LangServe deploy attempt 1

Dockerfile

@@ -16,6 +16,6 @@ COPY ./app ./app
 
 RUN poetry install --no-interaction --no-ansi
 
-EXPOSE 8080
+EXPOSE 7860
 
-CMD exec uvicorn app.server:app --host 0.0.0.0 --port 8080
+CMD exec uvicorn app.server:app --host 0.0.0.0 --port 7860

app/server.py

@@ -0,0 +1,56 @@
+from fastapi import FastAPI
+from fastapi.responses import RedirectResponse
+from langserve import add_routes
+from langchain.vectorstores import FAISS
+from langchain.llms import HuggingFaceHub
+import os
+from langchain.prompts import ChatPromptTemplate
+from langchain_core.runnables import RunnablePassthrough, RunnableParallel
+from langchain.schema import StrOutputParser
+from langchain.embeddings.huggingface import HuggingFaceEmbeddings
+
+app = FastAPI()
+
+hf_llm = HuggingFaceHub(
+    repo_id="mistralai/Mixtral-8x7B-Instruct-v0.1",
+    huggingfacehub_api_token=os.environ["HF_TOKEN"],
+    task="text-generation",
+    model_kwargs={"temperature":0.01, "max_new_tokens" : 250}
+)
+
+embedding_model_id = 'WhereIsAI/UAE-Large-V1'
+embeddings_model = HuggingFaceEmbeddings(model_name=embedding_model_id)
+
+faiss_index = FAISS.load_local("../langserve_index", embeddings_model)
+retriever = faiss_index.as_retriever()
+# retriever = faiss_index.as_retriever(search_kwargs={"k": 2})
+
+prompt_template = """\
+Use the provided context to answer the user's question. If you don't know the answer, say you don't know.
+
+Context:
+{context}
+
+Question:
+{question}"""
+
+rag_prompt = ChatPromptTemplate.from_template(prompt_template)
+
+entry_point_chain = RunnableParallel(
+    {"context": retriever, "question": RunnablePassthrough()}
+)
+rag_chain = entry_point_chain | rag_prompt | hf_llm | StrOutputParser()
+
+@app.get("/")
+async def redirect_root_to_docs():
+    return RedirectResponse("/docs")
+
+
+# Edit this to add the chain you want to add
+add_routes(app, rag_chain, path="/rag")
+
+if __name__ == "__main__":
+    import uvicorn
+
+    uvicorn.run(app, host="0.0.0.0", port=8000)
+    # uvicorn.run(app, host="0.0.0.0", port=7860)

langserve_index/index.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1474088fe4c981d0e0b77b81ec35863e3d177cc59cb262f60b2cc067cd06a0b1
+size 13050

pyproject.toml

@@ -0,0 +1,23 @@
+[tool.poetry]
+name = "langserve_test"
+version = "0.1.0"
+description = ""
+authors = ["Your Name <you@example.com>"]
+readme = "README.md"
+packages = [
+    { include = "app" },
+]
+
+[tool.poetry.dependencies]
+python = "^3.11"
+uvicorn = "^0.23.2"
+langserve = {extras = ["server"], version = ">=0.0.30"}
+pydantic = "<2"
+
+
+[tool.poetry.group.dev.dependencies]
+langchain-cli = ">=0.0.15"
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"