bachelor's degree in Environmental Science and have completed the Canadian Certified Electrofishing Course, demonstrating my commitment to continuous learning and professional development. Furthermore, my Level 1 First Aid Certificate in BC showcases my dedication to safety in the field.\\n\\nI am confident that my technical expertise, leadership abilities, and strong communication skills make me a valuable asset to your team. I am excited about the opportunity to contribute to ABC Environmental Solutions and make a positive impact on environmental conservation.\\n\\nThank you for considering my application. I look forward to the opportunity to discuss how my qualifications align with the requirements of the Intermediate Applied Scientist position.\\n\\nSincerely,\\nJohn Smith\"}, vector=None, shard_key=None, order_value=None)]"
+ "[{'id': 302,\n",
+ " 'payload': {'text': 'I am applying for the System Administrator position at Adobe. My extensive experience with Red Hat, CentOS, and Puppet, as well as my proficiency in Ruby, makes me a strong candidate for this role. I am excited about the opportunity to bring my unique skill set to your team.'},\n",
+ " 'score': 0.36129672473127655},\n",
+ " {'id': 640,\n",
+ " 'payload': {'text': 'I am very interested in the Senior Support Engineer position at Innovative Tech. I have over 4 years of experience in IT support, and I am confident that I can bring a high level of expertise to your team. In my current role at ABC Inc, I have been responsible for managing a team of support specialists and dealing with complex technical issues. I am highly skilled in troubleshooting, networking, and both Linux and Windows systems. I hold a BSc in Information Technology and I am always eager to learn and improve my skills. I believe that my experience and dedication would make me a valuable addition to your company. Thank you for considering my application.'},\n",
+ " 'score': 0.35730961122204624},\n",
+ " {'id': 545,\n",
+ " 'payload': {'text': \"Dear Hiring Manager,\\n\\nI am writing to express my interest in the Intermediate Applied Scientist position at ABC Environmental Solutions. With my strong background in environmental science and experience in applied consulting, I believe I am well-suited for this role.\\n\\nIn my current position as an Applied Scientist at DEF Environmental Solutions, I have successfully conducted environmental impact assessments and provided regulatory support. I have also gained proficiency in data analysis using tools such as Microsoft Office Suite and Arc GIS. Additionally, my fieldwork experience has allowed me to develop strong problem-solving skills and the ability to thrive under new challenges.\\n\\nI hold a Bachelor's degree in Environmental Science and have completed the Canadian Certified Electrofishing Course, demonstrating my commitment to continuous learning and professional development. Furthermore, my Level 1 First Aid Certificate in BC showcases my dedication to safety in the field.\\n\\nI am confident that my technical expertise, leadership abilities, and strong communication skills make me a valuable asset to your team. I am excited about the opportunity to contribute to ABC Environmental Solutions and make a positive impact on environmental conservation.\\n\\nThank you for considering my application. I look forward to the opportunity to discuss how my qualifications align with the requirements of the Intermediate Applied Scientist position.\\n\\nSincerely,\\nJohn Smith\"},\n",
+ " 'score': 0.35427863518996816}]"
]
},
"execution_count": 18,
@@ -582,41 +607,41 @@
"execution_count": 18
},
{
+ "cell_type": "code",
+ "id": "72f666ce5b32c3c2",
"metadata": {
"ExecuteTime": {
- "end_time": "2024-07-19T15:18:27.617384Z",
- "start_time": "2024-07-19T15:18:27.609781Z"
+ "end_time": "2025-03-01T16:03:37.404063Z",
+ "start_time": "2025-03-01T16:03:37.398438Z"
}
},
- "cell_type": "code",
"source": [
"for letter in most_relevant_letters:\n",
- " print(\"=\"*80)\n",
- " print(f\"Letter ID: {letter.id}\")\n",
- " print(f\"Similarity: {letter.score:.2f}\")\n",
