Customizable consts

app.py

@@ -2,35 +2,7 @@ import gradio as gr
 import json
 import os
 import requests
-
-CORPUS_BY_DESC = {
-    'RedPajama (LLaMA tokenizer)': 'rpj_v3_c4_llama2',
-    'Pile-val (GPT-2 tokenizer)': 'pile_v3_val',
-}
-CORPUS_DESCS = list(CORPUS_BY_DESC.keys())
-QUERY_TYPE_BY_DESC = {
-    '1. Count an n-gram': 'count',
-    '2. Compute the probability of the last token in an n-gram': 'compute_prob',
-    '3. Compute the next-token distribution of an (n-1)-gram': 'get_next_token_distribution_approx',
-    '4. Compute the ∞-gram probability of the last token': 'compute_infgram_prob',
-    '5. Compute the ∞-gram next-token distribution': 'get_infgram_next_token_distribution_approx',
-    '6. Searching for document containing n-gram(s)': 'get_a_random_document_from_cnf_query_fast_approx',
-    # '7. Analyze an (AI-generated) document using ∞-gram': 'analyze_document',
-}
-QUERY_DESC_BY_TYPE = {v: k for k, v in QUERY_TYPE_BY_DESC.items()}
-QUERY_DESCS = list(QUERY_TYPE_BY_DESC.keys())
-
-MAX_QUERY_CHARS = 1000
-MAX_INPUT_DOC_TOKENS = 1000
-MAX_OUTPUT_DOC_TOKENS = 5000 # must be an even number!
-MAX_CNT_FOR_NTD = 1000
-MAX_CLAUSE_FREQ = 10000
-MAX_CLAUSE_FREQ_FAST = 1000000
-MAX_CLAUSE_FREQ_FAST_APPROX_PER_SHARD = 50000
-MAX_DIFF_TOKENS = 100
-MAX_DIFF_BYTES = 2 * MAX_DIFF_TOKENS
-MAX_CLAUSES_IN_CNF = 4
-MAX_TERMS_IN_DISJ_CLAUSE = 4
+from .constants import *
 
 API_IPADDR = os.environ.get('API_IPADDR', None)
 default_concurrency_limit = os.environ.get('default_concurrency_limit', 10)

constants.py

@@ -0,0 +1,30 @@
+import os
+
+CORPUS_BY_DESC = {
+    'RedPajama (LLaMA tokenizer)': 'rpj_v3_c4_llama2',
+    'Pile-val (GPT-2 tokenizer)': 'pile_v3_val',
+}
+CORPUS_DESCS = list(CORPUS_BY_DESC.keys())
+QUERY_TYPE_BY_DESC = {
+    '1. Count an n-gram': 'count',
+    '2. Compute the probability of the last token in an n-gram': 'compute_prob',
+    '3. Compute the next-token distribution of an (n-1)-gram': 'get_next_token_distribution_approx',
+    '4. Compute the ∞-gram probability of the last token': 'compute_infgram_prob',
+    '5. Compute the ∞-gram next-token distribution': 'get_infgram_next_token_distribution_approx',
+    '6. Searching for document containing n-gram(s)': 'get_a_random_document_from_cnf_query_fast_approx',
+    # '7. Analyze an (AI-generated) document using ∞-gram': 'analyze_document',
+}
+QUERY_DESC_BY_TYPE = {v: k for k, v in QUERY_TYPE_BY_DESC.items()}
+QUERY_DESCS = list(QUERY_TYPE_BY_DESC.keys())
+
+MAX_QUERY_CHARS = os.environ.get('MAX_QUERY_CHARS', 1000)
+MAX_INPUT_DOC_TOKENS = os.environ.get('MAX_INPUT_DOC_TOKENS', 1000)
+MAX_OUTPUT_DOC_TOKENS = os.environ.get('MAX_OUTPUT_DOC_TOKENS', 5000)
+MAX_CNT_FOR_NTD = os.environ.get('MAX_CNT_FOR_NTD', 1000)
+MAX_CLAUSE_FREQ = os.environ.get('MAX_CLAUSE_FREQ', 10000)
+MAX_CLAUSE_FREQ_FAST = os.environ.get('MAX_CLAUSE_FREQ_FAST', 1000000)
+MAX_CLAUSE_FREQ_FAST_APPROX_PER_SHARD = os.environ.get('MAX_CLAUSE_FREQ_FAST_APPROX_PER_SHARD', 50000)
+MAX_DIFF_TOKENS = os.environ.get('MAX_DIFF_TOKENS', 100)
+MAX_DIFF_BYTES = 2 * MAX_DIFF_TOKENS
+MAX_CLAUSES_IN_CNF = os.environ.get('MAX_CLAUSES_IN_CNF', 4)
+MAX_TERMS_IN_DISJ_CLAUSE = os.environ.get('MAX_TERMS_IN_DISJ_CLAUSE', 4)