Wi%ddlZddlmZddlmZddlmZddlmZm Z m Z m Z m Z m Z ddlmZddlmZmZdZd ZGd d eZy) N)tqdm) csr_matrix)Llama)MappingListTupleAnyUnionCallable)BaseRepresentation)truncate_document%validate_truncate_document_parametersa This is a list of texts where each collection of texts describe a topic. After each collection of texts, the name of the topic they represent is mentioned as a short-highly-descriptive title --- Topic: Sample texts from this topic: - Traditional diets in most cultures were primarily plant-based with a little meat on top, but with the rise of industrial style meat production and factory farming, meat has become a staple food. - Meat, but especially beef, is the word food in terms of emissions. - Eating meat doesn't make you a bad person, not eating meat doesn't make you a good one. Keywords: meat beef eat eating emissions steak food health processed chicken Topic name: Environmental impacts of eating meat --- Topic: Sample texts from this topic: - I have ordered the product weeks ago but it still has not arrived! - The website mentions that it only takes a couple of days to deliver but I still have not received mine. - I got a message stating that I received the monitor but that is not true! - It took a month longer to deliver than was advised... Keywords: deliver weeks product shipping long delivery received arrived arrive week Topic name: Shipping and delivery issues --- Topic: Sample texts from this topic: [DOCUMENTS] Keywords: [KEYWORDS] Topic name:z@You are an assistant that extracts high-level topics from texts.ceZdZdZddiddddfdeeefdedzdedzdeeefde d e dzd e dzd eee fdzfd Z d e jdedeeeeee ffdeeeeee fffdZdZedZy)LlamaCPPa A llama.cpp implementation to use as a representation model. Arguments: model: Either a string pointing towards a local LLM or a `llama_cpp.Llama` object. prompt: The prompt to be used in the model. If no prompt is given, `self.default_prompt_` is used instead. NOTE: Use `"[KEYWORDS]"` and `"[DOCUMENTS]"` in the prompt to decide where the keywords and documents need to be inserted. system_prompt: The system prompt to be used in the model. If no system prompt is given, `self.default_system_prompt_` is used instead. pipeline_kwargs: Kwargs that you can pass to the `llama_cpp.Llama` when it is called such as `max_tokens` to be generated. nr_docs: The number of documents to pass to OpenAI if a prompt with the `["DOCUMENTS"]` tag is used. diversity: The diversity of documents to pass to OpenAI. Accepts values between 0 and 1. A higher values results in passing more diverse documents whereas lower values passes more similar documents. doc_length: The maximum length of each document. If a document is longer, it will be truncated. If None, the entire document is passed. tokenizer: The tokenizer used to calculate to split the document into segments used to count the length of a document. * If tokenizer is 'char', then the document is split up into characters which are counted to adhere to `doc_length` * If tokenizer is 'whitespace', the the document is split up into words separated by whitespaces. These words are counted and truncated depending on `doc_length` * If tokenizer is 'vectorizer', then the internal CountVectorizer is used to tokenize the document. These tokens are counted and truncated depending on `doc_length` * If tokenizer is a callable, then that callable is used to tokenize the document. These tokens are counted and truncated depending on `doc_length` Usage: To use a llama.cpp, first download the LLM: ```bash wget https://huggingface.co/TheBloke/zephyr-7B-alpha-GGUF/resolve/main/zephyr-7b-alpha.Q4_K_M.gguf ``` Then, we can now use the model the model with BERTopic in just a couple of lines: ```python from bertopic import BERTopic from bertopic.representation import LlamaCPP # Use llama.cpp to load in a 4-bit quantized version of Zephyr 7B Alpha representation_model = LlamaCPP("zephyr-7b-alpha.Q4_K_M.gguf") # Create our BERTopic model topic_model = BERTopic(representation_model=representation_model, verbose=True) ``` If you want to have more control over the LLMs parameters, you can run it like so: ```python from bertopic import BERTopic from bertopic.representation import LlamaCPP from llama_cpp import Llama # Use llama.cpp to load in a 4-bit quantized version of Zephyr 7B Alpha llm = Llama(model_path="zephyr-7b-alpha.Q4_K_M.gguf", n_gpu_layers=-1, n_ctx=4096, stop="Q:") representation_model = LlamaCPP(llm) # Create our BERTopic model topic_model = BERTopic(representation_model=representation_model, verbose=True) ``` Nmodelprompt system_promptpipeline_kwargsnr_docs diversity doc_length tokenizerc t|trt|ddd|_n#t|tr||_n t d||nt |_||nt|_t |_ t|_ ||_ ||_ ||_ ||_||_t!|j|jg|_y)N ChatML) model_path n_gpu_layersstop chat_formatzpMake sure that the model that youpass is either a string referring to alocal LLM or a ` llama_cpp.Llama` object.) isinstancestrrr ValueErrorDEFAULT_PROMPTrDEFAULT_SYSTEM_PROMPTrdefault_prompt_default_system_prompt_rrrrrrprompts_) selfrrrrrrrrs m/home/sietch6/trending-topics-pipeline/venv/lib/python3.12/site-packages/bertopic/representation/_llamacpp.py__init__zLlamaCPP.__init__ss eS !%btYabDJ u %DJ<  !' 2f .;.G]Mb-&;#. "$"-dnndooN documentsc_tf_idftopicsreturnc |j|||d|j|j\}}}}i}t|j |j D]\}} | D cgc]$} t ||j|j| &} } |j| ||} |jj| |jjddd|jdd| dgi|j} | ddd d j!}|d fgt#d Dcgc]}d c}z||<|Scc} wcc}w)aOExtract topic representations and return a single label. Arguments: topic_model: A BERTopic model documents: Not used c_tf_idf: Not used topics: The candidate topics as calculated with c-TF-IDF Returns: updated_topics: Updated topic representations i)disablemessagessystem)rolecontentuserchoicesrmessager7 )r)_extract_representative_docsrrritemsverboser rr_create_promptr)appendrcreate_chat_completionrrstriprange)r* topic_modelr.r/r0repr_docs_mappings_updated_topicstopicdocsdoctruncated_docsrtopic_descriptionlabels r+extract_topicszLlamaCPP.extract_topicss[&'2&N&N idllDNN' #Aq! 2 8 8 : H[H[D[\ OKE4nrsgj/ T__dnn^absNs((GF MM  (!B A A!#+8J8JKV\ioMpq!&&! &i03I>yIOOQE&+QZLU1X3NG3N$NN5 ! Ot4Os ")D7" D<c`tt||}|jtk(r?|jj ddj |}|j ||}|S|j}d|vr!|j ddj |}d|vr|j ||}|S)Nz [KEYWORDS]z, [DOCUMENTS])nextziprr%replacejoin_replace_documents)r*rLrKr0keywordsrs r+rBzLlamaCPP._create_promptsVE]+, ;;. ([[((tyy7JKF,,VT:F [[Fv% dii6IJ&00> r-cNd}|D] }|d|dz } |jd|}|S)Nr=z- rrS)rV)rrL to_replacerMs r+rXzLlamaCPP._replace_documentss=  'C Bse2, &J ' z: r-)__name__ __module__ __qualname____doc__r r#rrr intfloatr r,pd DataFramerrrrQrB staticmethodrXr>r-r+rr)sGX"$(-/"&!%15 S%Z  d  Tz  !c*   4< $J h'$. D'<<' ' T%U "3445 ' d5e,-- . 'R&r-r)pandasrbr scipy.sparser llama_cpprtypingrrrr r r bertopic.representation._baser bertopic.representation._utilsr rr%r&rr>r-r+rks<#==<c8[n!nr-