- " print(f\"Letter Text:\\n{letter.payload['text']}\")\n",
+ " print(\"=\" * 80)\n",
+ " print(f\"Letter ID: {letter['id']}\")\n",
+ " print(f\"Similarity: {letter['score']:.2f}\")\n",
+ " print(f\"Letter Text:\\n{letter['payload']['text']}\")\n",
" print()"
],
- "id": "72f666ce5b32c3c2",
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"================================================================================\n",
- "Letter ID: 478\n",
+ "Letter ID: 302\n",
"Similarity: 0.36\n",
"Letter Text:\n",
"I am applying for the System Administrator position at Adobe. My extensive experience with Red Hat, CentOS, and Puppet, as well as my proficiency in Ruby, makes me a strong candidate for this role. I am excited about the opportunity to bring my unique skill set to your team.\n",
"\n",
"================================================================================\n",
- "Letter ID: 644\n",
+ "Letter ID: 640\n",
"Similarity: 0.36\n",
"Letter Text:\n",
"I am very interested in the Senior Support Engineer position at Innovative Tech. I have over 4 years of experience in IT support, and I am confident that I can bring a high level of expertise to your team. In my current role at ABC Inc, I have been responsible for managing a team of support specialists and dealing with complex technical issues. I am highly skilled in troubleshooting, networking, and both Linux and Windows systems. I hold a BSc in Information Technology and I am always eager to learn and improve my skills. I believe that my experience and dedication would make me a valuable addition to your company. Thank you for considering my application.\n",
"\n",
"================================================================================\n",
- "Letter ID: 159\n",
+ "Letter ID: 545\n",
"Similarity: 0.35\n",
"Letter Text:\n",
"Dear Hiring Manager,\n",
@@ -640,35 +665,44 @@
"execution_count": 19
},
{
- "metadata": {},
"cell_type": "markdown",
- "source": "# Gluing Everything Together",
- "id": "6b7ec625af7b6ac5"
+ "id": "6b7ec625af7b6ac5",
+ "metadata": {},
+ "source": "# Gluing Everything Together"
},
{
+ "cell_type": "code",
+ "id": "469615267e34f4b7",
"metadata": {
"ExecuteTime": {
- "end_time": "2024-07-19T15:18:27.630258Z",
- "start_time": "2024-07-19T15:18:27.621249Z"
+ "end_time": "2025-03-01T16:03:37.446492Z",
+ "start_time": "2025-03-01T16:03:37.443381Z"
}
},
- "cell_type": "code",
"source": [
"prompt_part_1 = \"I'm applying for a job with this description:\\n\\n\"\n",
"prompt_part_2 = \"#START OF JOB AD\\n\\n\" + sample_job_ad + \"\\n\\n#END OF JOB AD\"\n",
"prompt_part_3 = \"\\n\\nI need to submit a application letter with my CV. Here is a few examples of my previous application letters:\\n\\n\"\n",
- "prompt_part_4 = \"\\n\\n\".join([('#START OF EXAMPLE APPLICATION LETTER\\n\\n'+\n",
- " t.payload['text'] + '\\n\\n#END OF EXAMPLE APPLICATION LETTER')\n",
- " for t in most_relevant_letters])\n",
+ "prompt_part_4 = \"\\n\\n\".join(\n",
+ " [\n",
+ " (\n",
+ " \"#START OF EXAMPLE APPLICATION LETTER\\n\\n\"\n",
+ " + t['payload'][\"text\"]\n",
+ " + \"\\n\\n#END OF EXAMPLE APPLICATION LETTER\"\n",
+ " )\n",
+ " for t in most_relevant_letters\n",
+ " ]\n",
+ ")\n",
"# Extra information for the prompt\n",
- "prompt_part_5 = (\"\\n\\nWrite a new application letter that is tailored to the job description above. \"\n",
- " \"Be concise and to the point. The letter should be no longer than 500 words. \"\n",
- " \"The letter should be written in English and be easy to read.\\n\\n\")\n",
+ "prompt_part_5 = (\n",
+ " \"\\n\\nWrite a new application letter that is tailored to the job description above. \"\n",
+ " \"Be concise and to the point. The letter should be no longer than 500 words. \"\n",
+ " \"The letter should be written in English and be easy to read.\\n\\n\"\n",
+ ")\n",
"\n",
"prompt = prompt_part_1 + prompt_part_2 + prompt_part_3 + prompt_part_4 + prompt_part_5\n",
"pprint(prompt)"
],
- "id": "469615267e34f4b7",
"outputs": [
{
"data": {
@@ -684,18 +718,18 @@
"execution_count": 20
},
{
+ "cell_type": "code",
