add claude

app.py

@@ -17,6 +17,7 @@ from langchain_community.callbacks import get_openai_callback
 from langchain_community.embeddings import HuggingFaceBgeEmbeddings
 from langchain_community.vectorstores.utils import DistanceStrategy
 from langchain_openai import ChatOpenAI
+from langchain_anthropic import ChatAnthropic
 from langchain_pinecone import PineconeVectorStore
 from pinecone import Pinecone
 import streamlit as st
@@ -46,7 +47,12 @@ OPENAI_CHAT_MODELS = [
     "gpt-3.5-turbo-0125",
     "gpt-4-0125-preview",
 ]
-
+ANTHROPIC_CHAT_MODELS = [
+    "claude-3-opus-20240229",
+    "claude-3-sonnet-20240229",
+    #    "claude-3-haiku-20240229",
+]
+CHAT_MODELS = OPENAI_CHAT_MODELS + ANTHROPIC_CHAT_MODELS
 
 PREAMBLE = "You are an expert analyst. Use the following excerpts from US congressional legislation to respond to the user's query."
 PROMPT_TEMPLATES = {
@@ -354,10 +360,13 @@ def render_sidebar():
     st.checkbox("add legis urls in answer", value=True, key="response_add_legis_urls")
 
     with st.expander("Generative Config"):
-        st.selectbox(label="model name", options=OPENAI_CHAT_MODELS, key="model_name")
+        st.selectbox(label="model name", options=CHAT_MODELS, key="model_name")
         st.slider(
             "temperature", min_value=0.0, max_value=2.0, value=0.0, key="temperature"
         )
+        st.slider(
+            "max_output_tokens", min_value=512, max_value=1024, key="max_output_tokens"
+        )
         st.slider("top_p", min_value=0.0, max_value=1.0, value=1.0, key="top_p")
 
     with st.expander("Retrieval Config"):
@@ -424,9 +433,12 @@ def render_query_tab():
             .assign(answer=prompt | llm | StrOutputParser())
         )
 
-        with get_openai_callback() as cb:
+        if SS["model_name"] in OPENAI_CHAT_MODELS:
+            with get_openai_callback() as cb:
+                SS["out"] = rag_chain.invoke(SS["query"])
+                SS["cb"] = cb
+        else:
             SS["out"] = rag_chain.invoke(SS["query"])
-            SS["cb"] = cb
 
     if "out" in SS:
 
@@ -438,9 +450,11 @@ def render_query_tab():
         with st.container(border=True):
             st.write("Response")
             st.info(out_display)
-        with st.container(border=True):
-            st.write("API Usage")
-            st.warning(SS["cb"])
+
+        if SS["model_name"] in OPENAI_CHAT_MODELS:
+            with st.container(border=True):
+                st.write("API Usage")
+                st.warning(SS["cb"])
 
         with st.container(border=True):
             doc_grps = group_docs(SS["out"]["docs"])
@@ -486,12 +500,26 @@ with st.sidebar:
     render_sidebar()
 
 
-llm = ChatOpenAI(
-    model_name=SS["model_name"],
-    temperature=SS["temperature"],
-    openai_api_key=st.secrets["openai_api_key"],
-    model_kwargs={"top_p": SS["top_p"], "seed": SEED},
-)
+if SS["model_name"] in OPENAI_CHAT_MODELS:
+    llm = ChatOpenAI(
+        model_name=SS["model_name"],
+        temperature=SS["temperature"],
+        openai_api_key=st.secrets["openai_api_key"],
+        model_kwargs={"top_p": SS["top_p"], "seed": SEED},
+        max_tokens=SS["max_output_tokens"],
+    )
+elif SS["model_name"] in ANTHROPIC_CHAT_MODELS:
+    llm = ChatAnthropic(
+        model_name=SS["model_name"],
+        temperature=SS["temperature"],
+        anthropic_api_key=st.secrets["anthropic_api_key"],
+        top_p=SS["top_p"],
+        max_tokens_to_sample=SS["max_output_tokens"],
+    )
+else:
+    raise ValueError()
+
+
 vectorstore = load_pinecone_vectorstore()
 format_docs = DOC_FORMATTERS[SS["prompt_version"]]
 

requirements.txt

@@ -2,17 +2,22 @@ aiohttp==3.9.3
 aiosignal==1.3.1
 altair==5.2.0
 annotated-types==0.6.0
+anthropic==0.18.1
 anyio==4.3.0
+asttokens==2.4.1
 async-timeout==4.0.3
 attrs==23.2.0
+black==24.2.0
 blinker==1.7.0
 cachetools==5.3.2
 certifi==2024.2.2
 charset-normalizer==3.3.2
 click==8.1.7
 dataclasses-json==0.6.4
+decorator==5.1.1
 distro==1.9.0
 exceptiongroup==1.2.0
+executing==2.0.1
 filelock==3.13.1
 frozenlist==1.4.1
 fsspec==2024.2.0
@@ -24,12 +29,15 @@ httpx==0.27.0
 huggingface-hub==0.20.3
 idna==3.6
 importlib-metadata==7.0.1
+ipython==8.22.1
+jedi==0.19.1
 Jinja2==3.1.3
 joblib==1.3.2
 jsonpatch==1.33
 jsonpointer==2.4
 jsonschema==4.21.1
 jsonschema-specifications==2023.12.1
+langchain-anthropic==0.1.1
 langchain-community==0.0.24
 langchain-core==0.1.26
 langchain-openai==0.0.7
@@ -38,6 +46,7 @@ langsmith==0.1.7
 markdown-it-py==3.0.0
 MarkupSafe==2.1.5
 marshmallow==3.20.2
+matplotlib-inline==0.1.6
 mdurl==0.1.2
 mpmath==1.3.0
 multidict==6.0.5
@@ -48,9 +57,16 @@ openai==1.12.0
 orjson==3.9.15
 packaging==23.2
 pandas==2.2.1
+parso==0.8.3
+pathspec==0.12.1
+pexpect==4.9.0
 pillow==10.2.0
 pinecone-client==3.1.0
+platformdirs==4.2.0
+prompt-toolkit==3.0.43
 protobuf==4.25.3
+ptyprocess==0.7.0
+pure-eval==0.2.2
 pyarrow==15.0.0
 pydantic==2.6.2
 pydantic_core==2.16.3
@@ -72,6 +88,7 @@ six==1.16.0
 smmap==5.0.1
 sniffio==1.3.0
 SQLAlchemy==2.0.27
+stack-data==0.6.3
 streamlit==1.31.1
 sympy==1.12
 tenacity==8.2.3
@@ -79,10 +96,12 @@ threadpoolctl==3.3.0
 tiktoken==0.6.0
 tokenizers==0.15.2
 toml==0.10.2
+tomli==2.0.1
 toolz==0.12.1
 torch==2.2.1
 tornado==6.4
 tqdm==4.66.2
+traitlets==5.14.1
 transformers==4.38.1
 typing-inspect==0.9.0
 typing_extensions==4.9.0
@@ -90,5 +109,7 @@ tzdata==2024.1
 tzlocal==5.2
 urllib3==2.2.1
 validators==0.22.0
+watchdog==4.0.0
+wcwidth==0.2.13
 yarl==1.9.4
 zipp==3.17.0