pinecone test

app.py

@@ -1,21 +1,47 @@
+from langchain_community.vectorstores import Pinecone
 from langchain_openai import ChatOpenAI
-from langchain_core.messages import HumanMessage, SystemMessage
-
+from pinecone import Pinecone as PineconeClient
 import streamlit as st
 
 st.set_page_config(layout="wide", page_title="LegisQA")
 
-st.write("hello")
-llm = ChatOpenAI(
-    openai_api_key=st.secrets["openai_api_key"]
-)
-
-messages = [
-    SystemMessage(
-        content="You are a helpful assistant that translates English to French."
-    ),
-    HumanMessage(
-        content="Translate this sentence from English to French. I love programming."
-    ),
+
+CONGRESS_GOV_TYPE_MAP = {
+    "hconres": "house-concurrent-resolution",
+    "hjres": "house-joint-resolution",
+    "hr": "house-bill",
+    "hres": "house-resolution",
+    "s": "senate-bill",
+    "sconres": "senate-concurrent-resolution",
+    "sjres": "senate-joint-resolution",
+    "sres": "senate-resolution",
+}
+
+OPENAI_CHAT_MODELS = [
+    "gpt-3.5-turbo-0125",
+    "gpt-4-0125-preview",
 ]
-st.write(llm.invoke(messages))
+
+
+def load_pinecone_vectorstore():
+    model_name = "BAAI/bge-small-en-v1.5"
+    model_kwargs = {"device": "cpu"}
+    encode_kwargs = {"normalize_embeddings": True}
+    emb_fn = HuggingFaceBgeEmbeddings(
+        model_name=model_name,
+        model_kwargs=model_kwargs,
+        encode_kwargs=encode_kwargs,
+        query_instruction="Represent this question for searching relevant passages: ",
+    )
+    pinecone = PineconeClient(api_key=st.secrets["pinecone_api_key"])
+    vectorstore = Pinecone.from_existing_index(
+        index_name=st.secrets["pinecone_index_name"],
+        embedding=emb_fn,
+    )
+    return vectorstore
+
+
+
+
+docs = vectorstore.similarity_search_with_score("artificial intelligence")
+st.write(docs)

requirements.txt

@@ -1,30 +1,44 @@
+aiohttp==3.9.3
+aiosignal==1.3.1
 annotated-types==0.6.0
 anyio==4.3.0
+async-timeout==4.0.3
+attrs==23.2.0
 certifi==2024.2.2
 charset-normalizer==3.3.2
+dataclasses-json==0.6.4
 distro==1.9.0
 exceptiongroup==1.2.0
+frozenlist==1.4.1
 h11==0.14.0
 httpcore==1.0.4
 httpx==0.27.0
 idna==3.6
 jsonpatch==1.33
 jsonpointer==2.4
+langchain-community==0.0.24
 langchain-core==0.1.26
 langchain-openai==0.0.7
 langsmith==0.1.7
+marshmallow==3.20.2
+multidict==6.0.5
+mypy-extensions==1.0.0
 numpy==1.26.4
 openai==1.12.0
 orjson==3.9.15
 packaging==23.2
+pinecone-client==3.1.0
 pydantic==2.6.2
 pydantic_core==2.16.3
 PyYAML==6.0.1
 regex==2023.12.25
 requests==2.31.0
 sniffio==1.3.0
+SQLAlchemy==2.0.27
 tenacity==8.2.3
 tiktoken==0.6.0
 tqdm==4.66.2
+typing-inspect==0.9.0
 typing_extensions==4.9.0
 urllib3==2.2.1
+yarl==1.9.4