+ "id": "777666bb5f08fab",
"metadata": {
"ExecuteTime": {
- "end_time": "2024-07-19T15:18:27.881913Z",
- "start_time": "2024-07-19T15:18:27.631532Z"
+ "end_time": "2025-03-01T16:03:39.042845Z",
+ "start_time": "2025-03-01T16:03:37.490333Z"
}
},
- "cell_type": "code",
"source": [
- "num_tokens = gen_num_tokens(text=prompt, encoding='r50k_base')\n",
+ "num_tokens = gen_num_tokens(text=prompt, encoding=\"r50k_base\")\n",
"print(f\"Number of tokens sent to the API: {num_tokens}\")"
],
- "id": "777666bb5f08fab",
"outputs": [
{
"name": "stdout",
@@ -708,40 +742,39 @@
"execution_count": 21
},
{
+ "cell_type": "code",
+ "id": "fdcaa76ede6692a7",
"metadata": {
"ExecuteTime": {
- "end_time": "2024-07-19T15:18:33.990875Z",
- "start_time": "2024-07-19T15:18:27.883215Z"
+ "end_time": "2025-03-01T16:03:44.773958Z",
+ "start_time": "2025-03-01T16:03:39.049094Z"
}
},
- "cell_type": "code",
"source": [
- "draft_letter = connector.chat(prompt=prompt, \n",
- " model=LLM,\n",
- " temperature=0.1,\n",
- " max_tokens=512)"
+ "draft_letter = connector.chat(prompt=prompt, model=LLM, temperature=0.1, max_tokens=512)"
],
- "id": "fdcaa76ede6692a7",
"outputs": [],
"execution_count": 22
},
{
+ "cell_type": "code",
+ "id": "7fdc9e1c780ff8fc",
"metadata": {
"ExecuteTime": {
- "end_time": "2024-07-19T15:18:34.001718Z",
- "start_time": "2024-07-19T15:18:33.993466Z"
+ "end_time": "2025-03-01T16:03:44.788880Z",
+ "start_time": "2025-03-01T16:03:44.786983Z"
}
},
- "cell_type": "code",
- "source": "pprint(draft_letter)",
- "id": "7fdc9e1c780ff8fc",
+ "source": [
+ "pprint(draft_letter)"
+ ],
"outputs": [
{
"data": {
"text/plain": [
""
],
- "text/markdown": "[Your Name] \n[Your Address] \n[City, Zip Code] \n[Your Email] \n[Your Phone Number] \n[Date] \n\nHiring Manager \nOSI Assistance Foundation - Armenian Branch Office \n1 Pushkin Str., apt. 2 \nYerevan, Armenia \n\nDear Hiring Manager,\n\nI am writing to express my interest in the Chief Accountant/Finance Assistant position at the OSI Assistance Foundation, as advertised. With a university degree in finance and over a year of experience working in an international organization, I am confident in my ability to contribute effectively to your team.\n\nIn my previous role at [Your Previous Company], I was responsible for managing financial transactions, including grant payments and administrative expenses. This experience has equipped me with a solid understanding of International Accounting Standards (IAS) and Armenian taxation laws, as well as the reporting requirements necessary for compliance. I have developed strong organizational skills that enable me to handle multiple tasks efficiently while maintaining attention to detail.\n\nI am proficient in MS Excel and MS Access, which I have used extensively for data analysis and financial reporting. My ability to quickly learn new software and adapt to changing environments has been a key factor in my success. I pride myself on my discretion and ability to handle confidential information with the utmost professionalism.\n\nFluency in English, Armenian, and Russian allows me to communicate effectively with diverse stakeholders, enhancing collaboration and understanding within the team. I am self-motivated and committed to setting and achieving goals, which I believe aligns well with the values of the OSI Assistance Foundation.\n\nI am excited about the opportunity to bring my skills and experience to your organization and contribute to the important work you do. Thank you for considering my application. I look forward to the possibility of discussing how I can support the financial operations of the OSI Assistance Foundation.\n\nSincerely,\n\n[Your Name]"
