2023-10-31 01:10:48 +00:00
|
|
|
import os
|
|
|
|
|
|
|
|
|
|
import weaviate
|
|
|
|
|
from langchain.retrievers.weaviate_hybrid_search import WeaviateHybridSearchRetriever
|
2024-01-02 20:32:16 +00:00
|
|
|
from langchain_community.chat_models import ChatOpenAI
|
docs[patch], templates[patch]: Import from core (#14575)
Update imports to use core for the low-hanging fruit changes. Ran
following
```bash
git grep -l 'langchain.schema.runnable' {docs,templates,cookbook} | xargs sed -i '' 's/langchain\.schema\.runnable/langchain_core.runnables/g'
git grep -l 'langchain.schema.output_parser' {docs,templates,cookbook} | xargs sed -i '' 's/langchain\.schema\.output_parser/langchain_core.output_parsers/g'
git grep -l 'langchain.schema.messages' {docs,templates,cookbook} | xargs sed -i '' 's/langchain\.schema\.messages/langchain_core.messages/g'
git grep -l 'langchain.schema.chat_histry' {docs,templates,cookbook} | xargs sed -i '' 's/langchain\.schema\.chat_history/langchain_core.chat_history/g'
git grep -l 'langchain.schema.prompt_template' {docs,templates,cookbook} | xargs sed -i '' 's/langchain\.schema\.prompt_template/langchain_core.prompts/g'
git grep -l 'from langchain.pydantic_v1' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.pydantic_v1/from langchain_core.pydantic_v1/g'
git grep -l 'from langchain.tools.base' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.tools\.base/from langchain_core.tools/g'
git grep -l 'from langchain.chat_models.base' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.chat_models.base/from langchain_core.language_models.chat_models/g'
git grep -l 'from langchain.llms.base' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.llms\.base\ /from langchain_core.language_models.llms\ /g'
git grep -l 'from langchain.embeddings.base' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.embeddings\.base/from langchain_core.embeddings/g'
git grep -l 'from langchain.vectorstores.base' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.vectorstores\.base/from langchain_core.vectorstores/g'
git grep -l 'from langchain.agents.tools' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.agents\.tools/from langchain_core.tools/g'
git grep -l 'from langchain.schema.output' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.output\ /from langchain_core.outputs\ /g'
git grep -l 'from langchain.schema.embeddings' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.embeddings/from langchain_core.embeddings/g'
git grep -l 'from langchain.schema.document' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.document/from langchain_core.documents/g'
git grep -l 'from langchain.schema.agent' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.agent/from langchain_core.agents/g'
git grep -l 'from langchain.schema.prompt ' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.prompt\ /from langchain_core.prompt_values /g'
git grep -l 'from langchain.schema.language_model' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.language_model/from langchain_core.language_models/g'
```
2023-12-12 00:49:10 +00:00
|
|
|
from langchain_core.output_parsers import StrOutputParser
|
2024-01-03 21:28:05 +00:00
|
|
|
from langchain_core.prompts import ChatPromptTemplate
|
docs[patch], templates[patch]: Import from core (#14575)
Update imports to use core for the low-hanging fruit changes. Ran
following
```bash
git grep -l 'langchain.schema.runnable' {docs,templates,cookbook} | xargs sed -i '' 's/langchain\.schema\.runnable/langchain_core.runnables/g'
git grep -l 'langchain.schema.output_parser' {docs,templates,cookbook} | xargs sed -i '' 's/langchain\.schema\.output_parser/langchain_core.output_parsers/g'
git grep -l 'langchain.schema.messages' {docs,templates,cookbook} | xargs sed -i '' 's/langchain\.schema\.messages/langchain_core.messages/g'
git grep -l 'langchain.schema.chat_histry' {docs,templates,cookbook} | xargs sed -i '' 's/langchain\.schema\.chat_history/langchain_core.chat_history/g'
git grep -l 'langchain.schema.prompt_template' {docs,templates,cookbook} | xargs sed -i '' 's/langchain\.schema\.prompt_template/langchain_core.prompts/g'
git grep -l 'from langchain.pydantic_v1' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.pydantic_v1/from langchain_core.pydantic_v1/g'
