Gourisankar Padihary
commited on
Commit
·
201376b
1
Parent(s):
2889c96
Update
Browse files- config.py +1 -1
- generator/initialize_llm.py +2 -2
- retriever/embed_documents.py +4 -4
config.py
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
|
2 |
class ConfigConstants:
|
3 |
# Constants related to datasets and models
|
4 |
-
DATA_SET_NAMES = ['covidqa', 'cuad']#, 'delucionqa', 'emanual', 'expertqa', 'finqa', 'hagrid', 'hotpotqa', 'msmarco', 'pubmedqa', 'tatqa'
|
5 |
EMBEDDING_MODEL_NAME = "sentence-transformers/paraphrase-MiniLM-L3-v2"
|
6 |
RE_RANKER_MODEL_NAME = 'cross-encoder/ms-marco-electra-base'
|
7 |
GENERATION_MODEL_NAME = 'mixtral-8x7b-32768'
|
|
|
1 |
|
2 |
class ConfigConstants:
|
3 |
# Constants related to datasets and models
|
4 |
+
DATA_SET_NAMES = ['covidqa', 'cuad', 'techqa']#, 'delucionqa', 'emanual', 'expertqa', 'finqa', 'hagrid', 'hotpotqa', 'msmarco', 'pubmedqa', 'tatqa']
|
5 |
EMBEDDING_MODEL_NAME = "sentence-transformers/paraphrase-MiniLM-L3-v2"
|
6 |
RE_RANKER_MODEL_NAME = 'cross-encoder/ms-marco-electra-base'
|
7 |
GENERATION_MODEL_NAME = 'mixtral-8x7b-32768'
|
generator/initialize_llm.py
CHANGED
@@ -3,7 +3,7 @@ import os
|
|
3 |
from langchain_groq import ChatGroq
|
4 |
|
5 |
def initialize_generation_llm(input_model_name):
|
6 |
-
os.environ["GROQ_API_KEY"] = ""
|
7 |
|
8 |
model_name = input_model_name
|
9 |
llm = ChatGroq(model=model_name, temperature=0.7)
|
@@ -13,7 +13,7 @@ def initialize_generation_llm(input_model_name):
|
|
13 |
return llm
|
14 |
|
15 |
def initialize_validation_llm(input_model_name):
|
16 |
-
os.environ["GROQ_API_KEY"] = ""
|
17 |
|
18 |
model_name = input_model_name
|
19 |
llm = ChatGroq(model=model_name, temperature=0.7)
|
|
|
3 |
from langchain_groq import ChatGroq
|
4 |
|
5 |
def initialize_generation_llm(input_model_name):
|
6 |
+
os.environ["GROQ_API_KEY"] = "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"
|
7 |
|
8 |
model_name = input_model_name
|
9 |
llm = ChatGroq(model=model_name, temperature=0.7)
|
|
|
13 |
return llm
|
14 |
|
15 |
def initialize_validation_llm(input_model_name):
|
16 |
+
os.environ["GROQ_API_KEY"] = "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"
|
17 |
|
18 |
model_name = input_model_name
|
19 |
llm = ChatGroq(model=model_name, temperature=0.7)
|
retriever/embed_documents.py
CHANGED
@@ -1,4 +1,4 @@
|
|
1 |
-
import os
|
2 |
import logging
|
3 |
from langchain_huggingface import HuggingFaceEmbeddings
|
4 |
from langchain_community.vectorstores import FAISS
|
@@ -16,9 +16,9 @@ def embed_documents(documents, embedding_path="embeddings.faiss"):
|
|
16 |
vector_store = FAISS.from_texts([doc['text'] for doc in documents], embedding_model)
|
17 |
vector_store.save_local(embedding_path)
|
18 |
|
19 |
-
return vector_store
|
20 |
|
21 |
-
|
22 |
import logging
|
23 |
import hashlib
|
24 |
from typing import List, Dict
|
@@ -91,6 +91,6 @@ def _save_metadata(metadata_path: str, metadata: Dict[str, bool]):
|
|
91 |
"""Save metadata to a file."""
|
92 |
import json
|
93 |
with open(metadata_path, "w") as f:
|
94 |
-
json.dump(metadata, f)
|
95 |
|
96 |
|
|
|
1 |
+
'''import os
|
2 |
import logging
|
3 |
from langchain_huggingface import HuggingFaceEmbeddings
|
4 |
from langchain_community.vectorstores import FAISS
|
|
|
16 |
vector_store = FAISS.from_texts([doc['text'] for doc in documents], embedding_model)
|
17 |
vector_store.save_local(embedding_path)
|
18 |
|
19 |
+
return vector_store'''
|
20 |
|
21 |
+
import os
|
22 |
import logging
|
23 |
import hashlib
|
24 |
from typing import List, Dict
|
|
|
91 |
"""Save metadata to a file."""
|
92 |
import json
|
93 |
with open(metadata_path, "w") as f:
|
94 |
+
json.dump(metadata, f)
|
95 |
|
96 |
|