+ "text/markdown": "[Your Name] \n[Your Address] \n[City, State, Zip] \n[Your Email] \n[Your Phone Number] \n[Date] \n\nHiring Manager \nOSI Assistance Foundation - Armenian Branch Office \n1 Pushkin Str., apt. 2 \nYerevan, Armenia \n\nDear Hiring Manager,\n\nI am writing to express my interest in the Chief Accountant/Finance Assistant position at the OSI Assistance Foundation, as advertised. With a university degree in finance and over a year of experience in an international organization, I am confident in my ability to contribute effectively to your team.\n\nIn my previous role at [Your Previous Company], I was responsible for managing financial transactions, including grant payments and administrative expenses. This experience has equipped me with a solid understanding of International Accounting Standards (IAS) and Armenian taxation laws, as well as the reporting requirements necessary for compliance. My strong organizational skills have allowed me to maintain accurate financial records while ensuring timely reporting and adherence to deadlines.\n\nI am proficient in MS Excel and MS Access, which I have used extensively for data analysis and financial reporting. My ability to quickly learn new software and adapt to changing environments has been a key asset in my previous positions. I pride myself on my discretion and ability to handle confidential information with the utmost professionalism.\n\nFluency in English, Armenian, and Russian enables me to communicate effectively with diverse stakeholders, fostering collaboration and understanding within the team. I am self-motivated and goal-oriented, always striving to improve my skills and contribute positively to my workplace.\n\nI am excited about the opportunity to join the OSI Assistance Foundation and support its mission through effective financial management. Thank you for considering my application. I look forward to the possibility of discussing how my qualifications align with the needs of your organization.\n\nSincerely,\n\n[Your Name]"
},
"metadata": {},
"output_type": "display_data"
@@ -750,33 +783,35 @@
"execution_count": 23
},
{
+ "cell_type": "code",
+ "id": "72e655639ecf67ec",
"metadata": {
"ExecuteTime": {
- "end_time": "2024-07-19T15:18:34.016275Z",
- "start_time": "2024-07-19T15:18:34.004639Z"
+ "end_time": "2025-03-01T16:03:44.827391Z",
+ "start_time": "2025-03-01T16:03:44.825356Z"
}
},
- "cell_type": "code",
"source": [
"# Save the draft letter to a file\n",
"output_file = OUTPUT_DIR / f\"draft-letter-using-{LLM}.txt\"\n",
- "with io.open(output_file, 'w', encoding='utf-8') as f:\n",
+ "with io.open(output_file, \"w\", encoding=\"utf-8\") as f:\n",
" f.write(draft_letter)"
],
- "id": "72e655639ecf67ec",
"outputs": [],
"execution_count": 24
},
{
+ "cell_type": "code",
+ "id": "58c6a81261120d3a",
"metadata": {
"ExecuteTime": {
- "end_time": "2024-07-19T15:18:34.023149Z",
- "start_time": "2024-07-19T15:18:34.018419Z"
+ "end_time": "2025-03-01T16:03:44.872718Z",
+ "start_time": "2025-03-01T16:03:44.870933Z"
}
},
- "cell_type": "code",
- "source": "print(\"Done! The draft letter is saved to the file: \", output_file)",
- "id": "58c6a81261120d3a",
+ "source": [
+ "print(\"Done! The draft letter is saved to the file: \", output_file)"
+ ],
"outputs": [
{
"name": "stdout",
diff --git a/pyproject.toml b/pyproject.toml
index 9911a83..3f74a2e 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,11 +1,12 @@
[tool.poetry]
name = "easy-letters"
-version = "0.1.8"
-description = "A Python package for generating draft application letters using generative AI"
+version = "0.1.9"
+description = "A Python library for generating draft application letters using generative AI"
authors = ["Hassan Abedi "]
+maintainers = ["Hassan Abedi "]
readme = "README.md"
packages = [{ include = "easy_letters", from = "." }]
-include = ["README.md", "LICENSE"]
+include = ["README.md"]
license = "MIT"
repository = "https://github.com/habedi/easy-letters"
@@ -15,20 +16,95 @@ openai = "^1.16.1"
qdrant-client = "^1.8.2"
[tool.poetry.group.dev.dependencies]
-jupyter = "^1.0.0"
-pytest = "^8.2.2"
-black = ">=24.4.2,<26.0.0"
-pytest-cov = ">=5,<7"
poetry-dynamic-versioning = "^1.4.0"
-tiktoken = ">=0.7,<0.10"
-pandas = "^2.2.2"
+pytest = "^8.2.2"
pytest-mock = "^3.14.0"
+pytest-cov = "^6.0.0"
+pandas = "^2.2.2"
+jupyter = "^1.0.0"
+tiktoken = "^0.9.0"
+ruff = "^0.9.9"
+mypy = "^1.15.0"
+icecream = "^2.1.4"
+numpy = "^2.2.3"
+notebook = "^7.3.2"
+
+#[build-system]
