初探 Mem0

! pip install mem0ai langchain_openai

from langchain_openai import OpenAIEmbeddings,ChatOpenAI

openai_embeddings = OpenAIEmbeddings(
    model="BAAI/bge-m3",
    openai_api_base="https://api.siliconflow.cn/v1",
    openai_api_key=API_KEY,
    dimensions=1024
)
llm = ChatOpenAI(
    base_url="https://api.siliconflow.cn/v1", 
    api_key=API_KEY,                  
    model="Qwen/Qwen3-14B"  
)

docker pull qdrant/qdrant

docker run -p 6333:6333 -p 6334:6334 \
    -v $(pwd)/qdrant_storage:/qdrant/storage:z \
    qdrant/qdrant

config = {
   "llm": {
       "provider": "langchain",
       "config": {
           "model": llm,
       }
   },
    "embedder": {
        "provider": "langchain",
        "config": {
            "model": openai_embeddings
        }
    },
    "vector_store": {
        "provider": "qdrant",
        "config": {
            "host": "localhost",
            "port": 6333,
            "embedding_model_dims":1024
        }
    },
}

from mem0 import Memory
m = Memory.from_config(config)
messages = [
    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
    {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
    {"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
]

# 插入：
m.add(messages, user_id="alice", metadata={"category": "movies"})

# Get all memories
all_memories = m.get_all(user_id="alice")

# Get a single memory by ID
specific_memory = m.get("MEMORY-ID")

# Search Memories
related_memories = m.search(query="What do you know about me?", user_id="alice")


# Delete a memory by id
m.delete(memory_id="MEMORY-ID")
# Delete all memories for a user
m.delete_all(user_id="alice")

m.reset() # Reset all memories

custom_fact_extraction_prompt = """
Please only extract entities containing customer support information, order details, and user information. 
Here are some few shot examples:

Input: Hi.
Output: {{"facts" : []}}

Input: The weather is nice today.
Output: {{"facts" : []}}

Input: My order #12345 hasn't arrived yet.
Output: {{"facts" : ["Order #12345 not received"]}}

Input: I'm John Doe, and I'd like to return the shoes I bought last week.
Output: {{"facts" : ["Customer name: John Doe", "Wants to return shoes", "Purchase made last week"]}}

Input: I ordered a red shirt, size medium, but received a blue one instead.
Output: {{"facts" : ["Ordered red shirt, size medium", "Received blue shirt instead"]}}

Return the facts and customer information in a json format as shown above.
"""

config = {
  ...,
    "custom_fact_extraction_prompt": custom_fact_extraction_prompt,
}