_llamacpp.py
9.19 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
import pandas as pd
from tqdm import tqdm
from scipy.sparse import csr_matrix
from llama_cpp import Llama
from typing import Mapping, List, Tuple, Any, Union, Callable
from bertopic.representation._base import BaseRepresentation
from bertopic.representation._utils import truncate_document, validate_truncate_document_parameters
DEFAULT_PROMPT = """
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:"""
DEFAULT_SYSTEM_PROMPT = "You are an assistant that extracts high-level topics from texts."
class LlamaCPP(BaseRepresentation):
"""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)
```
"""
def __init__(
self,
model: Union[str, Llama],
prompt: str = None,
system_prompt: str = None,
pipeline_kwargs: Mapping[str, Any] = {},
nr_docs: int = 4,
diversity: float = None,
doc_length: int = None,
tokenizer: Union[str, Callable] = None,
):
if isinstance(model, str):
self.model = Llama(model_path=model, n_gpu_layers=-1, stop="\n", chat_format="ChatML")
elif isinstance(model, Llama):
self.model = model
else:
raise ValueError(
"Make sure that the model that you"
"pass is either a string referring to a"
"local LLM or a ` llama_cpp.Llama` object."
)
self.prompt = prompt if prompt is not None else DEFAULT_PROMPT
self.system_prompt = system_prompt if system_prompt is not None else DEFAULT_SYSTEM_PROMPT
self.default_prompt_ = DEFAULT_PROMPT
self.default_system_prompt_ = DEFAULT_SYSTEM_PROMPT
self.pipeline_kwargs = pipeline_kwargs
self.nr_docs = nr_docs
self.diversity = diversity
self.doc_length = doc_length
self.tokenizer = tokenizer
validate_truncate_document_parameters(self.tokenizer, self.doc_length)
self.prompts_ = []
def extract_topics(
self,
topic_model,
documents: pd.DataFrame,
c_tf_idf: csr_matrix,
topics: Mapping[str, List[Tuple[str, float]]],
) -> Mapping[str, List[Tuple[str, float]]]:
"""Extract 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
"""
# Extract the top 4 representative documents per topic
repr_docs_mappings, _, _, _ = topic_model._extract_representative_docs(
c_tf_idf, documents, topics, 500, self.nr_docs, self.diversity
)
updated_topics = {}
for topic, docs in tqdm(repr_docs_mappings.items(), disable=not topic_model.verbose):
# Prepare prompt
truncated_docs = [truncate_document(topic_model, self.doc_length, self.tokenizer, doc) for doc in docs]
prompt = self._create_prompt(truncated_docs, topic, topics)
self.prompts_.append(prompt)
# Extract result from generator and use that as label
# topic_description = self.model(prompt, **self.pipeline_kwargs)["choices"]
topic_description = self.model.create_chat_completion(
messages=[{"role": "system", "content": self.system_prompt}, {"role": "user", "content": prompt}],
**self.pipeline_kwargs,
)
label = topic_description["choices"][0]["message"]["content"].strip()
updated_topics[topic] = [(label, 1)] + [("", 0) for _ in range(9)]
return updated_topics
def _create_prompt(self, docs, topic, topics):
keywords = list(zip(*topics[topic]))[0]
# Use the Default Chat Prompt
if self.prompt == DEFAULT_PROMPT:
prompt = self.prompt.replace("[KEYWORDS]", ", ".join(keywords))
prompt = self._replace_documents(prompt, docs)
# Use a custom prompt that leverages keywords, documents or both using
# custom tags, namely [KEYWORDS] and [DOCUMENTS] respectively
else:
prompt = self.prompt
if "[KEYWORDS]" in prompt:
prompt = prompt.replace("[KEYWORDS]", ", ".join(keywords))
if "[DOCUMENTS]" in prompt:
prompt = self._replace_documents(prompt, docs)
return prompt
@staticmethod
def _replace_documents(prompt, docs):
to_replace = ""
for doc in docs:
to_replace += f"- {doc}\n"
prompt = prompt.replace("[DOCUMENTS]", to_replace)
return prompt