+#requires = ["poetry-core"]
+#build-backend = "poetry.core.masonry.api"
+
+#[build-system]
+#requires = ["pdm-backend"]
+#build-backend = "pdm.backend"
[build-system]
-requires = ["poetry-core"]
-build-backend = "poetry.core.masonry.api"
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.pytest.ini_options]
+pythonpath = [".", "easy_letters", "notebooks"]
+addopts = "tests/ --cov --doctest-modules --cov-report=xml -s"
+
+[tool.mypy]
+python_version = "3.10"
+ignore_missing_imports = true
+disallow_untyped_calls = true
+strict_optional = true
+warn_redundant_casts = true
[tool.poetry-dynamic-versioning]
enable = true
vcs = "git"
versioning = "semver" # Semantic Versioning
+
+# Ruff configuration
+[tool.ruff]
+exclude = [
+ ".bzr",
+ ".direnv",
+ ".eggs",
+ ".git",
+ ".git-rewrite",
+ ".hg",
+ ".mypy_cache",
+ ".nox",
+ ".pants.d",
+ ".pytype",
+ ".ruff_cache",
+ ".svn",
+ ".tox",
+ ".venv",
+ "__pypackages__",
+ "_build",
+ "buck-out",
+ "build",
+ "dist",
+ "node_modules",
+ "venv"
+]
+line-length = 100
+indent-width = 4
+src = ["src", "tests", "bin", "notebooks"]
+target-version = "py310"
+
+[tool.ruff.lint]
+select = ["ANN", "D", "E", "F", "I"]
+ignore = [
+ # Ignore missing docstrings
+ "D100", "D101", "D102", "D103", "D104", "D105", "D106", "D107",
+]
+fixable = ["ALL"]
+unfixable = []
+dummy-variable-rgx = "^(_+|(_+[a-zA-Z0-9_]*[a-zA-Z0-9]+?))$"
+
+[tool.ruff.format]
+quote-style = "double"
+indent-style = "space"
+skip-magic-trailing-comma = false
+line-ending = "auto"
+
+[tool.ruff.lint.pydocstyle]
+convention = "google"
+
+[tool.ruff.lint.per-file-ignores]
+"tests/**/*.py" = []
diff --git a/tests/__init__.py b/tests/__init__.py
index 8ac1ecd..7c3cd66 100644
--- a/tests/__init__.py
+++ b/tests/__init__.py
@@ -1,4 +1,4 @@
import os
from pathlib import Path
-TEST_DATA_DIR = Path(os.path.join(os.path.dirname(__file__), 'test_data'))
+TEST_DATA_DIR = Path(os.path.join(os.path.dirname(__file__), "test_data"))
diff --git a/tests/shared.py b/tests/shared.py
new file mode 100644
index 0000000..1275834
--- /dev/null
+++ b/tests/shared.py
@@ -0,0 +1,39 @@
+import numpy as np
+
+from easy_letters import Ranker
+
+# Sample documents and their embeddings for testing
+documents_with_embeddings = {
+ "text": ["Document 1", "Document 2"],
+ "embedding": [np.array([0.1, 0.2, 0.3]), np.array([0.4, 0.5, 0.6])],
+}
+
+# Sample embedding to search for similar documents
+embedding_to_search = np.array([0.1, 0.2, 0.3])
+
+# The expected response (score is Cosine similarity)
+search_response = [
+ {"id": 0, "score": 1.0, "payload": {"text": "Document 1"}},
+ {"id": 1, "score": 0.9746, "payload": {"text": "Document 2"}},
+]
+
+
+def test_make_collection():
+ """
+ Test the make_collection method of the Ranker class.
+ This test checks if the collection is created successfully with the correct
+ parameters.
+ """
+ # Arrange
+ ranker = Ranker()
+ collection_name = "test_collection"
+
+ # Act
+ ranker.make_collection(documents_with_embeddings, collection_name)
+
+ # Assert
+ coll = ranker.client.get_collection(collection_name)
+ assert coll is not None
+ assert coll.points_count == 2
+ assert coll.config.params.vectors.size == 3
+ assert coll.config.params.vectors.distance == "Cosine"
diff --git a/tests/test_connectors.py b/tests/test_connectors.py
index d7abcdd..b1f4123 100644
--- a/tests/test_connectors.py
+++ b/tests/test_connectors.py
@@ -1,42 +1,8 @@
import numpy as np
+from icecream import ic
from easy_letters import Ranker
-
-# Sample documents and their embeddings for testing
-documents_with_embeddings = {
- 'text': ["Document 1", "Document 2"],
- 'embedding': [np.array([0.1, 0.2, 0.3]), np.array([0.4, 0.5, 0.6])]
-}
-
-# Sample embedding to search for similar documents
-embedding_to_search = np.array([0.1, 0.2, 0.3])
-
-# The expected response (score is Cosine similarity)
-search_response = [
- {"id": 0, "score": 1.0, "payload": {"text": "Document 1"}},
- {"id": 1, "score": 0.9746, "payload": {"text": "Document 2"}}
-]
-
-
-def test_make_collection():
- """
- Test the make_collection method of the Ranker class.
