cristiano.hoshikawa/rfp_response_automation
1
0
Fork 0
mirror of https://github.com/hoshikawa2/rfp_response_automation.git synced 2026-03-06 10:11:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

first commit

Browse Source
This commit is contained in:
Cristiano Hoshikawa
2026-01-09 22:56:30 -03:00
parent 774e8184fc
commit a624d09d74
1 changed files with 26 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files

52
files/graphrag_rerank.py
View File

@@ -26,6 +26,32 @@ PASSWORD = "**********"
os.environ["TNS_ADMIN"] = WALLET_PATH os.environ["TNS_ADMIN"] = WALLET_PATH
GRAPH_NAME = "GRAPH_DB_1" GRAPH_NAME = "GRAPH_DB_1"
# =========================
# Global Configurations
# =========================
INDEX_PATH = "./faiss_index"
PROCESSED_DOCS_FILE = os.path.join(INDEX_PATH, "processed_docs.pkl")
chapter_separator_regex = r"^(#{1,6} .+|\*\*.+\*\*)$"
pdf_paths = ['<YOUR_KNOWLEDGE_BASE_FILE>.pdf']
# =========================
# LLM Definitions
# =========================
llm = ChatOCIGenAI(
model_id="meta.llama-3.1-405b-instruct",
service_endpoint="https://inference.generativeai.us-chicago-1.oci.oraclecloud.com",
compartment_id="ocid1.compartment.oc1..aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
auth_profile="DEFAULT",
model_kwargs={"temperature": 0.7, "top_p": 0.75, "max_tokens": 4000},
)
llm_for_rag = ChatOCIGenAI(
model_id="meta.llama-3.1-405b-instruct",
service_endpoint="https://inference.generativeai.us-chicago-1.oci.oraclecloud.com",
compartment_id="ocid1.compartment.oc1..aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
auth_profile="DEFAULT",
)
oracle_conn = oracledb.connect( oracle_conn = oracledb.connect(
user=USERNAME, user=USERNAME,
password=PASSWORD, password=PASSWORD,
@@ -143,30 +169,6 @@ ensure_oracle_text_index(
"RELATION_TYPE", "RELATION_TYPE",
"IDX_REL_" + GRAPH_NAME + "_RELTYPE" "IDX_REL_" + GRAPH_NAME + "_RELTYPE"
) )
# =========================
# Global Configurations
# =========================
INDEX_PATH = "./faiss_index"
PROCESSED_DOCS_FILE = os.path.join(INDEX_PATH, "processed_docs.pkl")
chapter_separator_regex = r"^(#{1,6} .+|\*\*.+\*\*)$"
# =========================
# LLM Definitions
# =========================
llm = ChatOCIGenAI(
model_id="meta.llama-3.1-405b-instruct",
service_endpoint="https://inference.generativeai.us-chicago-1.oci.oraclecloud.com",
compartment_id="ocid1.compartment.oc1..aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
auth_profile="DEFAULT",
model_kwargs={"temperature": 0.7, "top_p": 0.75, "max_tokens": 4000},
)
llm_for_rag = ChatOCIGenAI(
model_id="meta.llama-3.1-405b-instruct",
service_endpoint="https://inference.generativeai.us-chicago-1.oci.oraclecloud.com",
compartment_id="ocid1.compartment.oc1..aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
auth_profile="DEFAULT",
)
embeddings = OCIGenAIEmbeddings( embeddings = OCIGenAIEmbeddings(
model_id="cohere.embed-multilingual-v3.0", model_id="cohere.embed-multilingual-v3.0",
@@ -534,8 +536,6 @@ def save_indexed_docs(docs):
# Main Function # Main Function
# ========================= # =========================
def chat(): def chat():
pdf_paths = ['FSGIU+OBCS+SD+121125+FINAL.pdf']
already_indexed_docs = load_previously_indexed_docs() already_indexed_docs = load_previously_indexed_docs()
updated_docs = set() updated_docs = set()