git grep -l 'from langchain.tools.base' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.tools\.base/from langchain_core.tools/g'
git grep -l 'from langchain.chat_models.base' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.chat_models.base/from langchain_core.language_models.chat_models/g'
git grep -l 'from langchain.llms.base' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.llms\.base\ /from langchain_core.language_models.llms\ /g'
git grep -l 'from langchain.embeddings.base' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.embeddings\.base/from langchain_core.embeddings/g'
git grep -l 'from langchain.vectorstores.base' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.vectorstores\.base/from langchain_core.vectorstores/g'
git grep -l 'from langchain.agents.tools' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.agents\.tools/from langchain_core.tools/g'
git grep -l 'from langchain.schema.output' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.output\ /from langchain_core.outputs\ /g'
git grep -l 'from langchain.schema.embeddings' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.embeddings/from langchain_core.embeddings/g'
git grep -l 'from langchain.schema.document' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.document/from langchain_core.documents/g'
git grep -l 'from langchain.schema.agent' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.agent/from langchain_core.agents/g'
git grep -l 'from langchain.schema.prompt ' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.prompt\ /from langchain_core.prompt_values /g'
git grep -l 'from langchain.schema.language_model' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.language_model/from langchain_core.language_models/g'
```
2023-12-12 00:49:10 +00:00
|
|
|
from langchain_core.runnables import RunnableParallel, RunnablePassthrough
|
2023-10-31 01:10:48 +00:00
|
|
|
|
|
|
|
|
# Check env vars
|
|
|
|
|
if os.environ.get("WEAVIATE_API_KEY", None) is None:
|
|
|
|
|
raise Exception("Missing `WEAVIATE_API_KEY` environment variable.")
|
|
|
|
|
|
|
|
|
|
if os.environ.get("WEAVIATE_ENVIRONMENT", None) is None:
|
|
|
|
|
raise Exception("Missing `WEAVIATE_ENVIRONMENT` environment variable.")
|
|
|
|
|
|
|
|
|
|
if os.environ.get("WEAVIATE_URL", None) is None:
|
|
|
|
|
raise Exception("Missing `WEAVIATE_URL` environment variable.")
|
|
|
|
|
|
|
|
|
|
if os.environ.get("OPENAI_API_KEY", None) is None:
|
|
|
|
|
raise Exception("Missing `OPENAI_API_KEY` environment variable.")
|
|
|
|
|
|
|
|
|
|
# Initialize the retriever
|
|
|
|
|
WEAVIATE_INDEX_NAME = os.environ.get("WEAVIATE_INDEX", "langchain-test")
|
|
|
|
|
WEAVIATE_URL = os.getenv("WEAVIATE_URL")
|
|
|
|
|
auth_client_secret = (weaviate.AuthApiKey(api_key=os.getenv("WEAVIATE_API_KEY")),)
|
|
|
|
|
client = weaviate.Client(
|
|
|
|
|
url=WEAVIATE_URL,
|
|
|
|
|
additional_headers={
|
|
|
|
|
"X-Openai-Api-Key": os.getenv("OPENAI_API_KEY"),
|
|
|
|
|
},
|
|
|
|
|
)
|
|
|
|
|
retriever = WeaviateHybridSearchRetriever(
|
|
|
|
|
client=client,
|
|
|
|
|
index_name=WEAVIATE_INDEX_NAME,
|
|
|
|
|
text_key="text",
|
|
|
|
|
attributes=[],
|
|
|
|
|
create_schema_if_missing=True,
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
# # Ingest code - you may need to run this the first time
|
|
|
|
|
# # Load
|
|
|
|
|
# loader = WebBaseLoader("https://lilianweng.github.io/posts/2023-06-23-agent/")
|
|
|
|
|
# data = loader.load()
|
|
|
|
|
#
|
|
|
|
|
# # Split
|
|
|
|
|
# text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=0)
|
|
|
|
|
# all_splits = text_splitter.split_documents(data)
|
|
|
|
|
#
|
|
|
|
|
# # Add to vectorDB
|
|
|
|
|
# retriever.add_documents(all_splits)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# RAG prompt
|
|
|
|
|
template = """Answer the question based only on the following context:
|
|
|
|
|
{context}
|
|
|
|
|
Question: {question}
|
|
|
|
|
"""
|
|
|
|
|
prompt = ChatPromptTemplate.from_template(template)
|
|
|
|
|
|
|
|
|
|
# RAG
|
|
|
|
|
model = ChatOpenAI()
|
|
|
|
|
chain = (
|
|
|
|
|
RunnableParallel({"context": retriever, "question": RunnablePassthrough()})
|
|
|
|
|
| prompt
|
|
|
|
|
| model
|
|
|
|
|
| StrOutputParser()
|
|
|
|
|
)
|