- This test checks if the collection is created successfully with the correct
- parameters.
- """
- # Arrange
- ranker = Ranker()
- collection_name = "test_collection"
-
- # Act
- ranker.make_collection(documents_with_embeddings, collection_name)
-
- # Assert
- coll = ranker.client.get_collection(collection_name)
- assert coll is not None
- assert coll.points_count == 2
- assert coll.config.params.vectors.size == 3
- assert coll.config.params.vectors.distance == "Cosine"
+from tests.shared import documents_with_embeddings, embedding_to_search, search_response
def test_find_similar():
@@ -54,6 +20,9 @@ def test_find_similar():
response = ranker.find_similar(embedding_to_search, collection_name, 2)
# Assert
- assert response[1].id == search_response[1]["id"]
- assert np.isclose(response[1].score, search_response[1]["score"], atol=1e-4)
- assert response[1].payload == search_response[1]["payload"]
+ ic(response)
+ ic(search_response)
+ ic(response[1])
+ assert response[1]['id'] == search_response[1]["id"]
+ assert np.isclose(response[1]['score'], search_response[1]["score"], atol=1e-4)
+ assert response[1]['payload'] == search_response[1]["payload"]
diff --git a/tests/test_data/README.md b/tests/test_data/README.md
index 2cd50dd..4823a72 100644
--- a/tests/test_data/README.md
+++ b/tests/test_data/README.md
@@ -1,6 +1,6 @@
-# Data for Testing
+# Datasets for Tests
-The files in the `sample_application_letters` directory are
+The files in the [sample_letters](sample_letters/) directory are
from [here](https://huggingface.co/datasets/ShashiVish/cover-letter-dataset).
-The files in the `sample_job_ads` directory are from [here](https://www.kaggle.com/datasets/madhab/jobposts).
+The files in the [sample_ads](sample_ads/) directory are from [here](https://www.kaggle.com/datasets/madhab/jobposts).
diff --git a/tests/test_similarity_search.py b/tests/test_similarity_search.py
index 5dfa5ab..b1f4123 100644
--- a/tests/test_similarity_search.py
+++ b/tests/test_similarity_search.py
@@ -1,42 +1,8 @@
import numpy as np
+from icecream import ic
from easy_letters import Ranker
-
-# Sample documents and their embeddings for testing
-documents_with_embeddings = {
- 'text': ["Document 1", "Document 2"],
- 'embedding': [np.array([0.1, 0.2, 0.3]), np.array([0.4, 0.5, 0.6])]
-}
-
-# Sample embedding to search for similar documents
-embedding_to_search = np.array([0.1, 0.2, 0.3])
-
-# The expected response (score is Cosine similarity)
-search_response = [
- {"id": 0, "score": 1.0, "payload": {"text": "Document 1"}},
- {"id": 1, "score": 0.9746, "payload": {"text": "Document 2"}}
-]
-
-
-def test_make_collection():
- """
- Test the make_collection method of the Ranker class.
- This test checks if the collection is created successfully with the correct
- parameters.
- """
- # Arrange
- ranker = Ranker()
- collection_name = "test_collection"
-
- # Act
- ranker.make_collection(documents_with_embeddings, collection_name)
-
- # Assert
- coll = ranker.client.get_collection(collection_name)
- assert coll is not None
- assert coll.points_count == 2
- assert coll.config.params.vectors.size == 3
- assert coll.config.params.vectors.distance == "Cosine"
+from tests.shared import documents_with_embeddings, embedding_to_search, search_response
def test_find_similar():
@@ -54,6 +20,9 @@ def test_find_similar():
response = ranker.find_similar(embedding_to_search, collection_name, 2)
# Assert
- assert response[1].id == search_response[1]["id"]
- assert np.isclose(response[1].score, search_response[1]["score"], atol=1e-4)
- assert response[1].payload == search_response[1]["payload"]
+ ic(response)
+ ic(search_response)
+ ic(response[1])
+ assert response[1]['id'] == search_response[1]["id"]
+ assert np.isclose(response[1]['score'], search_response[1]["score"], atol=1e-4)
+ assert response[1]['payload'] == search_response[1]["payload"]